Physical AI Brief

Current automated pipelines for audio-visual Question Answering (QA) generally adopt a ``video-caption-QA'' paradigm. However, these methods typically segment videos into short clips and generate separate descriptions for audio and visual modalities. This decoupled processing severs inherent associations between sounds and their visual sources, while independent clip processing often causes inconsistent descriptions of the same entity across segments. Furthermore, coupling long-text comprehension and QA synthesis into a single step often restricts models to localized events, yielding questions lacking long-term temporal connections and deep cross-modal reasoning. To address these issues, we propose an automated data engine featuring two mechanisms: (1) \textbf{Entity-Anchored Video Scripting} transforms videos into structured scripts, comprising summaries, main entity lists, and segment-wise audio-visual descriptions. The entity list serves as a global prior to ensure cross-segment referential consistency and reconstruct audio-visual associations. (2) \textbf{Clue-Guided QA Generation} prompts models to first mine cross-segment, multimodal clues from the script, and subsequently generate QA pairs based on these high-value clues. Leveraging this pipeline, we construct the instruction-tuning dataset \textbf{OmniVideo-100K} and a human-verified test set, \textbf{OmniVideo-Test}. Fine-tuning VITA-1.5, Qwen2.5-Omni-7B and Qwen3-Omni-30B on OmniVideo-100K yields performance gains of up to 20.59% on OmniVideo-Test, demonstrating strong generalization (up to 12.64% improvements) across established benchmarks like Daily-Omni and JointAVBench.

When humans see a bird, they recognize far more than just "bird" -- they see a head, wings, and talons, a structured assembly of reusable parts that can be identified across every bird they have ever seen. We ask whether a self-supervised visual model can discover the same compositional structure on its own. To this end, we propose RATS (Register Attention Transformers), which decomposes the classification token into N learnable register tokens that route patch information through an L->N->N->L bottleneck via a three-step compress-communicate-broadcast attention. The N registers are partitioned across the H attention heads, so that registers assigned to different heads do not interact with each other. Without auxiliary losses or part annotations, each register spontaneously specializes into a proto-semantic region whose emerging structure resembles object parts. RATS surpasses all baselines by +12 mIoU on average across five segmentation benchmarks, with consistent gains on ADE20K (+1.11 mIoU) and COCO (+0.2 AP^m). Its register dictionary further exhibits part-level consistency and semantic proximity across related categories. Our results suggest that RATS may provide a useful architectural prior for structured and interpretable visual representation learning.

Building trustworthy medical multimodal large language models (MLLMs) is critical for reliable clinical decision support. Existing medical hallucination benchmarks mainly focus on data collection, but often ignore where hallucinations originate within the reasoning process. We find that hallucination sources vary across samples: errors may arise from visual misrecognition, incorrect medical knowledge recall, or flawed reasoning integration. To enable source-level hallucination diagnosis, we introduce ClinHallu, a benchmark for stage-wise hallucination diagnosis in medical MLLM reasoning. ClinHallu contains 7,031 validated instances, where each instance is augmented with a structured reasoning trace decomposed into Visual Recognition, Knowledge Recall, and Reasoning Integration. We also use stage-replacement interventions to measure how correcting specific stages affects the final answer. Beyond evaluation, we show that trace-supervised fine-tuning reduces stage-wise hallucinations. ClinHallu provides a fine-grained hallucination testbed for diagnosing and mitigating reasoning failures in medical MLLMs. The benchmark is publicly available at https://github.com/alibaba-damo-academy/ClinHallu.

Cooperative multi-objective multi-agent reinforcement learning (MOMARL) models team decision making under multiple, potentially conflicting objectives. In this setting, conflicts arise not only across objectives but also across agents with different observations, roles, and contributions. We propose Preference Coordinated Multi-agent Policy Optimization (PCMA), which learns coordinated agent-specific preferences to enable complementary trade-offs among agents. Theoretically, we formulate cooperative MOMARL as a team-optimal game and show that, under suitable conditions, preference diversity can induce team improvement through a first-order improvement decomposition. Experiments on multiple cooperative MOMA environments and a practical traffic-control scenario show that PCMA improves both performance and trade-off coordination.

Reinforcement learning with verifiable rewards (RLVR) has successfully elicited the reasoning capabilities of large language models, motivating its extension to multimodal scenarios. Existing methods primarily focus on improving the visual coverage of reasoning traces and mitigating visual hallucinations, but underestimate the semantic inconsistency between the reasoning process and the final answer. In this paper, we delve into thinking-answer inconsistency in RLVR for large vision-language models (LVLMs), showing thorough analyses of rollouts collected throughout Group Relative Policy Optimization (GRPO) training process and post-RLVR evaluation outputs that this issue persists during training and remains present during inference. Motivated by the analysis, we propose Consistency-Oriented Reasoning Alignment (CORA), which introduces thinking-answer semantic consistency into RLVR through a lightweight plug-and-play consistency reward model, and further incorporates Hybrid Reward Advantage Splitting (HRAS) to stably coordinate task and consistency optimization. Extensive experiments across representative multimodal reasoning benchmarks and mainstream LVLMs show that CORA improves task performance while effectively mitigating thinking-answer inconsistency, leading to more faithful reasoning traces.

We study a \emph{max-risk} objective for active learning in a multi-group mean estimation $d$-armed bandits: a learner adaptively allocates a budget of $T$ samples across $d$ groups to minimize the worst-case uncertainty index $\max_{k\in[d]}σ_k^2/n_k$, where $σ_k$ is the standard deviation of the distribution of arm $d$, and $n_k$ is the number of times arm $d$ is sampled. We develop a local minimax framework and prove the first general lower bound for this objective, valid for any finite-variance hypothesis class. The bound separates difficulty into three orthogonal factors: a \emph{budget} term, a \emph{heteroscedasticity} index measuring how unevenly the uncertainty is spread across arms, and a model-dependent complexity measure, the \emph{Variance Local Curvature} ($\mathrm{VLC}$), which captures how much information a local change of variance creates inside the hypothesis class. For smooth classes, the $\mathrm{VLC}$ is a reparametrization of a variance--Fisher information, with closed-form values for common families. Benchmarking against the strongest available upper bound shows near-optimality up to logarithmic factors in broad regimes, and pinpoints a systematic gap in highly heterogeneous instances. Our proof introduces two key ingredients: a loss-induced $\ell_1$ geometry on the decision space, and a representation-based instance generator that reduces hard-instance construction to an explicit random matrix calculation.

LLM agents are increasingly built not as single model calls, but as scaffolded systems that combine reasoning, memory, reflection, action execution, and learning. While such scaffolds often improve performance, they are often embedded in tightly coupled pipelines, making it difficult to isolate component contributions, compare alternative designs, or understand how module interactions shape agent behavior. We introduce AgentSpec, a modular specification framework that represents embodied agents as typed compositions of reusable policy components with standardized interfaces. AgentSpec standardizes the interfaces among perception, memory, reasoning, reflection, action, and optional learning, enabling components to be swapped and recombined under controlled conditions. We instantiate this framework across DeliveryBench, ALFRED, MiniGrid, and RoboTHOR, and analyze reasoning, memory, reflection, and reinforcement-learning modules across model backbones. Our results show that agent performance is governed by scaffold compatibility and interaction effects rather than isolated module strength. In particular, structured multi-granularity memory improves long-horizon state tracking, reasoning and memory interact non-uniformly across environments, reflection trades off correction and cost, and RL-trained policies compose best when optimized with deployment-time scaffold structure. AgentSpec provides a controlled foundation for studying, comparing, and designing composable LLM agents. Our code, baselines and interactive playground are publicly available at https://agentspec-embodied.github.io.

Large language models increasingly serve as execution engines for agentic systems, yet they still consume context through a sequential text interface. This creates a mismatch with modern structured agent workflows, in which independent branches explore subtasks, retrieve evidence, or generate candidate solutions before a final synthesis step. Existing systems typically merge these branches by concatenating their textual outputs, which discards the parallel structure and incurs redundant prefill computation. In this work, we introduce Parallel-Synthesis, a plug-and-play framework that enables a synthesizer to directly consume the KV caches produced by parallel worker agents. Parallel-Synthesis combines a cache mapper that calibrates independently generated branch caches with a fine-tuned synthesizer adapter that enables generation from this non-sequential cache interface. We train Parallel-Synthesis using data that exposes the synthesizer to parallel cache contexts, teaches aggregation across cached branches, and distills reasoning behavior from standard text-concatenation-based synthesis. Across nine downstream datasets spanning math, science QA, code generation, GAIA, and multi-agent database diagnosis, Parallel-Synthesis matches or outperforms text-based synthesis on seven datasets and remains close on the other two. It also reduces time-to-first-token by 2.5x-11x, suggesting that direct cache-based synthesis is a promising interface for more native and efficient synthesis over parallel agent branches.

Knowledge editing systems must update selected facts while preserving nearby but irrelevant behavior. This paper studies this problem in a memory-assisted setting where an edit memory is retrieved at inference time and a parameter-efficient adapter corrects the model's object preference. We argue that the central design question is not only how to write an edit, but also when to suppress it. We introduce \method{}, a route-specialized dual-adapter editor. A relevance router first decides whether a prompt should receive an edit memory. Routed prompts use an edit adapter trained to prefer the new object over the original object; unrouted non-direct prompts use a separate locality adapter trained to preserve or restore the original-object preference. We evaluate \method{} on three 1,000-case protocols, \cf{}, \zsre{}, and \mquake{}, under the same memory protocol and two 7B/8B base models. On Llama-3.1-8B-Instruct, \method{} obtains the best overall probability-preference accuracy on all three benchmarks: 0.8180 on \cf{}, 0.8946 on \zsre{}, and 0.9922 on \mquake{}. The same trend holds on Qwen3-8B. Router ablations show that the relevant memory boundary differs across datasets: a lexical neural router is safest on \cf{}, while BGE embedding routing is better on \zsre{} and \mquake{}. Component and module ablations show that the gain mainly comes from separating edit injection from off-route suppression rather than from simply increasing LoRA capacity.

Long-form video generation requires recurring subjects to remain consistent across various shots, viewpoints, motions, and scene transitions. Existing temporal decomposition methods improve scalability by generating videos shot by shot. However, they mainly focus on optimizing plausible next-shot continuations without verifying whether the historical memory preserves identity-critical subject evidence. Consequently, as generation proceeds, recurring subjects may be diluted, overwritten, or forgotten. In this paper, we propose Memento, a subject-reconstruction-guided framework that treats subject preservation as an explicit identity grounding problem, based on the premise that a memory bank faithfully preserving a subject should support reconstructing that subject from memory alone. Specifically, Memento jointly trains autoregressive next-shot generation with memory-based subject reconstruction, recovering target appearances using historical memory and global story captions. To disentangle long-range subject evidence from short-range cues, Memento introduces a dual-query memory mechanism, where one query retrieves identity-relevant memory and the other selects short-context keyframes for coherent continuation. Additionally, a subject-aware cinematic data pipeline provides precise reconstruction supervision via consistent, pronoun-free subject descriptions. Experiments demonstrate that Memento achieves state-of-the-art performance in long-term subject consistency, cross-shot coherence, and visual quality.

Robot learning from real-world demonstrations is currently constrained by data scaling. Universal Manipulation Interface (UMI) provides an efficient robot-free data collection interface, yet current UMI-style pipelines often collect redundant demonstrations and lack global scene context. To improve data efficiency, we present EgoGuide, a collection interface that records synchronized wrist and head/egocentric observations and couples them with online visual-geometric data quality guidance. We also introduce a Gated Egocentric Residual Policy for robust learning from a viewpoint-varying egocentric camera, allowing head/egocentric context to correct ambiguous local observations while preserving stable wrist-view control. Real-world experiments show that EgoGuide reduces the required number of data episodes and improves data efficiency. The residual policy further improves robustness under visual occlusion. Project Page: https://silicx.github.io/EgoGuide

The identification of optimal structures within vast arrays of interconnected data necessitates significant sampling- and computational effort. Learning and leveraging underlying signal dependencies can improve efficiency and predictive capabilities considerably, but the ubiquity of nonlinear statistical relations amplifies the complexity of such undertakings. In this paper, we develop novel generic and adaptive strategies equipped with routines for graph-based causal reward modeling, analytic reproducing kernel methods, and Taylor approximation of functional processes. We establish theoretical performance guarantees sublinear in time and linear in data volume over time. Our analyses cover robustness to a multitude of uncertainties arising from noise interference, gradual model convergence, and solution space mismatch. The framework's general appeal is substantiated by a minimalistic set of conditions or reliance on prior estimates, while various outlined modifications address specific or extended settings. To demonstrate practical effectiveness, we conduct numerical experiments using both benchmarked synthetic and real-world transportation datasets.

Control-function instrumental variable estimators need a first-stage residual, not merely a first-stage prediction. High-capacity first stages can interpolate treatment and leave too little residual information for the outcome equation. We study Adaptive Anisotropic Instrumental Heat Flow (A-IHF), a deterministic graph-diffusion residual extractor for flexible control functions. A-IHF treats treatment as a signal on a graph of first-stage features, uses pilot diffusion to detect large treatment jumps, attenuates conductance across those jumps, and computes the generated control with a sparse graph resolvent. Its observational selection rule uses only $(Z,X)$, combining graph generalized cross-validation, roughness, residualized-treatment relevance, and graph-admissibility filtering. The analysis decomposes error into structural leakage, residual attenuation, and residualized treatment variation, yielding finite-sample bounds, graph-admissibility rates under latent piecewise-smooth geometry, and finite-path selection calibration. Across 54 synthetic benchmark cells with tuned graph, kernel, tree, boosting, series, and neural control-function baselines, guarded observational A-IHF has the lowest average structural-response MSE; the A-IHF family beats the best non-A-IHF baseline in 32 cells. Performance is strongest when the graph captures piecewise-smooth first-stage structure.

Event-based saliency prediction has gained attention recently, as combining event cameras with saliency estimation can act as an upstream stage that naturally improves the efficiency of downstream eventbased perception at the edge. However, current approaches are either neuromorphic, underperforming on event-based saliency benchmarks, or too heavy for resource-constrained edge applications due to their reliance on transformers or 3D convolutions. Drawing inspiration from efficient convolutional modules, SED and aiming to exploit the temporal information in event data, we propose a lightweight network, trained through knowledge distillation, built on a Depthwise Spatio-Temporal Block (DSTconv) -- a factorization of the 3D depthwise separable convolution. Relative to its teacher, our model reduces the model size from 180 MB to 0.32 MB (562x) and the parameter count from 45M to 81k (554x), while matching or outperforming it on the N-DHF1K and N-UCF Sports datasets. Moreover, it generalizes strongly beyond its training distribution, transferring from synthetic to real event data where a model trained from scratch fails.

Verifier-driven self-DPO is a common recipe for self-improving production visual-language models. In this setup, a frozen verifier scores candidate generations, the top- and bottom-scoring candidates form a preference example, and DPO updates the learner. The deployment-time assumption is monotone: a stronger verifier should yield a stronger student. We show that this assumption can fail because verifier quality is highly task-specific. On a four-rung open-source verifier ladder across MathVista, MMMU, and BLINK, the same verifiers that are above-threshold and improve a Qwen-3-VL-2B student on MathVista become sub-threshold on MMMU, where their task-rubric accuracy drops to 8% to 23%. In this regime, every verifier we tested silently regresses the student, producing drops of 3.4 to 10.9 percentage points below the frozen baseline while the DPO training loss continues to decrease. The regression replicates on a second student, Qwen-2.5-VL-3B. Moreover, within the failure regime, damage is confidence-inverted: the more accurate-but-still-wrong verifier causes larger regression than a near-random verifier, suggesting that progress-gated replay amplifies confidently wrong preference pairs. We give a compact mechanistic explanation via a variance theorem for progress-gated replay and its direction-mismatch failure mode. The deployment message is operational rather than purely diagnostic: before running any verifier-driven loop, teams should measure target-task rubric accuracy, rank verifiers by target-task rubric quality rather than parameter count, and treat diminishing returns in above-threshold regimes as a verifier-side compute budget cap.

In this work, we propose StereoGeo, an end-to-end network-based approach for stereo camera calibration. Our method estimates the focal lengths and gravity directions of the left and right cameras, as well as the relative extrinsic transformation relating them. Existing methods often rely on calibration patterns in structured environments or address only a single camera configuration, being limited to either intrinsic or extrinsic estimation, and depending on a multi-view setups. StereoGeo extends the GeoCalib algorithm, integrating deep neural network feature extraction with a differentiable optimizer. Extensive experiments on real-world benchmarks demonstrate that StereoGeo achieves competitive performance for intrinsic calibration and provides accurate stereo extrinsic estimation, outperforming existing methods that are limited to monocular settings. The dataset used in this work is partially publicly available at https://github.com/meddourimane/StereoGeo-dataset.

Floating-base robots must balance under rigid contact constraints while interacting safely with humans. Existing whole-body control~(WBC) frameworks allocate the full joint space to locomotion or rely on fixed-gain impedance feedback that accumulates steady-state error under sustained physical human--robot interaction~(pHRI) forces. This paper extends the authors' fixed-base two-layer Impedance MPC to floating-base platforms through a three-level architecture: a centroidal MPC plans contact forces over a 500\,ms horizon; a priority-driven WBC layer resolves balance into joint torques through contact-consistent null-space projection; and the residual null space is governed by a receding-horizon quadratic program~(QP) that predicts and rejects pHRI disturbances using a Kalman-augmented state. A contact-consistent feedback linearization reduces the arm end-effector plant to a double integrator with a \emph{constant} state matrix within each contact mode, enabling offline precomputation of the QP cost and ${\geq}1$\,kHz operation. A covariance-inflation protocol preserves the disturbance estimate across contact-mode switches, guaranteeing zero steady-state error under bounded constant pHRI loads, and an Impedance Equivalence Theorem shows the infinite-horizon limit recovers a classical task-space impedance law whose effective mass, damping, and stiffness adapt to posture and contact configuration. Simulations on a 17-DOF biped and the Unitree G1 humanoid validate the design.

We show that the three movements of Beethoven's "Moonlight Sonata" (Op. 27 No. 2) instantiate three distinct machine learning architectures -- not by analogy, but by structural correspondence. Through computational analysis of the score (entropy, Jensen-Shannon divergence, dissonance, hand distributional overlap, self-similarity matrices, temporal memory decay, and contextual pitch embeddings), we establish four counterintuitive findings: (1) perceived musical "temperature" is governed by throughput, not distributional width; (2) the lightest movement carries the highest dissonance; (3) the movements implement streaming, recurrent, and periodic positional encoding memory architectures; and (4) the same pitch class acquires different contextual identities across movements, analogous to contextual vs.static embeddings in NLP -- and unsupervised clustering recovers the tonal structure without music-theoretic input. We construct a reverse sonification (decoding analytical features back into MIDI) and quantify the chirality of the encode-decode cycle: what distributions preserve and sequential ordering destroys. Prompted by a listener's observation that the decoded piece sounds like "mirror isomers that can't be superimposed," the chirality measurement reveals reconstruction loss increasing monotonically with n-gram order. Bootstrap baselines and subsample checks confirm all movements carry sequential information above noise, though raw values are confounded by sample size. Cross-domain comparison shows natural language has higher chirality than music, reflecting stronger sequential constraints.

Dexterous hands must simultaneously track precise finger trajectories and maintain safe, compliant contact -- objectives in tension for any fixed-gain controller. We present an actuator-agnostic Impedance Model Predictive Control (Impedance MPC) framework for dexterous fingers, instantiating the constant-$A_d$ offset-free architecture established for physical human-robot interaction (pHRI); its stability, recursive-feasibility, and input-to-state-stability guarantees are inherited by preserving the architectural assumptions. An algebraic feedforward reduces the tendon transmission -- hydraulic, cable, pneumatic, twisted-string, or series-elastic -- to a constant-coefficient double integrator, so the QP cost inverse is precomputed offline and a 10-step receding-horizon quadratic program runs at 500\,Hz while enforcing hard constraints on contact force (ISO/TS 15066), actuation limits, and jerk. An encoder-only augmented-Kalman disturbance state drives steady-state error to zero under any constant contact load. On a hydraulically actuated finger -- the worked example platform, adding pressure and cavitation constraints -- the 500\,Hz Kalman MPC attains 0.5\,mrad RMS, 0.1\,mrad steady-state, and 6.6\,mrad peak deflection under 1.5\,Nm contact: 183$\times$, 1500$\times$, and 23$\times$ better than classical impedance. The realized first-move stiffness (18$\to$323\,Nm/rad with update rate) is independently verified. The architecture scales to a 16-DOF LEAP Hand MuJoCo simulation, recovering from 2.5\,N grasp-load disturbances within 0.7\,s.

Wearable devices and smartphones generate rich behavioural time series that can support proactive health interventions, yet systematic comparisons of modern forecasting architectures for these data are lacking. In particular, it remains unclear how models generalise across populations, how different architectures respond to participant-level fine-tuning and how forecasting accuracy degrades across multi-day horizons. We benchmark six deep learning architectures, two zero-shot Foundation Models (FM) and statistical baselines on three public datasets encompassing over 800 participants, reporting per-feature metrics for step counts, screen time and sleep duration across 1-8 day horizons. We further conduct a per-feature personalisation study across all six architectures and assess FM transferability across dataset sizes and temporal granularities. Our key findings are: (i) no single architecture dominates, PatchTST leads among trained models while the three runners-up (TCN, MLP, Transformer) show no meaningful performance difference; (ii) the FM TimesFM matches or exceeds trained models zero-shot, especially in low-data regimes and (iii) participant-level fine-tuning reduces per-feature RMSE by 16-60\%, with sleep benefiting most and step counts least. These results provide practical guidance on architecture selection, FM applicability and personalisation strategies for mobile health forecasting. To the best of our knowledge, this is the first study to jointly evaluate modern deep learning, FMs and personalisation for multi-horizon behavioural forecasting from wearables.

This study presents a statistical and machine learning framework for characterizing a hydrogen-based multi-energy system (H-MES) using one year of high-resolution operational data. Statistical analysis revealed a binary operation driven by renewable surplus, with solar irradiance explaining 45.7% of rank-based variance in hydrogen production, a large effect by conventional standards. Only high-irradiance periods triggered meaningful electrolyzer engagement, while electricity demand exerted a weaker inverse suppression effect ($ε^2 = 0.126$). Multiple regression confirmed electrolyzer power as the dominant linear predictor, with a synergistic solar-wind interaction. Notably, Random Forest analysis ranked wind output first in predictive importance despite its weak bivariate correlation (r = 0.167), revealing non-linear dynamics invisible to parametric methods. A sequence model exploited strong 24-hour autocorrelation (r = 0.845) for operational forecasting, while a reinforcement learning agent optimized hydrogen revenue dispatch. The core contribution is demonstrating that statistical and machine learning approaches are complementary for H-MES modeling and control.

Online group chats are social spaces with local conversational norms that are rarely stated explicitly. The ability and willingness of LLM-based agents to recognize and adapt to these norms remains mostly unexplored. We introduce LoSoNA, a benchmark for local social norm adaptation in multi-party chat. Each scenario gives a subject model a curated group-chat transcript in which non-subject participants demonstrate a hidden local norm, followed by a final elicitor turn that forces a response revealing whether the subject has inferred that norm. We evaluate eight frontier and open-weight models under four prompting conditions that vary how explicitly the model is told to treat the prior conversation as evidence for how it should answer. Naive prompting remains limited for most models; explicit norm-aware prompting helps unevenly, with Gemini 3.1 Pro reaching $84.2\%$ and Claude Fable 5 reaching $81.6\%$, while several other models show small gains or regressions. LoSoNA contributes to recent calls for evaluating LLM social capabilities by testing whether models can infer local conversational norms from precedent and use them in a one-turn group-chat response.

Post-training INT8 (W8A8) quantization of diffusion transformers is widely deployed as a speed optimization, yet on consumer Ampere GPUs it is frequently slower than the FP8 and NF4 alternatives it is meant to beat. We trace this to a software artifact: the production "INT8" forward quantizes weights and activations only to immediately dequantize them back to bf16 and run a bf16 matrix multiply, never engaging the GPU's INT8 tensor cores, so the hardware's compute advantage is left entirely unrealized. We close this gap with a single fused Triton INT8 GEMM (int8xint8->int32 on Ampere tensor cores, with per-token x per-channel dequantization and bias folded into the epilogue, autotuned per GEMM shape) dropped into the Ideogram 4.0 diffusion transformer's linear layers in place of the dequantize-to-bf16 path. In the kernel, the int8xint8->int32 accumulation is bit-exact against torch._int_mm and the dequantized output matches the reference at cosine similarity 1.0 with no NaNs, running 2.8-4.2x faster than bf16 per GEMM. End to end it delivers a ~1.1x (~9-10%) speedup at 768px, and at 1024px it generates an image in 156.5 s on a single RTX 3090, faster than the single-card NF4 (164.5 s) and FP8 (172.9 s) baselines, at no measurable quality cost on these point estimates (PickScore/CLIPScore). INT8 thus goes from the slowest variant to the fastest, and 1024px becomes single-GPU feasible. The primary speed criterion (beat FP8, by ~9.5%) is comfortably met; the NF4 margin (~4.9%, single-run n=4) is within run-to-run variance we did not quantify and is best read as consistent with meeting the stretch target. We close with an honest deployment map: the win is specific to consumer Ampere, and on A100 and B200 the same kernel loses to those cards' fast native bf16/FP8 paths.

Transformer-based neural operators have shown remarkable performance for approximating solution operators of partial differential equations on complex geometries. However, existing approaches implicitly assume a fixed domain size, which limits their ability to generalize at inference. In this work, we investigate domain extension, namely zero-shot inference on spatial domains that are significantly larger than those encountered during training. We argue that this setting fundamentally requires spatial locality and translation equivariance. We propose to implement this locality via a decomposable bias in the attention logits computation, enabling finely controllable locality while remaining fully decomposable into query-key inner products and directly compatible with optimized attention kernels. Combined with rotary positional embeddings, it enables expressive embeddings with controllable spatial support without altering the transformer architecture. We empirically show that our approach substantially improves zero-shot generalization to larger domains across two PDE benchmarks and a 3D industrial atmospheric flow application. Our code and datasets are available at https://github.com/cerea-daml/domain-extension.

AI-assisted software development has moved from line-level autocomplete to agents that can plan changes, edit files, and submit pull requests with limited human supervision. Open-source software, however, evolves through a process designed for humans: contributor agreements, codes of conduct, and review norms all assume a legally accountable person who can attest to provenance and answer reviewer questions. Autonomous and semi-autonomous AI contributors strain those assumptions, and the 2025-2026 record of agent-driven incidents, AI-generated nuisance volume, and platform-level shutdowns shows that the gap is operationally consequential. Several open-source organisations have responded with contribution policies, but the result is fragmented, and its alignment with emerging AI governance frameworks (EU AI Act, NIST AI RMF with the UC Berkeley Agentic AI Profile, ISO/IEC 42001 and 23894) is unmapped at the contribution level. We compare policies across six organisations (SymPy, LLVM, matplotlib, OpenInfra, the Apache Software Foundation, and the Linux Foundation) using Most-Similar Systems Design with indicator-based coding and process tracing for SymPy and LLVM. From this we derive a six-dimensional taxonomy (disclosure, responsibility, human oversight, licensing, enforcement, maintainer workload), an ordinal Policy Maturity Score, and a mapping of documented agent incidents onto the dimensions each policy fails to govern. Aligning the dimensions with the regulatory frameworks above identifies overlapping gaps neither side currently closes, and we close by sketching the shape of a harmonised tiered framework and the empirical evaluation needed to calibrate it.

Large Audio-Language Models (LALMs) have shown strong performance on a wide range of audio understanding tasks, yet they still struggle with complex audio reasoning. A practical way to improve such capabilities is post-training, whose effectiveness critically depends on the quality and diversity of training data. However, existing audio-language datasets often contain substantial redundancy, where many samples are highly similar in acoustic content and thus provide overlapping supervisory signals. Such redundancy not only increases annotation cost, but also limits corpus diversity and reduces the effectiveness of post-training. To address this issue, we propose a redundancy-aware data construction pipeline for building reasoning-oriented supervision for LALMs. Specifically, we first perform acoustic similarity-based deduplication across raw audio datasets to improve corpus diversity. We then integrate existing audio captions and question-answer pairs into a unified multiple-choice format. Based on these unified annotations, we leverage Qwen3-30B to generate chain-of-thought (CoT) rationales for reasoning-oriented supervision. Based on this pipeline, we construct AudioDER, a reasoning-oriented post-training dataset containing approximately 191k samples spanning sound, speech, and music. Each sample consists of an audio clip, a multiple-choice question, four answer candidates, an audio caption, and a CoT rationale. Extensive experiments show that post-training on AudioDER consistently improves the performance of Qwen2-Audio-7B-Instruct on multiple audio reasoning benchmarks, including MMAU-mini, MMSU, and MMAR. We hope AudioDER can serve as a valuable resource for advancing audio reasoning research and the development of more capable LALMs.

LLM agent systems increasingly run as long-lived autonomous runtimes: scheduling jobs, calling tools, maintaining memory, and pushing results to humans. We present a longitudinal study of silent failures in one such system: a personal-assistant agent runtime in continuous production since March 2026, with roughly 40 scheduled jobs, 8 LLM providers, a tool-governance proxy, and a knowledge-base memory plane, defended by 4,286 unit tests and 827 governance checks. Over eight weeks we documented 22 incidents with full root-cause postmortems, in which one meta-pattern -- a failure whose error signal never reaches a human in actionable form -- manifested at least 28 times. We derive a five-class, mechanism-oriented taxonomy: (A) environment and platform quirks, (B) design-assumption mismatches, (C) error swallowing and dilution, (D) chained hallucination and fabrication, (E) operational omission and forensic blind spots. Class D is unique to LLM systems and the most dangerous: the system does not merely fail to report an error -- the LLM transforms it into fluent, plausible narrative delivered to the user. We term this fail-plausible: gray failure's differential observability escalated -- the observer is not just blind, it is convincingly lied to by the failure itself. Three findings: about 70% of silent failures were caught by human user-view observation, not tests or audits; a retrospective audit of 15 incidents found 0% ex-ante prevention but 87% regression blocking -- audits are regression engines, not prediction engines; incident latency (13 hours to 60 days) tracks failure mechanism, not code complexity -- the longest-lived failures lived in the seams between components, where no test runs. We describe the resulting defense framework and distill design principles for agent systems whose failures are loud, attributable, and boring. All postmortems and artifacts are public.

Generative dynamics models enable planning in challenging robotic systems, but safe deployment requires reliably detecting policy-induced out-of-distribution (OOD) transitions. Existing methods typically treat the learned dynamics as fixed and attach post hoc support surrogates. We show that these surrogates can fail when the dynamics are locally insensitive to critical action choices: unsupported control actions may produce latent predictions that resemble demonstrated transitions, suppressing OOD signals despite large true predictive errors. To address this, we introduce support-conditioned control-sensitivity regularization, which promotes sensitive local response to control input changes in learned dynamics in high-support training regions. This preserves control-induced variation while limiting unstable extrapolation due to weak empirical support. Experiments in vision-based obstacle avoidance, manipulation, and real-robot navigation show improved OOD detection and safer closed-loop planning.

Efficient route optimization play a vital role in ensuring both safety and punctuality in railway operations. It is very crucial particularly in heterogeneous multi-gauge railway networks with varying train speed, stopping pattern, infrastructure compatibility constraints increase coordination complexity. In single-track systems these challenges are further intensify due to all trains to share the same track and requires frequent track switching.Stochastic disruptions events including blocked tracks, blocked trains, engine failure and speed slowdowns introduces additional unpredictability in operations and deviate the timetable. However, existing studies predominantly focuses on high-level timetabling, omitting operational details such as track switching coordination. As a result leaving decision to human operators, increasing safety risks into railway operations. This study proposes a framework based on temporal planning for dynamic route optimization and disruption management in heterogeneous railway systems. The framework formulates railway operations as a temporal planning problem using PDDL 2.1 with explicitly modeling gauge compatibility constraints and diverse disruption scenarios. It generates conflict-free timestamped operational plans specifying both optimized schedules and executable action sequences. To evaluate the proposed framework, we developed a benchmark problem set with 200 instances using up to 1,000 track points and 120 trains. Two state-of-the-art temporal planners and a plan validator were employed to assessed the framework. The experimental results demonstrate that the framework effectively generates temporal operational plans for heterogeneous railway systems and handles multi-gauge constraints, disruptions, and reduces dependence on manual decision making.

Granting LLMs direct control over costly, irreversible scientific experiments leads to unsafe exploration and unstable performance, but discarding LLM creativity entirely sacrifices significant optimization potential. We introduce CARE (Controlling LLM-Generated Policies through Auditable Review of Evidence in Scientific Experimentation), an auditable controller for high-throughput experimentation (HTE) optimization that keeps a non-LLM incumbent optimizer as the default action path while using LLMs to revise challenger ranking policies. Before each outcome is revealed, a public-evidence intervention gate compares the challenger with the incumbent. It authorizes the challenger's selection only when the evidence available before selection supports the change, with the decision recorded in the audit log. CARE outperforms all other evaluated methods on Minerva/Olympus and ChemLex benchmarks, with final-best improving from 80.0 to 88.5 on Minerva/Olympus and from 83.9 to 92.1 on ChemLex, relative to the public incumbent. Our experiments indicate that LLM self-evolution is more reliable when it expands the proposal space under an auditable controller, rather than directly choosing experiments.

Identifying persuasive rhetorical cues is critical across domains, from detecting information manipulation and improving AI safety to advancing public health communication. We propose Persuasion Index (PI), a taxonomy of 15 dimensions grounded in persuasion theories from psychology and communication, and one transparent implementation using 55 sub-features built from lexicons and rule-based detectors. The taxonomy is modular: individual detectors can be replaced while preserving the theoretical structure. By evaluating PI on four public datasets varying in domain, style, and outcome measures, we show that PI provides a shared feature space for interpreting rhetorical patterns associated with persuasion-related outcomes. Linear models show that PI features carry meaningful predictive signal while remaining computationally lightweight. Dimension-level analyses reveal recurring associations between PI dimensions and persuasion outcomes across datasets, while also highlighting topic- and stance-specific variation. We release PI as an open-source package and web interface for principled and auditable analysis of human and AI-mediated communication.

When applying Group Relative Policy Optimization (GRPO) for GUI Grounding, rollouts are sampled from a single screenshot view; groups often become either all failures on difficult instances or all successes on easy ones, yielding no useful relative advantage. We propose VISTA (View-Consistent Self-Verified Training), a GRPO-based training framework that constructs each comparison group from multiple target-preserving views of the same GUI instance.Each view is generated by a crop that keeps the target element visible and remaps its box exactly, so model rollouts are compared across semantically equivalent but geometrically different inputs. To stabilize short coordinate generation without turning reinforcement learning into unconditional imitation, VISTA further adds a self-verified cross-view anchor: an oracle answer optimized with an advantage-weighted loss, excluded from the group baseline and activated only when the model has produced a maximum-reward rollout. Across five GUI-grounding benchmarks and multiple Qwen backbones, VISTA consistently improves grounding accuracy.On ScreenSpot-Pro, it raises Qwen3-VL 4B/8B/30B-A3B from 55.5/52.7/53.7 to 63.4/65.8/67.0. Robustness analyses further show higher worst-view accuracy and lower prediction flip rates.

Large language models (LLMs) are increasingly deployed as planners for autonomous agents in household environments. While existing benchmarks evaluate whether LLM-generated plans execute successfully, they overlook a critical type of failure: latent failures. Unlike immediate failures that trigger instant feedback at execution time and enable timely correction, latent failures do not immediately halt plan execution but silently compromise goal achievement. In severe cases, they cause irreversible harm. To address this gap, we introduce SIMMER, a benchmark for evaluating latent failures in LLM planning through a human-curated symbolic world model grounded in the kitchen domain. SIMMER defines a world model comprising 77 actions, 262 unique objects, and approximately 46,800 possible interactions that are semantically realistic, derived from real-world cooking scripts. It then leverages a state machine executor that validates plans against the world model and detects immediate precondition violations, latent hazards, and irreversible failures. Experiments across six LLMs show that even frontier models achieve at most 17% error-free plans. Moreover, up to 56% of plans contain latent failures, the majority of which lead to irreversible consequences. We further demonstrate that explicit state reasoning via counterfactual foresight simulation can reduce latent failures by up to 72% and irreversible cases by up to 75%, suggesting a promising direction for more robust LLM planners.

A central role of personal-agent memory is to turn stored information and prior interactions into future-oriented assistance. In daily use, useful cues come from what the agent observes and how the user interacts with the agent, and the agent must carry them forward from the current request to similar future tasks. Existing memory benchmarks usually test dialogue recall or task improvement in isolation, leaving the trajectory from streaming observations to later assistance largely untested. We introduce StreamMemBench, a streaming benchmark that constructs a two-step task sequence around each evidence anchor from EgoLife egocentric streams. The initial task tests evidence use, while the follow-up task tests whether feedback and interaction experience are reused. Four metrics diagnose evidence recall, initial evidence use, feedback incorporation, and follow-up reuse. Experiments with eight memory systems across two backbones show that current systems often fail to use observed evidence or turn feedback into reliable follow-up behavior, even when evidence is stored or feedback is incorporated locally. StreamMemBench is publicly available at https://github.com/landian60/StreamMemBench.

Constitutive artificial neural networks (CANNs) provide interpretable material model discovery, but have so far been used in stress-supervised settings based on apparent stress-strain data from homogeneous tests. Because each test samples only a narrow loading path and provides homogenized rather than local stress information, robust discovery typically requires multiple loading modes to constrain the multidimensional response. This is challenging for soft biological tissues, where repeated testing, damage, and sample variability limit reliable information from a single specimen. Here, we combine CANNs with the stress-unsupervised full-field discovery framework EUCLID to identify sparse hyperelastic laws directly from displacement fields and reaction forces in one heterogeneity-inducing loading case. CANN-EUCLID minimizes equilibrium imbalance with sparsity-promoting regularization selecting compact active terms, without local stress measurements or a prescribed law. We evaluate the approach on isotropic and anisotropic benchmarks with prescribed ground-truth laws. When the ground truth is representable by the chosen CANN basis, our method recovers the correct terms with near-exact accuracy, including exponential terms with embedded parameters. When it is not contained in the basis, the method retains shared terms and approximates missing contributions using available basis functions. Generalization depends strongly on sampled deformation states: exponential strain-stiffening terms can be recovered accurately when sufficiently probed, but can produce large extrapolation errors when the stiffening regime lies outside the sampled domain. Forward FE validation simulations show that the discovered behavior accurately replicates the ground truth. These results establish stress-unsupervised CANN discovery as a promising framework for interpretable full-field constitutive model identification.

Sociable weaver nests function as complex ecological structures offering thermoregulatory microhabitats and sustaining diverse species; however, datasets used in prior studies lack fine-grained 3D structural detail. Producing usable and accurate 3D weaver nest data is challenging due to their irregular geometry and integration with complex host vegetation. We bridge this gap with an open-access, 1.4 TB multimodal drone dataset of 104 nest-bearing trees, comprising 27,945 RGB images, 111,780 multispectral images, approximately 781 million 3D points, and expert-annotated semantic segmentation labels. We benchmark semantic segmentation using KPConv, RandLA-Net, and Point Transformer V3, with PT-v3 achieving an mIoU of 86.35% on the test set. While the results demonstrate strong performance for transformer-based and point-wise methods, they also highlight architecture-dependent challenges, particularly for convolution-based approaches such as KPConv. By uniquely combining spectral, spatial, and structural information, the presented dataset advances 3D reconstruction, segmentation, and classification algorithms, enabling ecological applications from nest volume estimation to species conservation, and serves as a demanding benchmark that exposes architecture-dependent performance under extreme class imbalance.

Robotics manipulation research increasingly focuses on two-finger parallel grippers for their effectiveness, affordability, and ease of teleoperation. Grippers are nonetheless limited by their form factor, often requiring bimanual setups even for simple reorientation tasks. Anthropomorphic hands are a more natural platform for dexterous robot learning -- closer to the human hand, and capable of learning from human video -- yet they remain hard to use in learning research: even where open and accessible hand hardware exists, the software for control, simulation, teleoperation, and retargeting is scattered in one-off code bases, and largely disconnected from the robot-learning ecosystem. In this work, we introduce the \orca~learning stack, an open-source research stack for dexterity as a first-class robot learning domain. Our \orca~stack unifies low-level control, simulation, teleoperation from a range of consumer platforms, and hand retargeting, behind a single interface, and integrates natively with popular robot-learning frameworks such as \lerobot, so dexterous hand researchers can leverage the same data, training, and evaluation pipelines used for non-dexterous robot learning. We demonstrate a complete end-to-end workflow, collecting expert demonstrations of an in-hand reorientation task by teleoperation with a consumer-grade VR headset, training an autonomous policy with \lerobot, and evaluating the learned policy in a fully reproducible and observable setup. We open-source the entire stack as a shared, reproducible foundation for dexterous-manipulation research.

Robots under autonomous operation may require decisions based on evidence that is no longer visible. We study \emph{delayed-evidence} tasks, where an early cue disappears before a later decision point, so visually similar observations can require different actions. In these settings, the current observation is not a sufficient state for control. We introduce TRAjectory-routed Causal Evidence (TRACE), a memory framework for visuomotor imitation policies. TRACE stores task-relevant visual and robot-state evidence, such as object identity, target choice, or route-dependent state, in a fixed-size latent memory that remains bounded over long episodes. Instead of indexing memory by raw time or manually provided task labels, TRACE uses \emph{path signatures}: compact, order-sensitive features of the executed robot-state trajectory. These signatures do not store the visual cue itself; rather, they provide trajectory-conditioned keys for writing and retrieving the evidence stored when the cue was visible. When the robot later reaches an ambiguous observation, the policy conditions on TRACE memory to recover the missing context and choose the correct branch. TRACE attaches through lightweight adapters to policies, without changing the policy backbone, action head, or imitation objective. Across real-world long-horizon manipulation tasks with visually ambiguous branch points, TRACE improves branch selection and task success over alternative baselines, including short-history and recurrent memory. Project page: https://jeong-zju.github.io/trace

Recent visual imitation learning systems have widely adopted multi-camera setups with wrist-mounted cameras as the de facto standard. However, manipulation from a single global view remains challenging, as the policy should capture fine-grained interaction details and identify task-relevant regions without local wrist views. To address this challenge, we present Spatially Conditioned Diffusion Policy (SCDP), a diffusion-based visuomotor policy that achieves precise and robust manipulation in a single-camera setting. Our key idea is that end-effector trajectories can serve as visual attention anchors that reflect task-relevant regions. Building on this idea, SCDP consists of two key components: (i) a visual encoder that produces multi-scale feature maps to capture both broader context and fine-grained visual features, and (ii) a spatial conditioning module that samples point-wise features along intermediate end-effector trajectories in the diffusion loop. Extensive simulation experiments show that SCDP consistently outperforms strong single-view baselines and achieves performance comparable to multi-camera baselines. Real-world experiments further demonstrate precise manipulation and robustness to visual distractors, highlighting the potential of single-camera imitation learning.

Principal Component Analysis (PCA) preserves variance, not the information needed to detect rare catastrophic events. This paper proves the existence of a {\it Risk Shadow}: PCA can retain over 99.9999 percent of total variance while completely erasing all signal about rare, high-impact failures. When this happens, even the best possible classifier operating on the PCA representation reduces to a constant predictor. The root cause is a fundamental mismatch between variance maximization and tail risk awareness. To break the shadow, we introduce Expectile PCA (ExPCA) and Tail-Preserving PCA (TP-PCA), two methods that reweight the data covariance toward high-impact events. We prove theoretically that ExPCA strictly outperforms PCA in retaining rare-event information, and we validate our claims on synthetic data and a real-world credit card fraud detection benchmark. Our results call for a fundamental rethinking of variance-based dimensionality reduction in high-stakes decisions.

Object placement is a fundamental component of aerial manipulation tasks, yet existing systems typically require the desired placement position to be specified explicitly in metric coordinates. Such interfaces are not intuitive and require users to reason about coordinate frames and scene geometry, making them difficult to use in practical deployments. In contrast, humans often communicate spatial goals through a combination of language and pointing gestures. Inspired by this observation, we present AERMANI-PLACE, a framework for language-guided object placement with aerial manipulators. Given a scene image and a natural language instruction, an image editing model generates a modified version of the scene containing a visual marker that indicates where the object should be placed. This marker is then grounded into the physical environment using depth observations to recover a metric place point, after which a placement trajectory is generated and executed by the aerial manipulator. We evaluate the proposed approach on a test set of 100 language-guided placement tasks and demonstrate successful execution on a real aerial manipulation platform. Experimental results show that the proposed method reliably infers placement locations from language instructions with an average success rate of 87\% on the test-set and transfers effectively to real-world aerial manipulation with an average success rate of 72\%. Video: https://youtu.be/SgwwgLBsv0g

LLM-based guardrails have emerged as a highly effective defense against prompt injection and jailbreak attacks in autonomous agents. However, we reveal that the very reasoning and task-following capabilities enabling this protection introduce a novel vulnerability: attackers can inject crafted data to trap the guardrail in extended reasoning loops, effectuating a systematic denial-of-service (DoS) attack. To systematically expose this threat, we design a beam-search optimization framework that crafts natural-language payloads to maximize guardrail reasoning length, utilizing an LLM proposer guided by a strategy bank. Based on the observation of guardrail's schema-following nature, we also provide another attack framework driven by mechanism-aware structural mutations with less computational load. The attack efficacy is systematically evaluated in two parts. First, in standalone evaluations, the attack generalizes across diverse guardrail architectures, safety templates, and agent benchmarks. Payloads optimized on a single open-source surrogate successfully transfer to eight leading model backbones (e.g., Claude, GPT, Gemini, DeepSeek, and Qwen), achieving a 13--63$\times$ token amplification. Second, in end-to-end real-world agent deployments (web, desktop, code, and multi-agent systems), the attack reveals up to a 148$\times$ latency amplification. We show that a single poisoned document can saturate shared guardrail infrastructures, effectively starving co-located agents and paralyzing the entire system. By uncovering this availability flaw, our work underscores the urgent need to develop cost-bounded, reasoning-robust guardrails.

AI evaluations are widely used for testing and understanding progress. However, the diverse evaluators bring with them inconsistencies that challenge analysis and comparison. First, results are saved in incompatible formats, scattered across leaderboards, papers, blog posts, evaluation harness logs, and custom repositories. Second, results are created by different evaluation frameworks, which produce divergent scores for nominally identical evaluations and record metadata inconsistently, hindering comparison, cross-community evaluation science, cost reduction, and reuse. We introduce Every Eval Ever, the first shared schema and community-crowdsourced repository for AI evaluation results. The schema standardizes how evaluations are represented in a unified, single JSON document. It is source-agnostic by design, ingesting results from evaluation harnesses and papers alike, and optionally stores per-instance outputs for fine-grained analysis. We contribute: (i) a community-governed metadata schema with a companion instance-level schema, the first standardization effort of its kind; (ii) automatic converters from popular formats, evaluation harnesses, and leaderboards to the unified schema; and (iii) a crowdsourced community database hosted on Hugging Face, currently spanning to date 22,235 models, 2,273 unique benchmarks, and 31 evaluation formats.

Physical adversarial attacks on vision systems are typically studied through scene manipulation, such as adversarial patches or projections, where the adversary controls what the camera observes. Camera-side attacks using stickers or auxiliary optics have also been explored, but they treat attacks as image-space perturbations from designed patterns. This misses how physical imperfections interact with scene-dependent lighting and optics. We identify a threat: passive lens-side damage that is persistent yet trigger-conditioned, producing optical artifacts that bias geometric inference under particular visual conditions. We instantiate this threat through Scratch-induced Lens Adversarial Streak Hijacking SLASH, a physical-world attack caused by small scratches on a camera lens or protective cover. Scratches interact with bright light sources and specular reflections to create structured streak artifacts that distort depth cues. Since the perturbation is fixed in the optical path but triggered by the scene, it is both persistent and selective. We formulate the attack in optical space, model the scratch pattern as a trigger-conditioned optical channel, and optimize one fixed configuration across diverse viewing conditions. We evaluate SLASH on monocular depth estimation and monocular 3D object detection in digital and real-world settings. Under the fixed-scratch constraint, directional depth shifts reach up to 32% relative error for monocular depth estimation, with consistent effects on monocular 3D object detection. Physical experiments confirm transfer to real camera recordings, inducing depth shifts above the model's natural prediction baseline. These findings reveal an attack surface where benign-looking hardware imperfections act as latent, scene-triggered adversarial mechanisms, challenging assumptions about physical robustness and motivating defenses for secure vision systems.

Large Language Models (LLMs) are undergoing a fundamental transformation from conversational generators into integrated AI systems capable of reasoning, action, memory, and self-improvement. We conceptualize this transition as a shift from Chatbot to Digital Colleague: from conversational answers to persistent work. We organize this transition along two tightly coupled dimensions. First, at the cognitive core level, LLMs are advancing from Chatbot-era "fast thinking" systems driven by next-token prediction toward Thinking LLMs that leverage inference-time computation, Chain-of-Thought reasoning, reflection, process supervision, and reinforcement learning to support more deliberate and reliable cognition. Second, at the tool-augmented task execution level, LLMs are progressing from tool-calling Agents that invoke external resources in an ad hoc manner toward OpenClaw-style workstation systems (OpenClaw) equipped with persistent Workspaces, skills, verification loops, and governance. The "Workspace + Skill" paradigm makes episodic tool use colleague-like via state persistence, reusable procedures, task closure, and experience reuse. We examine data construction shifts from instruction-response pairs to State-Action-Observation trajectories and evaluation from static benchmarks to sandboxed, auditable, self-evolving AI ecosystems.

Predicting the Kohn-Sham Hamiltonian with machine learning can accelerate density functional theory while retaining access to molecular orbitals, energy levels, and electronic-structure observables that energy-only surrogates cannot resolve. Yet element-wise agreement with the converged Hamiltonian, an implicit fixed point of the self-consistent field iteration, does not determine the occupied subspace that governs orbital energies and densities. Here we present HamEvo, a neural operator that learns the single-step self-consistent update and returns the converged Hamiltonian as its fixed point. HamEvo is pre-trained on intermediate self-consistent trajectories and calibrated at equilibrium with density-matrix supervision. Across benchmarks from MD17 to drug-like QMugs, HamEvo lowers Hamiltonian errors by 35-49% over direct-regression and deep-equilibrium baselines, and predicts QMugs HOMO and LUMO energies with mean absolute errors of 0.036 and 0.053 eV, near the 1 kcal/mol chemical-accuracy scale. Few-shot fine-tuning with only 20 reference conformations extends HamEvo to molecules of up to 122 atoms, well beyond the size range covered by pre-training. With thermal molecular-dynamics sampling, HamEvo captures temperature-dependent HOMO-LUMO gap renormalization beyond the harmonic approximation. Inference is up to 242 times faster than conventional DFT.

We present a recipe-controlled decoder audit (RCDA) for structural transductive knowledge-graph completion (KGC). The audit asks a simple reporting question: before attributing gains to an encoder or training recipe, what changes when the decoder is swapped under the same recipe? Using ComplEx and DistMult as the primary controlled pair, with targeted RotatE/TransE spot-checks, we evaluate seven benchmarks. On five standard KGs, ComplEx-vs-DistMult differences are modest but consistent under our recipe (+0.005 to +0.012 MRR), whereas CompGCN-style encoder effects vary more by dataset. On small KGs, decoder effects become the main diagnostic: Kinship shows a stable ComplEx advantage of +0.143 MRR (6 seeds), while UMLS favours ComplEx by +0.022 MRR in a clean 6-seed server rerun but reverses in an earlier provenance variant. We therefore treat small-KG decoder choice as recipe- and provenance-sensitive rather than as a fixed dataset winner. We further show that decoder choice interacts with encoder depth on WN18RR, and that under our recipe L=0 ComplEx on YAGO3-10 reaches 0.6971 +/- 0.0048 MRR at d=128. The result is a compact audit protocol: report matched decoder rows, log small-KG provenance, and sweep decoder x depth before making encoder-level claims.

A growing line of work equips large language model (LLM) agents with graph neural networks (GNNs) as callable tools, assuming the agent exercises judgment over when and how much to rely on such a tool. We test this directly. We expose a frozen GNN to a ReAct-style LLM agent as an explicit tool and measure, on node classification over a text-attributed graph (ogbn-arxiv, replicated on WikiCS), whether the agent uses the tool or merely obeys it. We find the agent does not exercise judgment: its predictions agree with the raw GNN's 97.6-99.2% of the time (5 seeds), collapsing into a GNN parrot that adopts the tool's output wholesale and bypasses its own reasoning. Sweeping backbone capability (Qwen2.5 0.5B-7B), the deference is not a weak-model artifact: among models able to invoke the tool, agreement rises with capability (0.60 to 0.98 from 1.5B to 7B). Crucially, the cost of deference does not shrink as capability grows and grows where alternatives emerge: a per-node oracle over the available actions beats the parrot by 0.09-0.18 at 3B and 0.12-0.22 at 7B, roughly doubling at high homophily, because the parrot is pinned to the frozen GNN while the agent's alternatives improve; at 7B a simple neighbour-label tool overtakes the GNN at high homophily (0.81 vs 0.71) yet the agent still defers. A simple selective-invocation gate recovers about half of that high-homophily gap (0.71 to 0.83) but yields no net global gain, and held-out estimates bound the best achievable gate over standard test-time features to at most a third of the oracle headroom: reliable selective invocation looks limited by available information, not merely router design. Our results are a cautionary measurement: evaluations of agent+tool systems cannot assume the agent adds judgment on top of the tool, and selective invocation must be designed in rather than expected to emerge from scale.

Industrial anomaly detection suffers from limited data, making cross-domain generalization particularly challenging. Generalist Anomaly Detection (GAD) aims to train a unified model on a source domain that can effectively detect anomalies in unseen target domains. In the initial semantic feature space, strong entanglement between anomalies and object categories or defect types hinders effective generalization across domains. Recent works address this issue by projecting features into a residual space; however, such methods primarily increase cross-domain overlap for normal features, while anomalous features remain specific to object categories, defect types and data domains, leading to poor alignment and generalization. To address this limitation, we propose Value-order Decomposition (VOD), a simple yet effective technique that bridges \textbf{three types of generalization gaps} across object categories, defect types (including real and synthetic defects), and data domains. VOD disentangles and suppresses object-category-, defect-type-, and domain-specific information, promoting alignment within normal and abnormal samples while preserving their separability, thereby enabling robust generalization across the three gaps. Leveraging the strong alignment between real and synthetic defects within the same object, we perform anomaly detection using only normal and synthetic-abnormal reference, and effectively generalize to unseen real defect types. Experiments on diverse industrial and medical benchmarks demonstrate that our method, using a simple cut-and-paste anomaly simulation strategy, achieves strong generalization across the three gaps.

Large language model (LLM) reasoning is ephemeral: chains of thought vanish with the context window, pruned search branches leave no record, and memory buffers cannot be diffed, merged, or audited. Every other complex software process (code, infrastructure, data, experiments) is version-controlled; reasoning is not. We introduce GitOfThoughts, which stores an agent's reasoning tree as a git repository: every scored thought is a commit, scores are notes, outcomes are tags, and retrieval is "git log" over the agent's own history. This makes reasoning replayable, auditable, and mergeable across agents at near-zero engineering cost. We then ask the harder question: does memory, in any substrate, actually improve accuracy? Across five substrates (none, markdown, vector, graph, git), two benchmarks, two model scales, and pre-registered replications, the answer for novel problems is no. No memory format reliably helps, and a promising early result collapsed under its own pre-registered replication. Memory pays only above what we call the copyability threshold: when the retrieved case is a near-duplicate of the current problem (similarity >~ 0.8), accuracy jumps sharply; below it, nothing. The gain is answer retrieval, not method transfer: a 4.5x larger model doubles the near-duplicate payoff yet still cannot extract a transferable method from a worked example. The only general lever we find is test-time sampling. The case for git-as-substrate is therefore auditability, provenance, and mergeability at accuracy parity. We document a retracted result and a refuted hypothesis to model the evaluation standard we hold ourselves to.

This paper investigates the fragility of post-hoc explanation methods in audio deepfake detection. While previous work on explanation manipulation focused on images using standard $L_p$ metrics, we introduce a psychoacoustic framework that optimizes inaudible perturbations to decouple model attributions from final classifications. We evaluate this vulnerability across state-of-the-art architectures under strict prediction-preserving constraints. By evaluating the manipulation cost through domain-specific perceptual audio quality metrics alongside explanation alignment criteria, our framework demonstrates that an adversary can systematically distort automated explanation heatmaps while preserving the predicted deepfake label. Full code available at: https://github.com/cncPomper/Audio-XAI

Transformer-based clinical language models are increasingly integrated into high-stakes clinical decision support pipelines, yet the computational mechanisms through which demographic associations encoded in medical documentation propagate into model probability distributions remain empirically underspecified. We present a systematic computational audit of representational bias in ClinicalBERT (Alsentzer et al., 2019), a BERT-based model pretrained on MIMIC-III discharge summaries, employing two complementary probing methodologies: Log Probability Bias Analysis (LPBA), which quantifies demographic descriptor-induced shifts in masked token probability distributions across behavioral and evaluative semantic categories, and Masked Language Model-based analysis (MLM), which probes internal representational structure for demographic agency attribution encoding across 98 real clinical sentence templates and eight intersectional race-gender combinations. Corpus frequency analysis operationalizes the distinction between statistical disparity and bias amplification by benchmarking model outputs against empirical term frequencies in the MIMIC-III training corpus. Of 32 statistically significant findings, 65.6% contradict observed corpus distributions, rising to 80% for Black patients and 87.5% for agency attribution under MLM probing, providing direct empirical evidence that representational bias in ClinicalBERT operates predominantly through model-internal amplification rather than training data inheritance. Keywords: natural language processing, clinical documentation, algorithmic auditing, representational bias, health equity 1

Modern Automatic Speech Recognition (ASR) systems have made remarkable progress on standard benchmarks, yet performance gaps have emerged under real-world distribution shifts, caused by recording conditions, accents, speech impairments, and noise. Existing datasets and benchmarks typically isolate these factors, which overlooks their co-occurrence in real-world applications. In this paper, we argue that model robustness can be treated as a dynamic capability that continually develops, and we introduce MoDiCoL, a Modular Diagnostic Continual Learning dataset designed for controlled analysis of linguistic content, speaker characteristics, and acoustic environments. Furthermore, we propose a real-world-inspired continual learning curriculum to simulate incremental updates and study how robustness is acquired, transferred, and forgotten. We evaluate three continual learning strategies and provide detailed insights into robustness under evolving conditions.

Existing multi-agent software development systems have proposed many forms of agent collaboration, including role-based collaboration and automated code review. However, many systems assume a common runtime, a central conversation server, or the same API family. Under these assumptions, LLM agents from different vendors cannot easily exchange messages directly from their own execution environments while dividing development and review work on a shared codebase. This paper presents tap, a file-based collaboration protocol that allows Claude (Anthropic) and Codex (OpenAI) to collaborate on one codebase without shared memory or an identical runtime. The core of tap is a file-first design that preserves markdown files with metadata as original messages, combines a file inspection path (file communication, Tier 1) with real-time notification paths for Claude and Codex (real-time communication, Tier 2), and isolates work through separate git worktrees. Even if real-time notification fails or a receiver restarts, the message file remains available and the same content can be inspected again. In a 27-day, 37-generation self-applied operation where tap was used to develop and review itself, we collected 209 tap-related pull requests and 717 operational artifacts. An analysis of 375 review artifacts showed that the share of reviews recording at least one defect or requested change was 69.8% for heterogeneous model pairs and 53.1% for homogeneous model pairs. These results show that tap, which combines file-based message preservation with real-time notification, operates in a real production repository, and that combining heterogeneous models and execution environments can broaden review perspectives. tap is distributed as the open-source npm package @hua-labs/tap (v0.5.2).

End-to-end (E2E) autonomous-driving planners trained by imitation are prone to statistical shortcuts: they associate scene elements that merely co-occur with expert actions (a roadside object, a building facade) with driving decisions, rather than the variables that causally determine them. Such causal confusion silently compromises reliability in long-tail scenarios, and it is difficult to detect, because prevailing open-loop metrics (L2 displacement and collision rate) are dominated by ego status and do not indicate whether a planner depends on spurious cues. Existing remedies based on causal-intervention training require retraining large models and cannot audit a planner that is already deployed. We present CADET, a training-free framework that audits, benchmarks, and repairs spurious reliance in pretrained E2E planners without any parameter update.

The recent popularity of robotics, combined with the steadily decreasing cost of robotic hardware, has lowered the entry barrier to robotics research and enabled rapid advancements in the field. One of the primary examples is the Unitree Go2 quadruped robot, which is often used by researchers in the areas of locomotion, navigation, control, and others. Many researchers use the Go2 robot in combination with techniques like imitation learning, reinforcement learning, and behavioral cloning to allow machine learning systems to take full control of the robot. At the same time, many of those techniques require demonstration data consisting of the robot's kinematics information and actions applied to the motors. Obtaining such data is difficult, requires building complex pipelines, and can take significant time. To aid in those kinds of efforts, we present Kine2Go - a dataset with 800 diverse gait kinematics trajectory motion data for the Unitree Go2 robot, derived from 40 distinct policies. Our pipeline accepts data from various quadruped morphologies and translates them to a Go2-compatible format. Then we use Reinforcement Learning to train policies following a given motion, and finally we gather data from those policies, which grants robust, perturbed kinematic data with corresponding motor-level actions.

Reliable return navigation remains an important challenge in GPS-denied environments where external positioning infrastructure may be unavailable or unreliable. This paper presents ForestBack, an infrastructure-free pedestrian return navigation framework based on breadcrumb-based pedestrian dead reckoning (PDR). The system records a user's walking route as a sequence of reversible breadcrumb nodes and generates reverse-path guidance without requiring GPS, Wi-Fi, Bluetooth beacons, or pre-installed infrastructure. ForestBack integrates acceleration-based step detection, adaptive step-length estimation, magnetometer-assisted heading estimation, barometric-altitude correction, and bidirectional breadcrumb path reconstruction. The system was evaluated using an indoor obstacle-avoidance route with five checkpoints, where the user navigated around a central obstacle. A dataset of 36 walking trials and 42,474 time-series samples was used for evaluation, including IMU signals, magnetometer readings, barometric variables, turn-event labels, ground-truth trajectories, baseline PDR outputs, proposed ForestBack outputs, and power-related measurements. Experimental results show that ForestBack reduced the mean RMSE from 1.129 m to 0.965 m compared with traditional PDR, corresponding to a 15.76% improvement. The mean final-position error was reduced from 1.781 m to 1.388 m, while turn-event detection consistency reached approximately 99.90%. These results indicate that ForestBack improves trajectory reconstruction and route-preserving return guidance in obstacle-avoidance scenarios. The released dataset and analysis notebook support reproducibility and future benchmarking of infrastructure-free PDR-based return navigation systems.

We introduce COMET (Causal Object-centric Model for Efficient Tree search), a model-based reinforcement learning algorithm that performs Monte Carlo Tree Search in a slot-structured latent space. COMET pairs a frozen unsupervised object-centric encoder with a transformer-based world model, in which actions are bound to objects through a novel action-slot fusion mechanism that is used in slot transition prediction. Policy and value heads use object-causal attention, modulating token interactions by learned per-slot relevance scores so that decision-making concentrates on task-relevant entities. COMET adds an explicit object-level inductive bias to MuZero-style latent planning. Across eight visually and dynamically diverse tasks from the Object-Centric Visual RL benchmark, ManiSkill, Robosuite, and VizDoom, COMET achieves a higher mean normalized score during the early stages of training compared to object-centric and monolithic baselines.

Safe reinforcement learning (Safe RL) aims to maximize expected return while satisfying safety constraints, typically modeled as Constrained Markov Decision Processes (CMDPs). While primal-dual methods scale well to deep RL, they often suffer from delayed constraint correction, leading to oscillatory behavior and prolonged safety violations. In this paper, we propose Constraint-Sensitive Policy Optimization (CSPO), a first-order primal-dual method that incorporates local constraint sensitivity into policy updates. CSPO augments the primal objective with a constraint-sensitive correction derived from the shortest signed distance to the safety boundary, enabling smarter recovery steps back to safety, compensating for delayed Lagrange multiplier updates, reducing oscillations near the boundary, and preserving the KKT solutions of the original constrained problem. Experiments on navigation and locomotion benchmarks demonstrate that CSPO achieves faster safety recovery and high reward preservation, resulting in higher constrained returns compared to state-of-the-art primal-dual and penalty-based methods

In this report, we present Hy-Embodied-0.5-VLA, abbreviated as HyVLA-0.5, an end-to-end system that spans the full robot learning stack: data collection, model design, continued pre-training and supervised fine-tuning, RL post-training, and real-world deployment. Each component serves a distinct role in this stack.

As agentic systems continue to evolve and are widely deployed in real-world scenarios, there is a growing demand to faithfully evaluate their capabilities. However, current benchmarks are typically built on popular applications with relatively simple tasks and focus on a narrow set of capabilities while overlooking broader dimensions, resulting in saturated performance on modern agents and failing to probe their limitations. To this end, we introduce GauntletBench, a web-based benchmark for evaluating agent generalisation in challenging scenarios, focusing on three underexplored capabilities (temporal perception, graphical understanding, and 3D reasoning), across five less-covered professional applications (Video Editor, Workflow Builder, 3D Modeller, Flight Analyser, and Circuit Designer), each with 20 vision-intensive tasks (100 in total). Our benchmark provides a modular pipeline that comprises an environment compatible with both open- and closed-source agent frameworks, a controlled web-based application, a well-structured task suite, and an automated evaluation engine with diverse metrics. Contrary to widespread expectations, our empirical results reveal that frontier agentic systems remain far from achieving human-level performance. Even the state-of-the-art agent achieves only a 19.1% success rate on our GauntletBench, highlighting the limitations in these overlooked capabilities and generalisation. By comparison, non-expert human annotators achieve over 80% success on our challenging yet feasible tasks, revealing the substantial gap between current agent capabilities and those required for complex real-world scenarios.

Scientific discovery saturates when new hypotheses cease to provide independent information, even if the nominal hypothesis space remains large. We study hybrid discovery systems that combine structured local search with LLM-generated non-local proposals and pose the Search Compression Hypothesis: non-local exploration helps only when three geometric conditions co-occur: spectral compression, orthogonal escape from the explored span, and residual signal alignment with the target. We formalize these conditions, derive necessary conditions for hybrid advantage, and test the mechanism in controlled synthetic environments, large-scale A-share factor discovery, and symbolic-regression benchmarks; a public tabular operational sanity check tests the associated budget-allocation implication. Signal-planting and directed-versus-random experiments show that novelty alone is insufficient: random orthogonal jumps expand coverage but do not improve yield without predictive alignment. Across compression sweeps, real factor archives, and LLM-SRBench tasks, hybrid gains concentrate in weakly represented but target-bearing directions and vanish as the hypothesis space approaches full rank. The framework turns LLM-guided discovery from generic novelty search into a diagnostic procedure for deciding when directed non-local exploration is warranted.

Industrial products such as valves and circuit breakers are defined by dense technical specifications that govern procurement, compatibility, and safety across supply chains. These specifications are scattered across multiple heterogeneous product images, including specification tables, nameplates, and technical drawings, yet whether Multimodal Large Language Models (MLLMs) can reliably recover them remains underexplored. To fill this gap, we introduce IndustryBench-MIPU, the first large-scale benchmark for multi-image industrial product understanding, built around structured attribute extraction -- recovering property-value pairs from product images. This task jointly probes text recognition on specification tables and nameplates, visual reasoning over technical drawings, domain knowledge to decode industrial terminology, and cross-image evidence integration to assemble scattered specifications. Concretely, the benchmark comprises 4,559 products across 27,652 images with 103,703 annotations spanning 18 industrial categories, constructed through multi-model consensus and three-tier quality assurance. Evaluating nine MLLMs under both single-image and product-level multi-image settings reveals a stark completeness gap: models achieve high precision (86--94%) but the best recovers only 49.9% of product-level attributes; moving from single-image to multi-image extraction costs 15--34 percentage points of recall. Multi-image completeness, not single-image accuracy, is the core bottleneck. Dataset and code are publicly available.

Anticipating traffic accidents from dashcam videos is a critical challenge in intelligent transportation systems. Existing methods typically map visual context directly to a collision probability without explicitly modeling the future evolution of the driving scene. In this paper we propose FLaRA (Predicting Future Latent Representations for Accident Anticipation), a novel predictive architecture that shifts this paradigm by forecasting future latent representations for accident anticipation. Building upon the Video Joint-Embedding Predictive Architecture (V-JEPA2), our model conditions a predictor network on observed context frames to predict the forthcoming latent features of the scene. A classifier then operates on these predicted future representations rather than only on past observations. To ensure these forecasts remain grounded in realistic future dynamics, we introduce a joint training objective that simultaneously optimizes an auxiliary feature-level reconstruction loss and a cross-entropy classification loss. Extensive evaluations on the Nexar dataset, alongside cross-domain validations on the DAD, DADA-2000, and DoTA benchmarks, demonstrate that our approach achieves state-of-the-art performance while maintaining realistic early warning capabilities.

Vision-language-action (VLA) models are powerful action generators for robot manipulation, but they are typically executed with fixed inference and replanning schedules. This rigidity ignores the uneven difficulty of robot control: contact-rich or uncertain states may need more computation and fresher feedback, while easier states can often be handled with fewer inference steps and longer open-loop execution. We propose Elastic Queries Reinforcement Learning (EQRL), a framework that makes each VLA policy query elastic. A lightweight latent-schedule adaptor jointly selects the latent input, denoising budget, and action chunk length, without fine-tuning the underlying VLA model. To make scheduling difficulty-aware, EQRL trains a critic over the joint latent-schedule action and derives a state difficulty signal from critic ensemble disagreement. This signal guides compute toward difficult states, while a learned residual allows task-driven correction. We formulate variable chunk execution as query-level macro-action RL with chunk-dependent discounting and an amortized number-of-function-evaluations (NFE) budget. Across simulation and real-robot manipulation, EQRL reduces amortized inference cost while preserving or improving task success.

Photon-number-resolving (PNR) detectors are essential components of photonic quantum technologies, yet thus far, no practical metric exists to certify how many photons they can genuinely resolve in a single measurement. Here we introduce an operational framework for quantifying the capability of a PNR detector to distinguish between different numbers of photons, i.e. its genuine resolution. In turn, we develop a practical and scalable protocol for certifying the genuine resolution of a detector, which is based on coherent state probes. We apply the method to a 28-pixel photon-number-resolving superconducting nanowire single-photon detector (PNR-SNSPD) and certify genuine four-outcome resolution. Our work highlights the critical requirements in terms of detector efficiency towards achieving high genuine resolution. This approach provides an operational benchmark for PNR detectors and fills a crucial gap in the characterization of photonic quantum devices.

Frontier coding models may spend substantial capacity learning not only program behavior, but also accidental entropy in human repositories. Such repositories contain valuable signals: tests, incidents, migrations, edge cases, product judgment, and operational history. These signals are entangled with framework churn, naming drift, generated-source ambiguity, dependency rituals, CI dialects, weak proof routes, and human-oriented review customs. We propose agent-first canonical code, a proof-carrying substrate that rewrites routine product software into canonical behavior profiles, typed change algebra, proof lanes, constrained edit grammars, semantic patch cells, runtime negative memory, and proof-carrying change objects. The core hypothesis is that quotienting software by behavior equivalence under a declared oracle can collapse equivalent encodings into governed representatives with explicit evidence and proof obligations. The endpoint is amortized cost per verified correct change, including source, context, reasoning, tools, verification, security, provenance, review, failed loops, defects, and foundry cost under a common oracle. Reported reduction bands are hypotheses, not measured frontier results. The proposed limit is a No-Accident Horizon: removable accident decreases until residual novelty, evidence, governance, risk, and future optionality dominate. For supported routine-product distributions, this gives a defensible planning target near 100-fold all-in cost reduction, not a guarantee for all software. Preliminary QLoRA experiments on Qwen2.5-Coder-14B show that 64,088 canonical trajectories are learnable and suppress tested forbidden-language markers, but do not establish behavior preservation, scaling economics, or verified-change cost. The contribution is a falsifiable program centered on minimum functional description length and verified-change cost.

Tactile imaging seeks to reconstruct the internal structure of soft objects through touch sensing, with applications in medical diagnosis and robotic manipulation. Recent self-supervised learning approaches have shown promising results, but rely on global, unstructured representations and robot-controlled sensing, limiting generalization and practical use. We propose Local Encoder for Spatial Sensing (LESS), an object-centric tactile representation that exploits the local nature of touch. The tactile scene is modeled as a grid of recurrent encoders with local receptive fields, whose states are fused to reconstruct 2D or 3D images of internal structure. This compositional design enables strong generalization: models trained on single-inclusion phantoms accurately image objects with multiple inclusions and varying sizes. The local structure further supports spatial uncertainty estimation. In addition, we enable hand-held tactile imaging via external pose tracking and human-like palpation data, and extend tactile imaging to full 3D reconstruction.

Property Graphs are rapidly being adopted as database frameworks for representing heterogeneous data sources. To enable precise access to the information contained in them we need conversational interfaces based on Text-To-Cypher (Text2Cypher) parsers. This paper presents an automatic synthetic data generation method that can be leveraged to fine-tune small LLMs for this task. We conduct experiments on all the major Text-To-Cypher benchmarks, demonstrating that with our synthetic data generation approach we can significantly increase the performance of small LLMs, allowing them to compete with much larger proprietary models. This means that in settings in which models must be locally deployed we can ensure data-sovereignty without sacrificing accuracy and without costly annotation campaigns.

LLM agents have rapidly evolved into autonomous systems, yet a persistent information gap remains between users and agents: communication is costly, while users' identical preferences further limit information exchange. To investigate how agents should communicate across modalities, this paper formalizes Communication Policy, establishes textual and UI-based policies, and then evaluates communication policies across diverse environments, personas, and model combinations. Building information asymmetry for proactive agents, we set up two complementary settings, User-Agent and Planner-Executor. Experimental results reveal complementary strengths between interaction channels: text-based interaction often facilitates task performance, while structured UI improves agents' response quality and persona compliance. Motivated by that, a hybrid method combines these advantages. We further propose Communication Policy Evolution (CPE), a self-evolution framework for refining communication policies through rollout and prompt-level evolving. Without model modification, CPE achieves the best task success across multiple settings using prompt refinement alone. Our findings identify communication behavior as a critical yet underexplored design dimension for LLM agents.

Current Generative AI (GenAI) interfaces remain largely constrained to chatbox interaction, which can impose high cognitive demands on users and create substantial barriers for people with intellectual disabilities (ID), including prompt formulation difficulties, response overload, and limited mechanisms to assess information reliability. To explore alternative interaction models for cognitive accessibility, we conducted a cross-disciplinary co-design challenge in which two student cohorts (Computer Science and Industrial Design) developed interface concepts from the same set of functional requirements (e.g., prompt scaffolding, structured output, GUI-based refinement, transparency, and personalization). Comparing the resulting proposals reveals both convergence on foundational requirements (notably initial calibration, proactive prompting, and direct manipulation of response fragments) and complementary contributions that outline a multi-layered support system. Computer Science teams primarily produced structural scaffolding, emphasizing predictability, navigability, and trust through mechanisms such as reliability indicators, explicit sources, and context management for long conversations. Industrial Design teams emphasized experiential scaffolding, focusing on pacing, attention guidance, multimodality, and proactive agency, including step-by-step response flows, focus modes, and assistant-like integrations. We synthesize these findings into a dual-layer scaffolding framework that expands the design space for cognitively accessible GenAI interaction beyond chat-centric models and motivates future work on expert refinement, technical feasibility, and empirical validation with users with ID.

LLM-based agents trained with reinforcement learning optimize step-wise action prediction but lack metacognitive awareness of task progress, inducing a gap that hinders long-horizon scaling. A pilot study reveals that online progress prompting hurts performance while retrospective demonstrations help, yet this capability cannot emerge from outcome-reward training alone. We present RePro, Retrospective Progress-Aware Training, a framework that trains agents to self-generate progress signals via a forward-then-reflect rollout paradigm: the agent executes actions online, then retrospectively reassesses its step-wise progress given the completed trajectory and known outcome. RePro initializes with a Retrospection Warmup that teaches reflection format from minimal external demonstrations, then further trains through RePro-PO with a composite reward that produces self-generated signals without continuous external supervision. Experiments on WebShop, ALFWorld, and Sokoban show that RePro enhances the Qwen family's performance, with up to $12\%$ absolute success rate gains.

Vision-Language Models (VLMs) such as CLIP have become a standard backbone for open-vocabulary recognition, yet their zero-shot predictions remain vulnerable to distribution shifts encountered at deployment. Test-Time Adaptation (TTA) has recently been extended to CLIP as a lightweight solution, leading to a rapidly growing body of TTA4CLIP methods. However, empirical progress in this area has largely outpaced our understanding of what truly drives adaptation, where their gains originate, and under which shifts they remain reliable. In this paper, we take a step back from the pursuit of state-of-the-art accuracy and conduct a systematic controlled study of TTA4CLIP. We first organize existing methods into three unified paradigms according to what is updated at test time. We then introduce TTABC, an open-source TTA Benchmark for CLIP, which standardizes evaluation protocols and integrates more than 20 representative methods. Our controlled empirical analysis focuses on three key areas. First, we determine the driving factors in parameter-based methods, revealing that adaptation gains are primarily driven by test-time evidence and reliable proxies rather than heavy optimization. Second, we explore evidence utilization beyond heavy parameter tuning, showing that competitive and efficient performance can be achieved through cross- or current-sample evidence and lightweight prototype updates. Finally, we demonstrate that there is no silver bullet for TTA: no single adaptation paradigm is universally optimal, and the preferred paradigm depends on the nature of shift. We hope our benchmark and study provide a clearer understanding of the current TTA4CLIP landscape and establish a foundation for further research.

Frontier AI systems are increasingly capable of cybersecurity tasks, including codebase inspection, vulnerability detection, and exploitation. However, evaluating their offensive capabilities remains constrained by limited access to open, reproducible, multi-host cyber ranges. Existing public benchmarks capture isolated skills such as CTF solving, vulnerability reproduction, and exploit generation, but often abstract away realistic intrusion workflows: discovering exposed services, gaining a foothold, collecting internal information, and expanding compromise across hosts. This gap makes it difficult to observe emerging risks early, because frontier AI systems are rarely evaluated under realistic attack conditions. We introduce AgentCyberRange, the first open, multi-range infrastructure for measuring autonomous cyber attack capability in realistic cyber ranges. It combines 110 vulnerabilities across 15 real web applications and 8 enterprise-like cyber ranges with 156 internal hosts, plus Cage, a toolchain for execution, orchestration, result collection, and verification. The benchmark covers two core stages: web exploitation, where agents explore exposed applications and validate vulnerabilities, and post exploitation, where agents turn an initial foothold into broader internal compromise. We evaluate six frontier AI systems under matched prompts and budgets. GPT-5.5 with Codex performs best, solving 16.1% of web exploitation tasks and 31.7% of post-exploitation tasks; with more concrete hints, these rates increase to 33.0% and 46.3%. We also observe out-of-benchmark findings, including unknown vulnerabilities in popular projects, and payload mutation that bypasses host defenses. These results show that open cyber-range evaluation is necessary for observing emerging offensive capabilities under realistic and reproducible conditions.

Population-based and distributional optimization methods, from evolution strategies and consensus-based optimization to covariance-matrix adaptation and stochastic gradient methods viewed as distributional dynamics, are widely used for nonconvex or black-box problems, yet their convergence analyses remain fragmented across algorithm-specific techniques. We introduce an operator calculus in which a broad class of such methods, after choosing an appropriate state space and, where necessary, augmenting the state by memory or strategy variables, is described as a composition of three elementary operators (mutation, selection, and recombination) acting on probability measures. Under explicit stability and regularity conditions, the composite operator admits a pre-generator whose continuous-time limit is a transport-reaction-jump (TRJ) PDE that preserves the operator splitting. On this foundation we establish a modular Lyapunov principle. If a state-space Lyapunov function both dissipates under the full generator and controls the relevant search-space gauges, then the state-space Lyapunov functional and the induced search errors decay exponentially. The additive generator structure allows dissipation estimates to be assembled operator by operator, providing a toolkit for certifying convergence of composite mean-field algorithms.

Deep learning has driven many recent advances in process analytics, especially for predictive and prescriptive monitoring. However, standard objectives such as cross-entropy optimize local next-step likelihoods and only implicitly capture control-flow structure. As a result, models can achieve high token-level accuracy while permitting imprecise global behaviour. We introduce DIFF-ERO, a conformance-aware loss function for deep learning models on process data. DIFF-ERO is a differentiable formulation of entropy-based stochastic conformance that incorporates control-flow information during training. Our approach constructs batch-level stochastic transition matrices with soft edge memberships, allowing structural precision and recall signals to directly inform backpropagation. The loss is model-agnostic and can be applied whenever the final representation parametrizes stochastic transitions. We instantiate DIFF-ERO in transformer encoder-decoder pipelines for next-activity prediction and use it jointly with cross-entropy to analyse its theoretical components with respect to convergence. Across benchmarks comparing other loss functions and targets, DIFF-ERO shows improved predictive performance where structure matters most while maintaining parity elsewhere. At the same time, the learned stochastic automaton converges towards the structural ground truth, indicating that the network internalizes process model structure.

Tunable, microscopic, and energy-efficient solutions for radio-frequency (RF) signal manipulation in the GHz regime are a key technology for efficient communication and sensing applications. Spin waves offer micrometer wavelengths at GHz frequencies, combined with strong magnetic-field tunability, making them inherently well-suited for tunable analog signal processing. Here, we demonstrate a novel concept: a micron-scale tunable RF phase shifter based on the wavelength shift of propagating spin waves. High energy efficiency is achieved by using the stray field of a micromagnet on a piezoelectrically actuated MEMS cantilever to locally induce this shift. The device shows a phase shift of more than 360° at a center frequency of 6.1 GHz using a phase-shifting area of less than 0.02mm$^2$. By changing the magnetic bias field, its functionality is experimentally confirmed over a range of center frequencies from 3 GHz to 8.2 GHz, and simulations show its applicability up to 14 GHz. A system-level characterization of an embedded device version demonstrates the qualification of magnonic phase shifters for highly integrated RF systems.

Large language models (LLMs) are now widely used as automatic judges for open-ended instruction-following evaluation. This practice is convenient, scalable, and often more semantically aware than reference-based metrics, but it also introduces a new reliability question: does a judge evaluate the quality of an answer, or does it also react to the language in which the comparison is presented? We propose Judge-LS, a lightweight meta-evaluation protocol that transforms LLMBar response-pair items into English, Chinese, and Chinese-English language-switched variants. A reliable judge should preserve its preference under label-preserving language transformations and should not prefer a language when two answers are translation-equivalent. We evaluate four API-accessible judges on the full 419-item LLMBar benchmark, producing 13,408 successful pairwise judgments. Across models, Chinese and language-switched presentations induce 10.7--14.4% preference flips relative to English, and all judges achieve their highest accuracy in English. However, translation-equivalent tie probes do not reveal a systematic English preference: most probes are judged as ties, and non-tie decisions more often favor Chinese. We add confidence intervals, paired significance tests, and an automatic transformation audit with a sensitivity analysis that excludes mechanically flagged high-risk variants. The experiment requires no model training, uses only API calls, and is feasible on modest local hardware.

Fall recovery is critical for autonomous legged locomotion. Existing methods have demonstrated that some legged robots, such as humanoids and quadrupeds, are capable of fall recovery from diverse postures by utilizing arms or coordinating multi-legs to generate support forces. Without arms or other legs to provide supportive assistance, a bipedal-wheeled robot must rely solely on the actuation of its legs, making recovery particularly difficult. To address this, we introduce FTSR (Force-guided Teacher-student framework with Stage-wise Rewards). The force-guided method constructs an external auxiliary force during simulation training that correlates directly with the robot's real-time height, explicitly formulating this force as an optimizable constraint. Through constrained reinforcement learning, the policy is guided toward reducing force dependency gradually and increasing the body height, developing internal recovery strategies despite having no arms for support. Height-progressive stage-Wise rewards progressively structure posture stabilization during recovery and transition to sustained locomotion, integrated with teacher-student architecture distilling privileged knowledge of force effects and recovery dynamics. After simulation training, the policy is deployed on a physical armless bipedal-wheeled robot and extensively evaluated. Experiments confirm robust and reliable fall recovery under diverse challenging conditions, demonstrating strong environmental adaptability and motion robustness, while maintaining full post-recovery motion capability. The framework also generalizes effectively to a high-DOF humanoid, confirming its practical generalizability. The project page is available at https://2350575870.github.io/force-guided.github.io/

Fixed-cardinality retrieval injects a constant top-K chunks into the generator regardless of query complexity, causing over-retrieval for narrow queries and under-retrieval for compositional ones. We describe ScoreGate, a lightweight score-space decision mechanism that controls retrieval cardinality at inference time using two scores already produced by the standard pipeline: bi-encoder similarity s_i and cross-encoder reranker score r_i, with no additional model inference calls required. Its core insight is that cross-encoder affirmation can rescue semantically relevant chunks that bi-encoder retrieval ranks poorly due to vocabulary mismatch -- a failure mode unaddressed by fixed-K or single-score thresholding. On MS MARCO (200 dev queries), ScoreGate achieves MRR@10 = 0.401 with 35% fewer retained chunks than Standard Top-K. On an internal benchmark (n=300, Fleiss' kappa=0.87), ScoreGate observed zero false positives (95% CI [96.4%, 100%]) at 97.77-99.34% recall, with 34.8% fewer tokens per query and only 31ms added latency. Results on both MS MARCO and real-world production traffic suggest that adaptive retrieval cardinality can improve retrieval efficiency without degrading retrieval quality.

Floor plans encapsulate compact spatial priors, enabling agents to navigate unseen scenes more efficiently. While prior work has explored floor plan-guided navigation, it has focused mainly on PointNav and a limited set of environments. To bridge this gap, we introduce FloVerse, a new task for floor plan-guided embodied navigation that unifies PointNav, ObjectNav, and ImageNav. To support FloVerse, we assemble FloVerse-1.6K, a large-scale dataset of 1.6K scenes from HM3D and Gibson 4+, paired with corresponding floor plans, comprising 240K expert trajectories and 12M RGBD frames. We further propose ThreeDiff, a two-stage imitation learning policy comprising a planner, a diffusion-based multimodal goal-reasoning module trained via masked-modality modeling, and a refiner, a depth-based trajectory-refinement module for safe execution. Extensive experiments demonstrate that (1) floor-plan priors improve navigation performance across all goal modalities, and (2) ThreeDiff implicitly captures spatial information from floor plans. These results underscore the effectiveness of spatial priors and validate our proposed unified approach for floor plan-guided embodied navigation.

Semantic IDs are crucial in generative recommendation, but with a fundamental limitation: temporal information is not well incorporated into semantic IDs. Instead, time influences recommendation only implicitly (e.g., through session construction heuristics, preference alignment, or sequence order), while existing semantic ID learning remains entirely time-agnostic. This design conflates interactions occurring under distinct temporal contexts into identical semantic representations, implicitly assuming that item semantics and user intent are temporally stationary. Such an assumption is misaligned with real-world recommendation scenarios, where evolving interaction rhythms play a central role. In this work, we investigate where and how the explicit time should be incorporated into semantic ID for generative recommendation. First, we systematically characterize the design space along three orthogonal dimensions of temporal signals and present a unified framework, ChronoID, for time-aware semantic ID learning. Then, by contributing a new time-explicit generation recommendation benchmark, ChronoID answers the questions: what is the effective way of infusing time, how to design the architecture, and where does the gain come from.

Linguistics olympiad problems (LOPs) are a category of self-sufficient puzzles consisting of a scaled-down corpus representative of certain linguistic phenomena, from which the solver must deduce a primitive set of rules of the language and then translate a new set of elements. The linguistics olympiads (LOs) have become a worldwide phenomenon with 43 different territories taking part in the International Linguistics Olympiad (IOL) 2025. While the typology and solving strategies of LOPs have been analysed, their scientific facet and connections to academic linguistics have yet to be explored. LOPs are directly connected to many linguistic fields, e.g., linguistic typology, linguistic relativity, and linguistics fieldwork. Recently, LOPs have become a research focus as benchmarks for large language models, thus highlighting their usefulness in computational linguistics. Nevertheless, they have not yet been integrated into mainstream linguistics research. This paper attempts to open new directions of including this particular type of puzzle in academic research by offering a structured evaluation of LOPs as linguistic data sources and proposes criteria for their responsible use in academic research. Starting from a set of over 1800 LOPs, this study critically examines the potential of LOPs as a novel corpus for linguistics research by discussing their strengths and limitations as tools, as well as the areas of linguistics into which these problems could fit. This work forms the foundation for a broader initiative aimed at bridging the gap between LOs and academic linguistics, by establishing a robust theoretical framework for LOPs.

Diffusion-based Vision-Language-Action (VLA) policies have demonstrated strong capability in modeling expressive and multimodal action distributions. However, their reliance on iterative sampling introduces substantial inference latency, which limits their applicability to reactive closed-loop robot manipulation. To address this limitation, we propose \texttt{ReactVLA}, a lightweight and low-latency VLA framework for real-time robotic manipulation. \texttt{ReactVLA} combines two complementary designs: (1) an improved Mean Flow (iMF) action generator that reduces expensive multi-step diffusion sampling to one-to-few-step action generation, and (2) Attention Residuals (AttnRes), a dynamic depth-wise feature routing mechanism that replaces uniform residual accumulation to better preserve task-relevant multimodal representations. We evaluate \texttt{ReactVLA} on large-scale simulation benchmarks, including LIBERO and RoboIMI, as well as real-world robotic manipulation tasks. Experimental results show that \texttt{ReactVLA} consistently outperforms similarly sized VLA baselines, including SmolVLA and $π_0$. On challenging precision manipulation tasks, \texttt{ReactVLA} achieves up to a 1.65$\times$ improvement in task performance while providing more than a 4$\times$ increase in inference speed compared with leading VLA models. Finally, it reduces real-world policy latency to below 38.6 ms, enabling fast reactive control on physical robot platforms. Please check out our project website at: https://game-loader.github.io/ReactVLA/.

Spatial transcriptomics (ST) links gene expression with tissue morphology but remains expensive and low-throughput, motivating surrogates that infer expression from routine histology. Whole-slide H&E-to-ST inference pairs a gigapixel image with gene measurements at a sparse, irregular set of locations, making multiscale modeling challenging without incurring dense-grid overhead or quadratic token mixing. We propose HiST, a hierarchical sparse transformer that treats measured locations as a lattice-indexed sparse field and builds a dyadic encoder--decoder directly on the active tissue footprint. HiST combines sparse window attention for local geometric correspondence with resolution-changing operators for rapid multiscale context integration. For a fixed window size, the dominant runtime and memory scale with the number of observed locations rather than the dense slide area. To mitigate slide-specific acquisition variation, HiST adds a bottlenecked global conditioning pathway via a \emph{slide calibration token} that summarizes slide-level context and conditions local representations. On a multi-organ benchmark spanning diverse tissues and acquisition sources, HiST improves predictive performance over recent baselines while reducing runtime and peak memory.

Designing anthropomorphic robotic hands that balance functional dexterity with mechanical simplicity remains a significant challenge. Inspired by human hand synergies, this paper presents the SyLink Hand, an anthropomorphic dexterous hand that integrates biomechanical synergy principles with linkage-driven transmission mechanisms to achieve a high degree of anthropomorphism in appearance, kinematics, and functionality within a compact and cost-effective architecture. Biomechanical analysis of natural hand motions using motion capture gloves reveals strong kinematic correlations among hand joints, providing the basis for a simplified yet functional degree-of-freedom (DOF) configuration. Guided by these synergistic characteristics, optimized linkage mechanisms are employed to coordinate multiple joint motions and reproduce natural finger trajectories. A novel spherical four-bar linkage is further proposed to achieve decoupled flexion/extension (Flex/Ext) and abduction/adduction (Abd/Add) at the metacarpophalangeal joint within a compact form factor. The resulting prototype integrates 19 joints driven by 11 actuators, with a total mass of 520g and a manufacturing cost of approximately USD 400. Experimental evaluations demonstrate its human-like kinematic performance, high load-bearing capability, and versatile grasping and manipulation skills. These results validate that the synergy-inspired, linkage-based design effectively balances anthropomorphism, mechanical simplicity, and functional versatility, highlighting its potential for practical deployment in dexterity-demanding robotic applications.

AI agent performance depends critically on the runtime harness, comprising the prompts, tools, memory, and control flow that mediate how a model observes, reasons, and acts. Yet today's harnesses remain largely hand-crafted and static: each new model or task still demands bespoke scaffolding, and the rich traces produced during execution are rarely distilled back into systematic improvement. We introduce HarnessX, a foundry for composable, adaptive, and evolvable agent harnesses. HarnessX assembles typed harness primitives via a substitution algebra, adapts them through AEGIS, a trace-driven multi-agent evolution engine grounded in an operational mirror between symbolic adaptation and reinforcement learning, and closes the harness-model loop by turning trajectories into both harness updates and model training signal. Across five benchmarks (ALFWorld, GAIA, WebShop, tau^3-Bench, and SWE-bench Verified), HarnessX yields an average gain of +14.5% (up to +44.0%), with gains largest where baselines are lowest. These results suggest that agent progress need not come from model scaling alone: composing and evolving runtime interfaces from execution feedback is an actionable and complementary lever. The complete codebase will be open-sourced in a future release.

Drug-target interaction (DTI) and affinity (DTA) predictors increasingly achieve strong benchmark scores, yet their internal use of sequence, fingerprint, and graph features often remains opaque. We present an interpretability audit of BridgeDPI architecture on three different datasets including Gao, Human, and C.elegans. This study combines gradient-based attributions -- integrated gradients, saliency, layer-wise relevance propagation, SmoothGrad, and SmoothGrad-IG -- with feature-wise occlusion ablation and strict intersection consensus across methods to reduce single-explainer bias. We summarize sensitivity and signed effects at raw inputs, at the bridge similarity scaffold, and through the graph convolution, including edge-level sensitivities and targeted edge removals. The results show that explainability is most informative when treated as model criticism: it reveals modality dominance, padding and special-token artifacts, dataset-dependent cooperative versus suppressive effects across layers, and chemistry-consistent fragment and composition motifs where methods agree. These analyses do not substitute for structural or experimental ground truth, yet they can provide testable hypotheses for downstream validation in computational drug discovery pipelines. More broadly, applying modern XAI to contemporary DTI/DTA models is still an early pass over the rich structure implicit in trained weights and data -- yet even this first layer of scrutiny already helps researchers relate predictions to drug- and target-side representations and to prioritize external validation.

Knowledge injection aims to equip large language models (LLMs) with external, domain-specific, or time-sensitive knowledge. Existing approaches typically face a trade-off between flexibility and integration: retrieval-augmented generation keeps knowledge outside the model but only provides prompt-level augmentation, whereas post-training based methods encode new knowledge into shared parameters but may introduce catastrophic forgetting, knowledge conflict, and costly updates. In this paper, we propose Decoupled Mixture-of-Experts (DMoE), a modular architecture for parametric knowledge injection that decouples both experts and the router from the base model. DMoE converts external knowledge corpora into independently updatable expert modules and uses a lightweight uncertainty-aware router to activate relevant experts only when the base model lacks sufficient knowledge during generation. To support efficient auto-regressive inference, DMoE attaches experts only to the final-layer feed-forward network, preserving KV-cache reuse while enabling parameter-level knowledge augmentation. Experiments on knowledge-intensive benchmarks show that DMoE consistently improves answer quality over retrieval and adapter-based baselines.

Affordance reasoning, the inference of an object's action possibilities from its physical properties (e.g., shape and material), is fundamental to human physical understanding and increasingly critical for Large Language Models (LLMs). However, existing affordance benchmarks largely expose explicit object identities in the evaluation setup, allowing models to rely on memorized object-affordance mappings rather than reasoning over physical properties. To address this gap, we introduce Affordance20Q, a novel affordance reasoning benchmark formulated as a 20-Questions game without exposing the object's identity. In each game, the model identifies a hidden object's affordance from a candidate set by asking yes/no questions about its physical properties. Affordance20Q comprises 1,009 games over 454 objects and 59 affordances, all manually filtered, refined, and annotated. We conduct comprehensive experiments with 15 state-of-the-art LLMs and find a substantial gap (~20 points) compared to human performance. A KL-based information-gain (IG) analysis further shows that models fail to ask discriminating questions as the game progresses. To close the gap, we develop KB-Anchored Rule Induction (KARI), a pipeline based on LLMs that generates affordance rules grounded in evidence from knowledge bases (KBs). KARI improves open-source LLMs by up to 15.2 points, while the limited coverage of KBs hinders further gains. We release all our code and data at https://github.com/1171-jpg/Affordance20Q.git

Agent skills are structured procedural packages that guide frozen LLM agents in specialized workflows. Skills rarely remain sufficient after deployment: edge cases, API changes, and deployment constraints become visible only through use, making skill evolution a practical necessity. Existing methods depend on privileged feedback such as held-out validation scores, hidden test outcomes, or environment rewards -- signals often unavailable when a practitioner has only a task description and workspace data. We introduce SkillAudit, a framework for evolving agent skills without ground-truth feedback. The key idea is paired trajectory auditing: at each iteration, the same task is executed with and without the candidate skill, isolating how the skill changes agent behavior without external labels. To turn behavioral differences into edit guidance, SkillAudit uses Process-Aligned Contrastive Evaluation (PACE), a cluster of evaluators that maps trajectory divergences to diagnostic signals linked to specific passages in the skill document. A structural verifier, compiled once from the task specification and then fixed, checks task constraints and rolls back harmful updates. SkillAudit routes edits through two pipelines: Refine removes noisy or irrelevant guidance from broadly useful skills, while Repair replaces passages that conflict with the task. Across 89 containerized tasks spanning 8 professional domains, SkillAudit achieves 73.9% average task reward, outperforming an agent without skills (40.9%) and the static expert skill (56.7%). These gains are obtained without accessing hidden tests, reference solutions, or external scoring functions during evolution.

Safety certification of Vision-Language-Action (VLA) driving planners under ISO 21448 (SOTIF) rests on an Operational Design Domain (ODD) specification that answers two complementary questions: when does the planner start to fail, and how severely does it fail once it does? We evaluate Alpamayo R1, a 10B-parameter open-weight driving VLA, on 15,968 (clip, attack) pairs. We find a conservative-aggregate gap: an aggregate safe threshold of $σ\leq 50$ under a 15% average displacement error (ADE) budget masks well-sampled scenarios that tolerate the top of the tested grid ($σ= 70$). A Gaussian Mixture Model (GMM) on the changed-explanation subset identifies six discrete severity bands (BIC-optimal $k{=}6$), so two perturbation conditions with the same mean error can differ materially in their share of high-severity (C4/C5) failures. Joining the two analyses on the same corpus surfaces a finding neither yields in isolation: the scenarios with the loosest noise thresholds are not those with the lowest high-severity rate: STOP_SIGNAL concentrates roughly $4\times$ the C4/C5 share of LANE_KEEPING despite tolerating a larger $σ$. A deployable SOTIF ODD specification for driving VLAs therefore requires a two-dimensional safety envelope, not a single aggregate value per hazard.

The advent of photonic integrated circuits (PICs) will allow the replacement of the large aperture of an optical telescope by a dense array of small apertures combined interferometically. The light coming from aperture pairs can be combined by a PIC in order to extract interferogram characteristics known as complex visibilities, from which the observed object can then be reconstructed. In such a compact interferometric imager, the optical components dedicated to image formation in a regular telescope are no longer necessary. In particular, such a concept is relevant for space missions where weight and size are critical. In this communication, we study such an instrument concept, focusing on signal-to-noise considerations. We recall the design basis for the field and the spatial resolution, and we show that the spectral resolution must be no less than the field to resolution ratio. Then, we analyze the signal-to-noise ratio of this concept, assuming that each spatial frequency is recorded only once, and compare the signal-to-noise ratio with that of a monolithic telescope. We perform the comparison in Fourier space for an identical number of recorded photons. We show that the noise propagation of the interferometric imager is identical to that of a monolithic telescope that would have a flat Modulation Transfer Function with a level roughly given by the ratio of the small apertures' diameter to the maximum baseline. We conclude that the noise propagation in low and medium spatial frequencies is unfavorable for the interferometric imager.

Agentic AI can support unmanned aerial vehicle (UAV) autonomy by providing high-level recovery reasoning when local waypoint- or setpoint-based execution encounters blocked passages, repeated no-progress behavior, or mission-level ambiguity. On physical UAVs, however, remote reasoning is most useful when it is invoked selectively, since each call introduces latency, resource cost, backend uncertainty, and a need to validate the returned decision. This paper presents Persistent Mission Runtime (PMR), a UAV recovery framework that keeps the mission loop and safety-critical execution local while using an external agentic reasoner only as an on-demand recovery module. The reasoner selects from predefined recovery skills, and each returned decision is parsed, verified, safety-filtered, and mapped to local executor actions before it can affect flight. PMR introduces learned Cognitive Value of Invocation (learned-CVI), a compact admission gate that estimates when remote agentic reasoning is likely to improve near-term mission progress enough to justify its operational cost. Across a fixed 400-run Gazebo/PX4 benchmark with eight scenarios, learned-CVI raises hard/ambiguous-regime success from 5.0% under local-only autonomy to 95.0%, outperforms one-shot and periodic reasoning baselines by 20.0 and 32.5 percentage points, and reduces remote-agent calls by 16.7% and logged tokens by 29.2% relative to a manually tuned rule-based invocation baseline.

For robots to work safely in household environments, they need to be compliant and react to torque and force feedback during contact. However, the majority of existing data collection pipelines still lack the ability to capture force and torque data for learning active compliant policies. In this paper, we present Universal Manipulation Exoskeleton (UME), an upper-limb exoskeleton that provides real-time haptic torque feedback while recording whole-arm configurations and joint torque signals for teleoperation. With transparent torque feedback, human operators can even unsheathe kinematically constrained objects while blindfolded. UME is low-cost, lightweight, and portable. Equipped with an embedded IMU, it enables teleoperation for mobile manipulation. With our proposed universal retargeting algorithm, UME can teleoperate a range of robots, including the 7DoF OpenArm, 7DoF Franka, and 6DoF X-ARM. We demonstrate that this combination of capabilities enables learning bimanual, whole-body, and active compliant policies that operate effectively in highly constrained spaces. The learned robust autonomous policies achieve high success rates across a variety of tasks, including long-horizon mobile manipulation, force-mediated box flipping, visually occluded box pushing, and space-constrained tabletop manipulation. Videos, code, and additional information can be found at https://ume-exo.github.io.

Accurate prediction of protein-ligand binding affinity is essential for structure-based drug discovery. Recent geometric deep learning methods have achieved promising performance by representing protein-ligand complexes as three-dimensional graphs. However, most existing approaches mainly rely on static interaction geometry from a single bound conformation, while neglecting molecular flexibility and binding-induced conformational changes. To address this limitation, we propose a curvature-informed potential energy surface (CPES) graph neural network for protein-ligand binding affinity prediction, which incorporates physics-informed curvature representations to model conformational flexibility. CPES first derives curvature spectral descriptors from the Hessian of the potential energy surface evaluated at equilibrium configurations, whose eigenvalues define the local principal curvatures of the potential energy surface. It then uses spectral cross-attention to compare the unbound ligand and protein with the bound complex, thereby capturing binding-induced changes in conformational dynamics. In parallel, hierarchical protein-ligand interaction representations are learned from static structural features through geometry-aware message passing, soft clustering, and bidirectional cross-attention. Finally, CPES fuses the curvature-informed dynamic representations with static interaction representations for affinity regression. Extensive evaluations on multiple benchmark datasets demonstrate that CPES achieves improved predictive performance and offers physical interpretability.

The emergence of Large Language Models (LLMs) has inspired the vision of generating bespoke crystal materials directly from natural-language instructions, enabling users to design materials through intuitive, conversational interaction. Existing text-to-crystal generative models represent important early steps toward this goal, but they suffer from two critical limitations: (i) restricted input formats that require highly structured descriptions (e.g., chemical formulas), and (ii) one-directional generation, where models can map text to crystal but cannot perform the inverse. These limitations prevent fully conversational workflows and hinder alignment with users' inherently ambiguous and evolving desiderata. We address these challenges with LapidaryEngine, the first model to support fully conversational crystal generation. LapidaryEngine accepts free-form natural-language requests and performs iterative refinement and editing in a dialogue-like manner. The key innovation is a pivot representation, a third, intermediate form that enables bidirectional translation between text and crystal structures despite the absence of direct paired datasets. Leveraging this pivot allows robust interpretation of user feedback and precise structural control. We demonstrate LapidaryEngine across diverse tasks, including insulator discovery, stability optimization, compositional modification, and structural editing, showcasing its ability to align generated materials with user intent in an interactive manner.

LLMs are increasingly deployed as agents that interact with external environments and observe feedback such as execution results, error messages, and tool outputs. A well-functioning agent should be able to leverage this feedback to accurately assess its own performance. Yet we find a persistent reflection gap: LLM agents tend to mis-assess their own outputs after observing concrete environment feedback -- even for questions they correctly answered -- and standard RL barely helps due to a credit-assignment mismatch. To close this gap, we propose RefGRPO, a simple yet effective fix that augments standard RL algorithms with two key ingredients: a free calibration bonus computed by contrasting the agent's own reflection with the actual outcome (requiring no additional reward model, LLM judge, or external annotation), and a dynamic schedule on its coefficient. Compared to standard RL baselines, our method simultaneously improves reflection calibration (e.g., reduces underconfidence rate $44.4\% \to 7.7\%$) and task accuracy (e.g., $75.1\% \to 76.5\%$) on text-to-SQL across five benchmarks. The resulting calibrated reflection turns the agent into its own verifier grounded in environment feedback, which further enables (i) better self-improvement that uses reflections as pseudo-rewards without outcome supervision, and (ii) more effective test-time selective prediction by committing only to rollouts flagged as correct.

Open platforms increasingly route tasks among heterogeneous LLM agents--differing in base model, scaffold, and tool stack--whose competence varies sharply by skill: an agent excellent at one skill may be useless at another. The standard reputation approach summarizes each agent by a single global trust score, but that scalar is the wrong object here, because routing every task to the globally most-trusted agent leaves the value of specialization unclaimed. We study skill-conditional trust R(i | k)--the trust to place in agent i for a task requiring skill k, rather than one score per agent--and pose three falsifiable questions: when is conditioning worth it, how much cross-skill evidence should be borrowed, and whether that borrowing is safe. A controlled phase-diagram analysis answers the first two: conditional trust wins only in a specific regime--high agent heterogeneity, sparse per-skill evidence, and correlated skills--and the coupling strength beta that buys this data efficiency is dual-use, because the same cross-skill borrowing is also a laundering channel. On a public benchmark of 14 genuinely heterogeneous AppWorld agents, real pools land inside the beneficial regime--a small but genuine gain, with the per-skill best agent genuinely changing across skills. We then show that an attacker with cheap evidence in one skill and none in a target skill hijacks the conditional router, driving routing regret from 0 to 0.94 on a pool our zero-cost Conditional Information Value Test (CIVT) rates GREEN--while the ungated trust verdict it contaminates reads -0.06 instead of the honest +0.19. A zero-evidence gate bounds the attack but does not eliminate it; we characterize the residual cost under an explicit budget. We do not claim Sybil-resistance--we quantify the trade-off.

Large language models are increasingly deployed as human simulators for interactive evaluation and social simulation. Yet helpfulness-driven post-training pulls them toward a homogeneous, overly agreeable assistant register, creating a behavioral Sim2Real gap. We present OdysSim, the largest open systematic investigation of behavioral foundation models, i.e., models trained to simulate human behavior at scale. We propose SOUL, a taxonomy of five capability axes (CONV, SS, COG, ROLE, EVAL) that unifies 62 datasets and 23 benchmark tasks under one framework. Specifically, we curate the OdysSim corpus (21.4M interactions, 10B tokens, retrofitted with back-generated social contexts), construct the SOUL-Index benchmark, and develop an end-to-end training recipe combining midtraining, task-specific RL, and expert distillation. The resulting open 8B OSim model ranks first or tied-first on 8 of 23 tasks, outperforming any individual frontier model by this count, with the strongest gains on conversational and social tasks. Its outputs are also more human-like in length, formatting, and word choice, and it transfers zero-shot to out-of-distribution user simulation on $τ$-bench, nearly matching real users on reaction alignment (93.2 vs. 93.5). We further show that LLM-as-judge RL induces reward-hacking patterns, and that our detectors can mitigate them during post-training. Together, our findings suggest that behavioral foundation models require rethinking the LLM training paradigm. We release all artifacts to support future research.

Auto-bidding is a core component of real-time advertising systems, where decisions must optimize long-term performance under budget and cost constraints, while online exploration is prohibitively risky. Offline reinforcement learning and, more recently, Transformer-based sequence modeling have shown promise for learning bidding policies from logged data, but their unimodal and purely parametric formulations often collapse multiple effective bidding strategies into suboptimal averaged actions and perform unreliably under sparse or long-tail traffic. To mitigate these limitations, we propose DRIVE (Distributional and Retrieval-Augmented Bidding with Value Evaluation), a unified Transformer-based framework that decouples candidate action generation from decision making for offline auto-bidding. DRIVE combines distributional action modeling, retrieval-augmented candidate generation from high-quality historical decisions, and value-based evaluation to select the most promising bid at inference time. Extensive experiments on AuctionNet and additional offline reinforcement learning benchmarks demonstrate that DRIVE consistently improves bidding performance and generalizes well across multiple Transformer-based methods.

We present CORD-SLS, a real-time control method for safe deformable object manipulation, with a focus on ropes and cloth. At its core is a GPU-parallel differentiable simulator with contact smoothing which enables efficient gradient-based planning through intermittent contact. To robustly satisfy constraints under model and sensing uncertainty, we develop a real-time, GPU-parallel output-feedback robust model predictive control (MPC) algorithm that plans with this simulator. We further show that the simulator accelerates model-based RL for training neural manipulation policies. To improve real-world robustness, we use conformal prediction to calibrate visual-feedback and perception-error bounds for MPC, producing reachable tubes that enable high-probability safe control. We evaluate CORD-SLS on high-dimensional, contact-rich rope and cloth manipulation tasks in simulation and hardware, including obstacle avoidance, routing, folding, and smoothing. Across settings, CORD-SLS achieves millisecond-speed planning, exceeding baselines in safety, speed, and task success.

Physics-informed neural networks (PINNs) are meshless and carry moving geometry and topology change through resampling of collocation points; the finite-element method (FEM) is the workhorse for boundary-fitted discretisations. Coupling the two across a shared interface promises the best of both, yet existing PINN-FEM schemes are validated only empirically. We put the coupling on a domain-decomposition footing: viewing each solver as a Steklov-Poincaré (trace-to-flux) operator, we transfer the classical Dirichlet-Neumann (DN) divergence diagnosis and its Robin-Neumann (RN) cure, including a closed-form, sweep-free interface impedance, and prove a PINN-specific contraction theorem: a trained network realises only a perturbed Steklov operator with a per-step training residual, and RN still contracts, with no shared-eigenbasis hypothesis, to a floor set by the achieved training loss. Because a PINN has no stiffness matrix, we introduce a Fourier-mode interface probe that recovers the network's resolvable Steklov eigenvalues to within 0.5% and doubles as a diagnostic of the network's spectral cap. The theory predicts measured PINN-FEM contraction rates to within 7% on 1D and 2D Poisson couplings, and a two-slab analogue of the large-added-mass regime shows RN's per-mode impedance matching winning decisively where tuned scalar relaxation saturates. We demonstrate the framework on a Stokes/rigid-disc problem with Alart-Curnier contact: the meshless PINN fluid absorbs the topology change at contact by collocation exclusion alone, no remeshing and no cut cells, and the static-equilibrium contact reaction matches the submerged weight to 0.4% under mesh refinement. We quantify remaining limitations: the warm-started PINN drifts off the Stokes manifold over long horizons, and matched FEM-FEM benchmarks attribute pre-impact squeeze-film signatures to PINN under-resolution.

We present CacheRL, a system for training small agent foundation models that achieves 92 percent process accuracy on multi-step tool-calling tasks, approaching GPT-5's 94 percent while requiring 100 times less compute. Our approach addresses three challenges in practical agent training: transferring tool-calling knowledge from large models at scale, enabling reinforcement learning without costly live tool execution, and learning robustly from noisy cached environments. CacheRL introduces three key innovations. First, a hybrid thinking trajectory pipeline augments agent trajectories with LLM-generated reasoning traces, producing training examples that teach models not only what tools to call but also why. Second, the CacheAgentLoop eliminates live execution costs through a three-tier fuzzy cache while preserving trajectory fidelity using token-level masking. Third, a cache-tier-aware reward dynamically adjusts answer-quality weights to avoid penalizing models for cache-induced limitations. Through iterative supervised fine-tuning (SFT) and Group Relative Policy Optimization (GRPO), CacheRL improves Qwen3-4B-Thinking's validation reward from 0.43 to 0.78. On public agentic tool-calling benchmarks, our model achieves competitive performance against frontier models such as GPT-5. Ablation studies show that removing knowledge transfer reduces performance by 41 percent, while cache-aware rewards contribute a 17 percent improvement. Interestingly, reinforcement learning improves training stability but yields limited gains beyond strong supervised fine-tuning, suggesting that data quality and reward design play a more important role than complex optimization methods in building practical small agent models.

Geometry problem generation is useful for AI-assisted education and multimodal mathematical reasoning, but reliable synthesis remains difficult because the problem statement, diagram, constraints, and solution should be mutually consistent. Existing methods often trade off controllability and reliability: seed-based rewriting is flexible but weakly verifiable, whereas diagram-first construction improves validity but is less suited to arbitrary user-specified constraints. We introduce VeriGeo, a controllable geometry generation framework grounded in executable reasoning traces. Given user constraints such as target concepts and difficulty, an Author agent generates a problem and diagram, and a Solver agent produces a proof-aligned solution. Both agents use a shared action sequence that connects natural language, diagrams, geometric constraints, and proof steps into a verifiable representation. A three-stage pipeline checks numerical consistency, analytical realizability, and global consistency, using verification-guided reflection to repair recoverable failures and reject unrecoverable ones. Across five LLM backbones, raw generations frequently fail these checks, while VeriGeo repairs a substantial fraction of the invalid attempts. Supervised fine-tuning on 8.7k examples generated by VeriGeo achieves the best reported GeoQA performance among end-to-end multimodal LLM-based solvers, and obtains strong results on PGPS9K and MathVista-GPS, demonstrating the effectiveness of verified synthetic data for improving multimodal geometry reasoning.

Text-driven 3D scene generation is a promising technique for digital content creation, embodied AI simulation, and interactive design, yet practical workflows often require refining, extending, or correcting existing scenes while preserving non-target content. Existing methods can produce realistic and structurally plausible scenes, but they generally lack editability with requirement-level state tracking, so part-level failures often lead to full-scene regeneration or manual intervention. To tackle this challenge, we formulate controllable 3D scene authoring as incremental requirement satisfaction, unifying construction and editing. In this paper, we present MUSE, a memory-grounded multi-agent framework in which an Architect compiles instructions into structured requirements, a Sculptor executes local scene operations, and an Inspector verifies each step while updating Working, Scene, and Skill Memory. To evaluate requirement-level controllability and preservation-aware editing, we introduce AuthorBench, offering 145 constrained construction cases and a 1,584-case preservation-aware editing pool paired with external structured checks. On full construction cases, MUSE improves All-Goal success from 37.9 to 80.7 and surface-constraint fulfillment from 35.0 to 92.6 over the strongest baseline. On a stratified 240-case editing test split, MUSE achieves 49.6 All-Goal success, 99.9 preservation rate, and only 0.6 unintended change rate. Beyond automated metrics, human evaluations on compared local-editing baselines support stronger alignment with user intent, and downstream navigation-proxy tests indicate stronger spatial stability. Combined with ablations validating our memory designs, these results establish MUSE as an effective framework for controllable 3D scene authoring.

Large-scale video diffusion models often fail to preserve 3D structure over time, causing geometric drift and implausible motion under viewpoint changes. Existing methods usually enforce geometric consistency by using explicit geometry reconstructions, such as depth maps, point clouds, or reconstructed 3D structures, to define conditions, supervision, or reward signals, making the generator sensitive to errors from upstream geometry pipelines. We propose VideoWeave, a latent-space post-training framework that uses implicit geometry-model features to constrain the generative distribution, providing a more flexible and non-rigid form of guidance that mitigates the impact of reconstruction errors from geometry models. Specifically, VideoWeave adapts these features into geometry latents and jointly models them with video latents in a shared denoising space, allowing geometry to shape the generative distribution during training. To support this process, we build GeoVid-80K, an 80K-video dataset with paired appearance and geometry representations. Experiments on text-to-video and image-to-video generation show that VideoWeave improves geometric coherence while preserving strong visual quality. VideoWeave project page at https://videoweave.github.io/

Protein-ligand binding affinity (PLA) prediction is critical in drug discovery. Despite the notable advancements in machine learning-based approaches, existing methods struggle to jointly characterize local geometric organization and globally coordinated cross-molecular interactions, limiting their ability to model complex binding mechanisms. Here, we propose RicciBind, a geometric representation framework that integrates curvature-guided hierarchical structure learning with optimal transport (OT)-based cross-domain alignment to model molecular interactions. Specifically, RicciBind leverages Ricci curvature to capture local interaction tightness within molecular structures, enhancing structural awareness and organizing atomic interactions into curvature-aware hierarchical representations. An OT-based cluster matching mechanism then aligns protein and ligand clusters across heterogeneous domains under geometric constraints, enabling globally consistent correspondences and revealing higher-order interaction patterns beyond local neighborhoods. By coupling curvature-guided structure encoding with OT-driven cross-domain alignment, RicciBind effectively models complex interaction semantics and substantially improves both the accuracy and interpretability of binding affinity prediction. Extensive experiments demonstrate that RicciBind achieved superior predictive performance and generalization across PLA benchmarks and virtual screening tasks. Ablation studies further confirmed the essential role of Ricci curvature in enhancing molecular interaction representations.

Context adaptation automates prompt engineering in LLM-based systems by iteratively revising tunable prompts from task feedback, without modifying model weights. Extending this paradigm to multi-LLM agentic systems is crucial: existing methods suffer from inaccurate credit assignment and lack convergence guarantees. We propose \textbf{G}raph-based \textbf{T}arget \textbf{B}ack-\textbf{P}ropagation (GTBP), a context adaptation framework for agentic workflows modeled as directed acyclic graphs. GTBP propagates local target outputs backward through the workflow graph and uses target--output discrepancies to guide a stage-wise prompt update mechanism. Theoretically, we show that GTBP's stage-wise prompt updates become stable over iterations, and that a sufficiently capable LLM optimizer can decrease the overall objective. Empirically, GTBP consistently outperforms strong baselines across three benchmarks while maintaining comparable computational cost.

Vision-language-action (VLA) policies typically inherit their vision encoder from upstream VLM releases, but it is unclear whether an encoder choice validated on a small VLA transfers to a larger backbone. We introduce a frozen-backbone grafting diagnostic: the vision tower of a released VLA is replaced by a candidate encoder under a fixed protocol (adaptive average pooling, LayerNorm, and a single trainable linear projector), with the language model and action expert frozen. Across four encoders, two LIBERO suites, two backbones (SmolVLA-450M and $π_{0.5}$-3.3B), and two-to-three seeds per cell (40 main grafting runs plus native, LoRA, pooling, and zero-/shuffled-image controls, all scored by offline action MSE), the small-backbone winner does not reliably select the large-backbone top tier: SigLIP is best on SmolVLA across both suites, while on $π_{0.5}$ DINOv2-small leads the spatial suite and the object suite is a seed-sensitive near-tie band; three of the four backbone-suite comparisons (and 11 of 12 seed-level cells) support backbone-dependent rankings. The grafting wrapper is itself non-neutral with opposite sign across backbones (+45-56% MSE on the SmolVLA native tower, -50-52% on $π_{0.5}$), so all conclusions are conditional on the fixed grafting protocol. We position frozen grafting as a cheap target-backbone diagnostic to run before committing to an encoder at scale, not as a closed-loop deployment claim.

Large Language Models (LLMs) are increasingly deployed in healthcare settings, yet their tendency to hallucinate poses risks when clinical decisions are involved. This study examine whether LLMs recommend recently banned or withdrawn pharmaceuticals when answering clinical questions and tests an agent-based method for reducing such errors. We developed a five-agent "Trust but Verify" system using a single LLM backbone. To measure regulatory knowledge obsolescence, we created an adversarial dataset of 103 clinical MCQs where historically correct answers now refer to banned substances. This scale ensures statistical significance across various therapeutic classes. We evaluated three open-access model families (GPT-OSS, Llama-3, Falcon-3) under vanilla and agentic conditions. Performance was measured via pointwise score, label accuracy, Hallucination Error Rate (HER), and Component Fidelity (CF) score. We also observed clinical safety regression in proprietary models. In default configurations, all models showed high hallucination rates, consistently selecting banned drugs that matched training data patterns. Our proposed agentic architecture reduced HER by approximately 53% across models. Pointwise scores shifted from -0.25 (unsafe recommendation) toward 0.0 (appropriate refusal). The safety audit intercepted dangerous outputs even when models' parametric knowledge favored the banned substance. The proposed multi-agent framework offers a model-agnostic method for enforcing regulatory compliance that prioritizes patient safety over fluent text generation. Our work demonstrates a practical approach for deploying autonomous AI systems in safety-critical healthcare settings. It shows how real-time regulatory data can be integrated into LLM pipelines to support clinical decision-making.

Sound events are entities with semantic identities, locations, and trajectories, but current audio-language models usually reason about clips as global event content. Conversely, sound event localization models track source directions over time but offer limited semantic coverage for language reasoning. To address this gap, we introduce ST-AudioQA, a spatio-temporal audio QA dataset and benchmark built from first-order ambisonic (FOA) renderings of static and moving sound sources. Each scene provides source identity, activity, direction, distance, and motion metadata, enabling dense trajectory supervision and questions about what is sounding, where it is, how it moves, and how sources relate. We further propose ST-Audio Encoder, a time-resolved FOA audio encoder that learns event semantics together with source trajectories, and ST-AudioLM, which connects the audio tokens from the encoder to an LLM for spatio-temporal audio QA. Experiments show that this representation improves the semantic-localization tradeoff and yields stronger reasoning performance than static spatial and localization-oriented baselines.

Full waveform inversion (FWI) recovers subsurface velocity from seismic recordings by solving a severely ill-posed, nonconvex PDE-constrained optimization. Classical regularizers stabilize the inversion but fail to reproduce realistic geological structures; recent diffusion-prior methods improve realism at the cost of a fragile trade-off between data fidelity and prior consistency. We propose Decoupled Latent Optimization (DLO), which relaxes the standard latent-optimization formulation into a quadratic-penalty objective over an auxiliary physical variable and a latent variable. The data-fidelity gradient acts in physical space, the diffusion sampler contributes only through a decoded prior sample, and the standard smoothed-velocity initialization of classical FWI is preserved. On the OpenFWI benchmark, DLO outperforms classical regularizers and existing diffusion-based methods under clean, noisy, and missing-trace acquisitions. The prior, trained on 70*70 OpenFWI models, transfers directly to the Marmousi and Overthrust benchmarks, where DLO recovers intricate fault structures and remains robust to initialization smoothing and measurement noise.

Constructing predictive models of nonlinear dynamical systems from measurement data is a longstanding problem in systems identification and control. Although Neural ordinary differential equations~(Neural ODEs), Koopman operator approximations, and input-aware architectures have each moved the field forward, none simultaneously addresses environment-varying operating conditions, rigorous stability guarantees, and input-to-state stability (ISS) certification within a unified trainable framework. This paper introduces Environment-Aware Stable Neural Koopman Dynamics Learning (ESNKD), which integrates four components: (i)~a bundle-structured encoder that maps environmental observations to a geometrically regularized latent manifold, drawing on the fiber bundle framework; (ii)~an input-conditioned Neural ODE whose residual term handles arbitrary external signals, extending the input concomitant philosophy; (iii)~a contraction synthesis layer enforcing convergence via Persidskii-type tractable linear inequalities, analogous to the certification mechanism; and (iv)~a Koopman lifting stage with LMI-based ISS verification that follows the theoretical pipeline of. Theoretical guarantees cover solution existence and uniqueness, incremental exponential stability, ISS with explicit gain bounds, and robustness to environmental perturbation. Experiments on five benchmark systems, including two robotic manipulation platforms, show consistent improvements over five competitive baselines in both prediction accuracy and safety certification rates.

Safe coordination problems surface in multi-agent reinforcement learning when global safety cannot be enforced by any agent unilaterally: the admissibility of one agent's action may depend on the dynamics of other agents. Decentralised shields can enforce safety at runtime, but purely factorised permissions often exclude optimal team behaviour that is safe only through coordination. We study deterministic safety guarantees for agents trained and deployed under decentralised execution, recovering team-optimal safe behaviour without centralised runtime control. Agents have a shared global specification $φ$ in the safety fragment of Linear Temporal Logic ($\mathsf{LTL}_{\mathsf{safe}}$ ), and select among tuples of local $\mathsf{LTL}_{\mathsf{safe}}$ obligations whose conjunction implies the global specification $φ$. Each agent may rely on the other agents' local obligations as assumptions because the whole contract tuple is certified simultaneously and allows projection into local action masks. At learning time, a non-stationary multi-armed bandit chooses among a library of local $\mathsf{LTL}_{\mathsf{safe}}$ obligations to select the tuple that optimises team reward, all without forgoing end-to-end safety. We evaluate the approach across 6 environments and 15 algorithmic variants.

Reconstruction-based anomaly detection is attractive for industrial inspection, but scaling it from category-specific training to a one-for-all setting is challenging. A single model must reconstruct diverse normal appearances without copying abnormal details, which exposes two coupled failure modes: identical shortcut, where anomalies pass through the reconstruction path, and mis-reconstruction, where normal categories are confused with one another. We propose \textbf{BoRAD}, a label-free training framework that treats this as a representation-capacity allocation problem. BoRAD uses a shared learnable prototype bank to impose two complementary regularizers: spatial prototype alignment contracts local within-prototype variation to suppress anomaly copying, while prototype-relative global alignment preserves between-prototype structure and improves sensitivity to abnormal angular deviations. The prototype bank and prediction heads are used only during training; inference remains a standard teacher-student feature discrepancy pass, with no class labels, negative pairs, memory retrieval, or prototype lookup. BoRAD achieves competitive one-for-all anomaly detection performance, including 86.2\% mAD on MVTec AD, 80.7\% mAD on VisA and 73.1\% mAD on Real-IAD. Diagnostic analyses further show reduced anomaly leakage, improved normal-category separability, and stronger anomaly-normal score separation.

Inversion-based image editing offers flexible and training-free control but still struggles with inversion accuracy and the trade-off between editing fidelity and background preservation. While recent methods improve inversion formulations or attention interactions, the role of textual conditioning in shaping diffusion dynamics and editing behavior remains underexplored. We show both empirically and theoretically that the precision of textual conditioning influences inversion stability by modulating the geometry of the diffusion velocity field, while also affecting the consistency of cross-branch attention during editing. These effects directly impact background preservation and semantic fidelity. Building on this analysis, we propose SimEdit, a conditioning-aware framework with two complementary components: (a) conditioning refinement, which constructs conditioning signals with improved semantic precision and structural alignment to facilitate stable inversion and consistent attention manipulation, and (b) token-wise cross-branch attention control, which separates edit-relevant and structure-preserving components and modulates them asymmetrically during attention manipulation. Extensive experiments on PIE-Bench demonstrate that SimEdit consistently improves both inversion reconstruction quality and editing performance over previous attention-manipulation approaches. Our code is available at https://github.com/zju-pi/SimEdit.

Byte-level tokenization enables language models to handle any Unicode input, but models can generate invalid UTF-8 sequences when encountering rare or unseen characters. We investigate the relationship between training scale and UTF-8 generation reliability with a 355M parameter model trained on 80B tokens from a balanced multilingual corpus of English, Japanese, Korean, and Chinese. We introduce multiple evaluation protocols that isolate UTF-8 structural validity from language modeling. UTF-8 validity convergence lags perplexity by a roughly a factor of two: perplexity stabilizes after 2.1B tokens, but UTF-8 validity requires 4.2B tokens. In context-free generation, rare characters achieve higher structural validity than common characters, suggesting over-specialization of frequent character representations. Through experiments, we observed that reliable UTF-8 generation is a distinct capability requiring evaluation beyond perplexity.

Fault diagnostics and recovery in smart factories is challenging because critical information is dispersed across manuals of multiple machines which are interconnected through the manufacturing process. Large Language Models (LLMs) can provide a promising approach. In this paper, we propose FactoryLLM, a safe and open-source AI playground designed for evaluating different LLM-based retrieval-augmented generation (RAG) models by analysing documents from multiple machines across the manufacturing process. FactoryLLM enables the user to configure the LLM, and assess performance when reasoning over multiple documents, through a dual evaluation setup using both RAGAS and NVIDIA's LLM-as-a-Judge metrics. FactoryLLM is safe because it allows users to run local or open-source LLMs without sharing sensitive industrial data, providing a controlled environment for experimentation. We demonstrate the efficacy of FactoryLLM through a case study which involves an Autonomous Intelligent Vehicle and its Mobile Planner software, evaluating three LLMs across 30 maintenance queries derived from approximately 600 pages of cross-machine documentation. The results suggest that FactoryLLM is effective in cross-machine document reasoning: every model achieved a groundedness score above 0.88. The full code and documentation for community to test FactoryLLM with their manufacturing specific scenarios are publicly available.

We introduce Adelic operation-preserved embeddings (AOE), a training-free representation that captures both a number's real value and its modular (p-adic) signatures. This construction preserves additive and multiplicative structure by design, turning numerical input into embeddings that "speak in the language of mathematics." Unlike prior approaches that rely on task-specific retraining, AOE is plug-and-play and drops seamlessly into existing architectures. On algebraic combinatorics benchmarks, it delivers consistent gains including the first-ever perfect accuracy on the Weaving Pattern task-while suggesting a principled path forward for overcoming the long-standing "number problem" in AI.

Graphical User Interface (GUI) agents are increasingly used to automate complex computer tasks across applications, websites, and operating systems. To improve their reliability, recent work has introduced experiential memory, where agents retrieve prior trajectories to guide decision-making in similar states. More recent approaches further extend this idea to visual memory by storing and retrieving screenshots from past interactions, providing agents with richer contextual information than text-only memories. However, the effect of visual memory in GUI agents remains insufficiently understood: it is unclear which failures visual memory mitigates, or which failures it exacerbates. To systematically analyze the effect of visual memory, we introduce a taxonomy of four GUI agent failures (i.e., cognitive failure, visual state misunderstanding, hidden operation blindness, and grounding error) that map to distinct stages of the perception-reasoning-action pipeline. We find that prepending full-image memory has a divergent effect on the failure distribution: it reduces state-level failures but worsens action-level ones, and increases hidden operation blindness and grounding error. Motivated by this finding, we propose Action-Grounded Visual Memory (AGMem), an action-grounded memory framework for GUI agents. The core idea of AGMem is to store image crops that capture the local GUI region closely related to a successful action or a recovery, rather than storing full screenshots. Experiments on OSWorld show that AGMem improves task success rates by 33.3 % over full-image memory. These results demonstrate that AGMem is an effective representation for visual memory in GUI agents.

Micro-actions are short-duration, low-amplitude subtle body movements at the whole-body level that can reveal latent intentions, involuntary reactions, and fine-grained affective changes. Our previous MA-52 benchmark has provided an important foundation for micro-action recognition, but it remains limited in scale, scene diversity, task coverage, and evaluation protocols. To advance micro-action analysis toward more realistic and comprehensive settings, we introduce MMA-82, a large-scale multi-domain extension of MA-52. MMA-82 expands the label space from 52 to 82 fine-grained micro-action categories and covers four distinct domains, including laboratory interviews, street interviews, psychiatric patient interviews, and emotion-rich television videos, resulting in 77,856 annotated instances from 454 subjects. Built upon MMA-82, we establish two core tasks: Micro-Action Recognition and Multi-label Micro-Action Detection. For recognition, we further define in-domain and cross-domain protocols, including few-shot and zero-shot settings, to evaluate model robustness, transferability, and generalization. Extensive experiments show that current methods still struggle with realistic micro-action understanding, especially under domain shift, long-tailed category distributions, and complex temporal localization. Beyond benchmarking, we investigate the relationship between micro-actions and emotion, showing that micro-actions are strongly associated with emotional states and provide complementary cues to facial micro-expressions for improved emotion recognition. These results demonstrate that MMA-82 serves as a comprehensive and challenging benchmark for realistic micro-action analysis and a valuable resource for human-centered AI. MMA-82 is available at https://github.com/LpyNow/MMA-82.

Conventional RGB cameras have been widely used in multi-object tracking due to their ability to capture rich appearance and semantic information. However, their performance is often degraded under complex real-world challenges, such as motion blur, low illumination, and overexposure. Bio-inspired event cameras offer high temporal resolution and high dynamic range, providing complementary cues under extreme scenarios. Nevertheless, RGB-event multi-object tracking remains underexplored due to the lack of large-scale and well-annotated datasets. To address this issue, we propose FEMOT, a large-scale RGB-event multi-object tracking dataset that covers diverse real-world scenarios and 14 challenging attributes. With both RGB and event data as well as high-quality annotations, FEMOT provides a reliable platform for systematically evaluating RGB-event multi-object tracking methods. Based on FEMOT, we retrain and evaluate over ten strong trackers, thereby establishing a comprehensive benchmark for future research. Furthermore, we propose FEMOTR, a multimodal tracking framework that decouples RGB and event features and fuses them in the frequency domain, thereby effectively exploiting their complementary characteristics for robust object localization and identity association. Extensive experiments on FEMOT and DSEC-MOT datasets demonstrate the effectiveness of the proposed method. The source code and benchmark dataset have been released on https://github.com/Event-AHU/FEMOT.

Diffusion-based Vision-Language-Action (VLA) policies enable strong generalization in robotic manipulation, but remain sensitive to spurious visual correlations and noisy action generation, leading to brittle behavior under perturbations. We introduce Selected Diffusion Noise (SDN), a simple, training-free test-time method that improves both robustness and success rate by leveraging the diffusion noise space as a controllable degree of freedom. SDN dynamically samples noise vectors that are maximally separated from a reference set to mitigate reliance on spurious cues, while selecting candidates that yield more coherent action trajectories. This dual objective encourages stable behavior even under object-masked observations and reduces action jitter without modifying model parameters. We evaluate SDN on two simulation benchmarks (Google Robot, Widow-X) and two real-world robotic datasets across multiple VLA policies, including pi_0, Groot-N1.5, and Groot-N1.6. SDN consistently improves success rates by +8% in simulation and +10% in real-world settings, while producing smoother and more stable actions. Our results highlight that diffusion noise selection can serve as an effective and general mechanism for enhancing VLA policies at test time.

Humans rely on directional fingertip forces to probe and regulate contact during manipulation, yet most wearable haptic gloves render only vibration or single-axis force, leaving force direction ambiguous. Without directional cues, users must infer contact force from vision alone, often leading to over-pressing, inconsistent control, and reduced precision in robotic teleoperation. We present the N2D Haptic Glove, a multi-finger wearable device that renders planar flexion-extension fingertip forces using capstan-drive transmissions for high-transparency force feedback. Through benchtop validations and a user study involving haptic teleoperation of a robotic arm and hand, we demonstrate that compared to visual-only and single-axis haptic baselines, planar fingertip feedback significantly reduces contact force error during precise manipulation, improves trial-to-trial consistency, and enhances overall user experience in axial probing tasks. These findings establish the N2D Haptic Glove and directional finger-based haptics devices as a promising modality for contact-rich teleoperation, immersive virtual reality simulations, and robot learning from demonstrations. N2D Haptic Glove's hardware and software system will be fully open-sourced at \href{https://ucsdarclab.github.io/n2d-glove/}{this https URL}.

Rapid post-event landslide mapping is essential for disaster response but remains difficult to automate due to extreme class imbalance. This study evaluates whether Clay v1.5, a Geo-Foundational Model (GFM), can improve pixel-level landslide segmentation on the Landslide4Sense (L4S) benchmark, which contains 3,799 training chips with 14 Sentinel-2 and terrain bands and approximately 2% positive pixels. We compare three strategies: Clay as the primary encoder with multi-scale residual terrain fusion, a U-Net backbone augmented with Clay semantic context at the bottleneck, and a standard U-Net baseline. The hybrid U-Net + Clay model with two-stage Low-Rank Adaptation (LoRA) achieved the best test F1 of 64.5 +/- 1.8% over three seeds, surpassing the Clay-only backbone (55.2 +/- 3.6%) and the U-Net baseline (59.9%). Clay as a standalone encoder underperformed the U-Net due to the absence of multi-scale skip connections, but its pretrained representations consistently improved performance when injected as auxiliary context. These findings suggest that GFMs are most effective for landslide detection when they complement spatially detailed convolutional architectures rather than replace them.

We propose ShearFuse-UNet, a lightweight and computationally efficient deep learning model for next-day wildfire spread prediction from multi-modal satellite data. The model integrates three complementary transform-domain branches inside each encoder block of a U-Net backbone: a 2D Fast Walsh-Hadamard Transform (WHT) branch, a 2D Discrete Cosine Transform (DCT) branch, and a cone-adapted digital Shearlet residual branch. The WHT and DCT branches establish orthogonal latent spaces with learnable spectral scaling and fixed soft-thresholding, while the Shearlet branch provides anisotropic, multi-directional feature decomposition that explicitly encodes the elongated edge structures characteristic of fire fronts. A learned SpectralFusion gate adaptively combines the WHT and DCT responses, and the Shearlet reconstruction is added as a residual. This three-branch design bears a loose structural analogy to transformer self-attention: the WHT and DCT branches provide complementary spectral representations that are adaptively fused, while the Shearlet branch contributes directional content through a residual pathway. Unlike self-attention, the proposed design relies on fixed mathematical transforms rather than learned projection operators, reducing parameter count and computational cost. Evaluated on the WildfireSpreadTS dataset, ShearFuse-UNet achieves an F1 score of 0.596 with only 267k parameters, outperforming a ResNet18-based U-Net (14M parameters, F1 = 0.589) and demonstrating a highly favorable accuracy-efficiency trade-off. Results on the Google Next-Day Wildfire Spread dataset further validate these findings across a different benchmark.

Existing studies on gender bias in LLMs have largely focused on stereotypes, occupational associations, or explicit harmful outputs. In this work, we ask whether LLMs apply consistent response standards to the same negative behavior under matched male-actor and female-actor conditions. We introduce GAMA-Bench, a gender-mirrored benchmark of 1,298 scenarios covering intimate relationship and public social conflicts. It constructs gender-neutral misconduct templates through controlled grids and cross-model review, then compiles them into paired first-person prompts with matched actor-gender and role-reference variations. We further design a structured response-framing protocol to measure how models allocate punishment, empathy, escalation, instruction, and blame. Experiments on 10 representative LLMs reveal a consistent male-disadvantaging asymmetry: male actors receive more punitive, escalatory, and blame-centered framing, whereas female actors receive more therapeutic and empathy-oriented framing for the same misconduct. Further analyses show that this pattern persists across model families, scenario tracks, model scale, and explicit thinking-style reasoning. The official code is available at https://github.com/xufeiqiong/GAMA-Bench.

We study near-symmetric resonant stratified media to show how a tiny broken spatial symmetry can effectively be probed by structured light with or without orbital angular momentum. This is achieved by examining both the in-plane and out of plane Goos-Hänchen and Imbert Fedorov shifts, respectively, in the reflected light, magnified by resonant enhancement and weak value amplification. We show that non-reciprocity in reflection for illumination from opposite ends can result in different shifts, even to the extent of shifts with opposite signs for tiny imbalance resulting from the broken symmetry. We believe that our results can lead to new type of extra-sensitive sensors for any agent (eg. refractive index, displacement, etc.) that can break the symmetry.

Adversarial conditions such as paraphrasing and targeted style transfer sharply degrade the accuracy of machine text detectors. A document, however, carries multiple complementary signals (e.g., stylistic features, likelihood and rank-order features, and structural features), and an attack that suppresses one may leave others intact. While a parametric classifier can learn to combine these features given sufficient supervision, classifiers are prone to making confidently incorrect predictions when the distribution shifts (e.g., novel attacks or unseen language models). To address this, we propose a multi-view, non-parametric detection framework that extracts complementary feature views from the same document and aggregates per-view evidence through a Gaussian process ensemble. By aggregating evidence across views, an adversary must simultaneously defeat multiple independent axes of detection, substantially raising the cost of evasion. The Gaussian process formulation additionally provides calibrated probabilities and principled abstention on out-of-distribution inputs, supporting reliable deployment in high-stakes settings. We evaluate on three benchmarks spanning diverse generators and attacks: the DetectRL and RAID benchmarks, and the PAN2025 shared task and demonstrate that our multi-view detector maintains strong performance under the considered attacks, outperforming existing approaches against held out attacks.

Reactive capability is a key property of data-driven behavior world model simulators for autonomous driving simulation systems. With this capability, simulated world agents can respond feasibly to autonomous vehicle (AV) behaviors that differ from the log. However, existing behavior simulation benchmarks do not directly measure reactive capability. They often let the simulator jointly control the AV and surrounding agents and evaluate realism through log similarity or open-loop prediction metrics. In this work, we introduce ReactSim-Bench for evaluating the reactive capability of behavior world model simulation in autonomous driving. We decouple the control of agents and the AV, using AV behaviors that differ from the log and require agents to respond as independent AV inputs. To obtain these AV behaviors, we construct a pipeline that uses an AV planner model to generate candidate behaviors and filters the data using rules and manual verification. Collision metrics, map-based metrics, and kinematic feasibility metrics are used to evaluate the safety and rule compliance of reactive responses. We construct 2,636 test scenarios with three categories and conduct a systematic evaluation of state-of-the-art models across multiple architectures, including Transformer-based, diffusion-based, and next-token-prediction-based models. We further analyze how replan frequency affects performance and provide insights for future studies.

In this work, we propose a Nonlinear Pluggable Optic (NLPO) transceiver that combines the low latency and low power consumption of Linear Pluggable Optics (LPO) with the range and robustness of digital signal processing (DSP)-based transceivers. The proposed NLPO uses an analog photonic Next-Generation Reservoir Computing (NGRC) architecture, constructed on a photonic integrated circuit (PIC), to compensate for electrical-domain distortions as well as optical-channel impairments from chromatic dispersion and Kerr nonlinearity. Focusing on a simulated 50 GBd PAM-4 link, we find that the NGRC-based NLPO not only extends the range of LPO, but actually outperforms DSP-based solutions as well. Our simulations reveal two key advantages compared to DSP-based Intensity Modulation/Direct Detection (IM/DD) links: (1) the NGRC can take advantage of the optical phase information without requiring a local oscillator and (2) the NGRC can optically sample the transmitted data well above the symbol rate without requiring high-bandwidth electronics. This work showcases the potential for photonic NGRCs to outperform state-of-the-art digital solutions in real-world applications and opens a path to low-latency, lower-power IM/DD links at ranges of 10s of km.

World action models (WAMs) have recently shown promise in jointly modeling future observations and executable robot actions. However, most existing WAMs still operate in 2D video or latent spaces, where visually plausible rollouts miss the 3D spatial constraints and occluded contact geometry required for precise manipulation. While geometric foundation models offer strong priors for recovering dense 3D structure and motion from visual observations, forcing WAMs to predict the dense 4D representation introduces costly geometric decoding and slows down causal action generation. To address the trade-off, we present WAM4D, a fast 4D world action model that uses lightweight spatial register tokens as training-time future-depth readouts to transfer pretrained geometric priors into a causal video-action transformer, then removes the register branch for lightweight action inference. To prevent non-causal shortcuts, we further design causal mixture attention for the Mixture-of-Transformers (MoT) WAM backbone, defining modality-specific visibility among video, action, and geometry tokens. Comprehensive experiments on RoboTwin 2.0 and challenging real-world manipulation tasks show that WAM4D improves spatial consistency and achieves competitive action prediction while maintaining efficient inference.

Long-context language modeling requires not only extending context windows but maintaining coherent understanding of entity states and relationships across thousands of tokens -- a challenge that semantic similarity alone cannot address. KGERMAR addresses this by constructing dynamic, context-specific knowledge graphs from input text during inference, enabling domain-adaptive retrieval that leverages both semantic similarity and explicit entity relationships. The framework performs real-time entity and relation extraction to build contextual knowledge graphs, then integrates graph-structural embeddings with textual semantics through a multi-component memory architecture. Three memory banks -- contextual, semantic, and structural -- are maintained with retrieval signals fused via learned weights to capture both surface-level semantics and deeper relational patterns. Evaluated on SlimPajama (84.7K training examples), WikiText-103 (4,358 examples), PG-19 (100 examples), and Proof-pile (46.3K examples), KGERMAR achieves up to 8.5\% lower perplexity and 2--2.5x better memory efficiency than memory-augmented baselines across context lengths from 1K to 32K tokens, with superior in-context learning performance across five NLU tasks. The dynamic knowledge graph construction approach advances memory-augmented language modeling by enabling domain-specific knowledge representation that adapts to input contexts rather than relying on fixed knowledge bases.

Zero-shot text-guided diffusion has significantly advanced image editing; however, its practical usability remains constrained by three persistent challenges: prompt brittleness that requires meticulous prompt engineering, spillover edits that unintentionally affect non-target regions, and failures on small or cluttered objects caused by limited fine-grained supervision in training data. We propose FocusDiff (Target-Aware Refocusing for Tuning-Free Diffusion Editing), a tuning-free framework for precise and region-specific image manipulation based on refocusing cross-attention. Given a target region obtained through automated segmentation or manual selection, FocusDiff applies selective blurring to non-edit areas to guide attention toward the masked region while accurately transferring the object's identity, structure, and appearance to the edited output. Integrated context-preserving modules further ensure background fidelity and global coherence, enabling accurate edits from simple text prompts in a single pass. We also extend FocusDiff to 360-degree indoor panorama editing and demonstrate its effectiveness within virtual reality environments. Extensive experiments on our localized editing benchmark LIMB, comprising 30 multi-object images and 100 annotated examples including challenging small-object cases, show that FocusDiff outperforms existing zero-shot editors in text-image alignment and background preservation, achieving superior precision, photorealism, and usability. The project page is available at https://vdkhoi20.github.io/FocusDiff.

Streaming speaker diarization is crucial for time-critical medical dispatch, but deploying it on resource-constrained hardware requires smaller, faster models. Using SIMSAMU, a dataset of simulated medical-dispatch conversations, we evaluate streaming behavior before compressing the segmentation model with pruning and low-bit quantization. We characterize performance across a range of streaming latency budgets and find that additional buffering is not consistently beneficial, while very low-latency operating points can substantially degrade performance. Our study shows that model compression trades performance for memory footprint, and we highlight an operating point where FP16 reduces model size by half with essentially unchanged real-time factor, at a cost of a 40\% relative DER increase against the baseline. This work characterizes the trade-offs for real-time deployment and contributes to speech technology that can enable reliable human communication in time-critical contexts.

Agentic browsers integrate autonomous AI agents into web browsers, enabling users to accomplish web tasks through natural-language instructions. The same-origin policy (SOP) is a fundamental browser security mechanism that prevents unauthorized automated cross-origin data flows induced by scripts. However, whether SOP remains effective in agentic browsers is an open question that has not been systematically studied. In this work, we bridge this gap. We first observe that an agentic browser can itself serve as an automated channel for cross-origin data flows, potentially leading to SOP violations. To investigate this phenomenon, we construct SOPBench, a benchmark for evaluating SOP violations in agentic browsers. Our evaluation shows that existing agentic browsers frequently violate SOP, both in benign settings and under attacks. To address this problem, we propose SOPGuard, an SOP enforcement mechanism tailored to agentic browsers. We implement SOPGuard in BrowserOS, an open-source agentic browser. Extensive evaluations demonstrate that SOPGuard effectively enforces SOP while preserving utility and incurring only a small runtime overhead. Our code and data are available at https://github.com/wxl-lxw/BrowserOS-SOPGuard.

Fashion sketching is a cornerstone of design workflows, allowing rapid visualization of creative concepts prior to physical prototyping. Yet, progress in sketch-based fashion image synthesis has been hindered by the absence of large-scale, high-quality paired resources. To bridge this gap, we present GarmentSketch, a novel dataset comprising 26,249 fashion sketches across 21 garment categories, each paired with detailed textual descriptions. Captions were produced through a multi-stage pipeline that integrates multiple multimodal large language models (MLLMs) with human-in-the-loop refinement, ensuring both semantic accuracy and descriptive richness. We benchmark GarmentSketch on state-of-the-art generative models, providing baseline performance for sketch-guided text-to-image generation. Our experiments reveal both the promise and the current limitations of existing methods. By offering a comprehensive and richly annotated resource, GarmentSketch establishes a foundation for advancing sketch understanding, fine-grained fashion image generation, and creative human-AI collaboration in design. The dataset will be available at: https://khangbdd.github.io/garmentsketch.

Vision-Language-Action (VLA) models have shown strong potential for end-to-end autonomous driving by jointly modeling visual perception, language reasoning, explainability and action prediction. However, their large vision-language backbones and reasoning modules introduce substantial inference latency and thereby prevent their deployment in the unforgiving reality of the road networks. We propose RT-VLA, a lightweight, distilled VLA model that transfers the driving and reasoning capabilities of the state-of-the-art SimLingo model into a compact student through multi-level supervised distillation. RT-VLA preserves language-based reasoning and supports post-hoc explanation through offline language analysis of safety-critical driving moments without adding latency to real-time control. Compared to the SimLingo teacher, RT-VLA maintains competitive closed-loop driving and language reasoning performance while reducing inference time by 44.8X in vision-only mode and 7.9X in vision+language mode. These results suggest that supervised distillation is a practical approach for building real-time, explainable VLA-style autonomous driving models.

Recent work has demonstrated that coding agents can formalize entire advanced mathematics textbooks in Lean 4, yet existing efforts concentrate on branches of mathematics already well-represented in mathlib and measure success solely through kernel acceptance. We address both limitations by applying a coding agent to formalize Numerical Methods for Ordinary Differential Equations, a textbook in numerical analysis that is largely absent from mathlib, stressing the agent's capacity to develop new theory from scratch. We further introduce a systematic, reproducible three-dimensional framework for evaluating the quality of agent-produced formalizations beyond compilation: semantic correctness, Mathlib reuse, and cross-file reuse via LLM-as-judge methods. Applying this framework to our own formalization and to the released outputs of RepoProver and M2F, we uncover recurring unfaithful formalization patterns, including incomplete multi-part statements, added weakening hypotheses, and parameter restrictions, that kernel acceptance entirely obscures. Our results suggest that compilation-based metrics substantially overstate formalization quality, and we provide a reproducible audit methodology to support more rigorous evaluation of future autoformalization systems.

AI coding agents have rapidly transformed software engineering, powering widely used interactive coding assistants. Despite their interactive real-world use, existing benchmarks evaluate them as fully-autonomous systems. In this work, we introduce Dialogue SWE-Bench, an automatic benchmark dataset for evaluating the ability of coding agents to resolve real-world software engineering problems through dialogue with a user. We design a novel, persona-grounded user simulator to support our task evaluation, and augment our task evaluation with automatic evaluations of dialogue quality. We also propose a new schema-guided agent, aimed at improving the dialogue capabilities of off-the-shelf coding agents, which improves over strong baselines by 3-14%. Our results indicate that better coding models do not always correspond to better dialogue models, suggesting that dialogue capability is a distinct and currently understudied dimension of coding agent performance.

LLM-based Agents are becoming increasingly capable and widely deployed, creating growing incentives for adversarial misuse in the real-world. A key emerging threat is Decomposition Attacks \cite{glukhov2024breach, jones2024adversaries} in which a harmful task is broken into simpler, benign subtasks that evade safety mechanisms when executed separately but cumulatively fulfill the malicious intent. Although recent benchmarks assess agent safety in multi-turn and multi-tool-use settings, they do not explicitly capture this form of decompositional misuse and may not represent realistic adversarial execution flows. To this end, we introduce DeCompBench, a benchmark designed specifically to evaluate agentic safety under decomposition attacks. DeCompBench is created with a decomposition-by-design principle using a graphical framework and enables harmful task decomposition into individually benign and executable subtasks with realistic workflows. Our experiments using a custom decomposer show that state-of-the-art agents exhibit high refusal rates on monolithic harmful tasks, but significantly lower refusal rates on their decomposed variants, while often inadvertently fulfilling the adversarial objectives. These findings underscore the need for safety evaluations against decomposition attacks and corresponding defenses. Our dataset is publicly available and can be found at https://huggingface.co/datasets/decompositionbench/DeCompBench.

Learning with missing modalities is a fundamental challenge in multimodal robot learning, as real-world robotic systems often operate in environments with incomplete sensor data. Attention-based models are appealing for processing multimodal data because they can handle multiple modalities with a single backbone network. However, most multimodal models assume that all modalities are available during both training and inference, limiting their applicability in robotic perception and decision-making. In this paper, we introduce a multimodal model designed to handle missing modalities during both training and inference. The model is formulated as a conditional variational autoencoder (CVAE) and incorporates a transformer-based architecture that leverages attention mechanisms to learn a unified, fixed-dimensional representation, even when some modalities are missing. We show that our proposed model can be trained with missing modalities while approximating a robust representation of all modalities. We evaluate our approach on five multimodal datasets across two robot learning tasks: human trajectory prediction and robot manipulation forecasting. Experimental results demonstrate that our model effectively learns from incomplete data and is superior to prior multimodal fusion approaches.

Researchers and practitioners working with large language models face a fragmented landscape: local models are free and private but hardware limits the model size and context windows a researcher can use; institutional HPC centers offer powerful GPU resources at no marginal cost and keep data within institutional boundaries, but operate behind firewalls and are designed for batch jobs rather than interactive use; commercial cloud APIs provide frontier-model quality on demand but impose significant cost and data retention policies unsuitable for sensitive research data. No existing system unifies all three. STREAM (Smart Tiered Routing Engine for AI Models) addresses this gap with four contributions: (1) a three-tier routing architecture combining local, HPC, and cloud inference with a local LLM-based complexity judge; (2) a dual-channel HPC streaming architecture that separates the Globus Compute control plane (authentication and job dispatch) from a WebSocket relay data plane (token delivery), enabling sub-second TTFT (0.54 s median, 21.1x over batch mode's 11.40 s) through institutional firewalls without VPN or firewall rule changes, with end-to-end AES-256-GCM encryption ensuring the relay operator cannot read token payloads; (3) tier-aware context summarization that prevents long conversations from forcing simple queries onto expensive tiers; and (4) an HPC-as-API proxy mode that exposes HPC inference as an OpenAI-compatible endpoint callable from any standard client with no HPC expertise, a deployment pattern made practical only by the sub-second TTFT of contribution (2). Llama 3.2 3B achieves 85.1% free-tier retention on a 1,200-query benchmark spanning ten domains. Measured TTFT: 0.26 s local, 0.54 s HPC (relay), 1.68 s cloud.

Learning-based video compression has recently achieved competitive rate-distortion performance compared to conventional video codecs. However, most existing methods rely on non-invertible analysis-synthesis transforms, with reconstruction quality subject to both quantization and transform approximation errors. This limitation becomes particularly restrictive at higher quality points, where quantization errors are small and transform-induced distortion dominates. To address this, we propose InnVC, an Invertible neural network based Video Codec for wide-range and high-fidelity compression. The core idea is to preserve an invertible main transform path prior to quantization, while injecting content-adaptive context through a compact implicit conditioning field. This decouples strongly correlated video content from harder-to-model fine details, allowing different components to specialize in complementary reconstruction tasks for more efficient compression. To further improve compressibility, we introduce a scheduled masking strategy that progressively concentrates informative content into fewer latent channels for more effective entropy coding. Experiments on the UVG and MCL-JCV benchmarks show that InnVC achieves strong compression performance over a broad quality range, being particularly effective in the high-quality regime, yielding BD-rate reductions of 21.66% in PSNR and 46.06% in MS-SSIM relative to x265 on UVG. To the best of our knowledge, InnVC is the first neural video codec covers operating poins from low bitrate to high fidelity within a single architecture scale, spanning more than 20 dB in PSNR.

Modern LLM-powered autonomous agents increasingly rely on rich user interface (UI) state observations to achieve reliable action grounding in complex digital environments. However, many deployments transmit the full UI state to remote inference servers even when most elements are irrelevant to the current task, which can leak sensitive but unnecessary context such as authentication codes, private notifications, and background application states. We propose MINIM, a trusted local broker that performs privacy-aware minimization on the client side before any observation leaves the device. Grounded in Contextual Integrity (CI), MINIM learns a dual-score representation for each UI element by predicting an inherent sensitivity score (s) and a task-conditioned necessity score (n). These scores drive a ternary disclosure policy that keeps essential elements, abstracts sensitive attributes when needed, and removes task-irrelevant content. We optimize a CI-aware objective that penalizes necessity errors more strongly on high-risk content, enabling aggressive pruning while preserving task-critical information. Experiments on real-world UI observations derived from WebArena show that MINIM substantially reduces task-irrelevant sensitive leakage while preserving task-critical semantic context and the interactive affordances required for reliable agent actions.

Rare diseases affect over $300$ million patients across more than $7{,}000$ conditions, yet no single hospital encounters enough cases of any one condition for reliable diagnosis. Cross-hospital collaboration could help by allowing a diagnosing institution to use distributed, case-specific diagnostic evidence, but privacy regulations restrict the transmission of identifiable clinical text across institutional boundaries. This setting raises two challenges: existing medical agent systems often rely on textual evidence exchange, while raw latent states such as hidden states and KV caches may still reveal prompt-derived clinical content. We introduce MedLatentDx, a latent multi-agent communication framework in which hospital agents keep private clinical records and retrieved cases local, and send compact latent KV blocks to a host agent for rare-disease diagnosis. MedLatentDx supports two deployment settings: same-backbone hospital agents use latent KV distillation, while hospitals with different LLM backbones use cross-family latent alignment. On CrossRare-Bench, a self-built large-scale rare-disease benchmark with hospital-level partitions, MedLatentDx improves cross-hospital diagnostic performance while reducing reconstructable clinical content relative to raw-latent communication baselines.

Automated International Classification of Diseases (ICD) coding is a core medical-coding task for billing, epidemiology, and clinical decision support. Generative large language models (LLMs) are often reported as weak medical coders, but this finding mainly comes from inference-time settings such as prompting, retrieval, reranking, or tool use, leaving the role of task-specific post-training underexplored. We present a controlled empirical study of post-training for generative ICD coding, comparing discriminative baselines with LLM coders across prompting, supervised fine-tuning, and reinforcement learning under a common protocol and metric set. To our knowledge, this is the first study to evaluate RL-based post-training for generative LLM coders in ICD coding. We further introduce PHI, a diagnostic curriculum that extends GRPO to refine missed-code cases. Our results show that prompting-only evaluation substantially underestimates the potential of LLMs for ICD coding. SFT provides the main capability jump, GRPO further improves code-set prediction beyond SFT, and PHI provides targeted gains on macro-level performance. These findings suggest that the main bottleneck is not the generative formulation alone, but how the model is adapted and optimized for full-taxonomy recall. We release our code, data splits, and checkpoints at https://github.com/AlexandreWANG915/LLM4ICD.

Humans cannot always intuit what scenarios are most challenging to LLMs. Hoping to capture challenging edge cases, developers either design problems to be difficult for humans or curate extensive benchmarks. What if we could instead anticipate which scenarios a model will fail on? In this paper, we use an LLM's representational geometry to predict which concept combinations it will fail on. We attribute this compositional failure to interference between salient features. In tasks that require systematic composition - toy programmatic settings, multihop reasoning, multilingual factual recall - we find that when a pair of concepts is encoded near-orthogonally, the model reliably composes them. When their linear encodings are close, producing interference, the model fails to compose them. Our method reliably anticipates failure modes across different compositional tasks, without evaluating specific inputs. These results lay the groundwork to use representational geometry to identify high-risk examples, construct targeted stress tests, and provide a scalable foundation for active learning in real-world deployment.

Lawyer-client consultation is a critical starting point for legal services. Effective legal assistance hinges on eliciting sufficient and truthful information from clients in order to devise strategies that best protect their interests. This task requires Large Language Models (LLMs) not only to perform robust legal reasoning, but also to strategically elicit material facts through multi-turn interactions and effectively guide clients with diverse personalities. Yet existing legal benchmarks overlook this interactive capability. To fill this gap, we introduce DLawBench, a diagnostic benchmark for real-world legal consultation. Drawing on realistic client behavior, we characterize lawyer-client interactions into four types: Cooperative, Dependent, Withdrawn, and Adversarial. Using dialogues grounded in real cases, DLawBench evaluates whether LLMs can effectively conduct legal consultation under realistic conditions. DLawBench comprises 461 cases from Chinese and U.S. law, 5,532 paired fact entries, 3,411 inquiry rubrics, and 3,348 issue-resolution rubrics, and evaluates 26 representative LLMs. Systematic experiments show substantial headroom: the best-performing model, GPT-5.5, achieves only 0.562 on consultation-grounded legal reasoning. More importantly, DLawBench exposes both sycophancy in legal consultation and a paradox: models perform worse when clients need guidance most.

Vision-language models (VLMs) are typically trained as passive answerers, while their ability to actively ask diverse, non-trivial, visual-centric and grounded questions remains underexplored. Existing visual questioners' performance is bottlenecked by the availability of high-quality training data or the cost of curating them. We show that a VLM can continuously improve itself as a visual questioner without any external supervision. We propose a self-evolving framework that uses a VLM itself as both a proposer and a filter to produce harder, more informative, and visual-centric questions, while maintaining their exploration diversity to avoid training collapse. These questions are then used to train the VLM in both questioner and answerer modes. To evaluate the questioner, we introduce an agentic protocol that assesses questions along perception, reasoning, and diversity dimensions. Experiments across various backbone VLMs show that our method substantially enhances the quality and substantially expands the difficulty boundary of autonomous question generation. Under the same budget, our self-supervision is more effective than training on the static source data. Moreover, the self-evolving questioner remains a competitive or even better answerer.

Each year, college admissions offices face an overwhelming challenge: processing millions of high school transcripts, each with unique formats, grading systems, and layouts. This manual process creates operational bottlenecks that delay admissions decisions and consume valuable resources. We present a transformative solution through a multi-agent AI system where specialized agents collaborate to automatically process diverse transcript formats through intelligent coordination and communication. Our multi-agent architecture consists of three specialized agents-a Pattern Recognition Agent for format-specific parsing, a Semantic Analysis Agent for natural language understanding, and a Vision Intelligence Agent for multimodal document analysis-coordinated by an Orchestration Agent that manages agent communication and result reconciliation. Our key innovation lies in agent-based quality control using GPA extraction as a coordination signal, ensuring reliable agent collaboration and preventing critical information loss. When evaluated on 40 real world transcripts from high schools across 13 U.S. states, our agent system successfully processed every document, achieving 96.7% accuracy compared to expert manual review while maintaining practical processing speeds of 45 seconds per transcript. This work demonstrates how multi-agent coordination can solve complex document processing challenges, offering institutions a scalable, collaborative AI solution that preserves accuracy while dramatically reducing processing time.

Automated aerial wildlife surveys increasingly rely on deep learning, yet standard object detectors require bounding-box annotations, reported to be up to seven times slower and three times more expensive to produce than point-level labels. To address this bottleneck, we introduce the Overhead Wildlife Locator (OWL), a weakly supervised density-estimation framework with three variants: OWL-C, a fully convolutional model for high-throughput screening; OWL-T, a Swin-augmented hybrid for heterogeneous, cluttered scenes; and OWL-D, built on a frozen DINOv3 ViT-H+/16 encoder with a DPT-style fusion decoder. We benchmark all three against POLO, YOLOv11n, and YOLOv11l across five public aerial datasets, from sparse fixed-wing savanna surveys to dense UAV paddock imagery, and against the published HerdNet baseline on its native Delplanque split. OWL-D sets a new state of the art on Delplanque (0.934 AP vs. HerdNet's 0.840) and records the highest AP on four of the five datasets. Performance is regime-dependent: on the extreme-density SheepCounter UAV dataset the hybrid OWL-T leads (0.978 AP) and the convolutional variants attain the lowest counting error, whereas the foundation-based OWL-D degrades, indicating which variant suits which survey type. We further validate operational readiness on the Alaska Department of Fish and Game's 2022 Central Arctic Caribou census: under cross-herd and cross-temporal transfer, OWL-C fine-tuned on the 2017 Porcupine Caribou Herd split attains F1 = 0.965 on a held-out patch test set, with a signed count error of +3.1% aggregated across the released test patches. We release the OWL code, model weights, and the annotated Porcupine Caribou Herd 2017 (PCH) and Central Arctic Herd 2022 (CAH) patches, the first open patch-level datasets for large-scale caribou aerial surveys, at https://github.com/microsoft/MegaDetector-Overhead.

Autonomous staff-free public transport requires reliable in-vehicle passenger monitoring. However, perception inside moving vehicles is challenged by confined spaces, variable illumination, motion-induced background variation, occlusion, and limited viewpoints. To mitigate these spatial constraints, ceiling-mounted fisheye cameras provide full-scene coverage from a single viewpoint. Yet existing public overhead fisheye datasets are recorded in static environments and do not capture the domain shift introduced by vehicle motion. To fill this gap, we introduce PMOF, Passenger Monitoring using Overhead Fisheye cameras, the first public dataset of top-view fisheye imagery captured inside a moving vehicle, comprising over 19k manually annotated frames. PMOF provides rotated bounding boxes, tracking identifiers, and action labels, supporting object detection, tracking, and action recognition. We benchmark PMOF using YOLO26m-obb models fine-tuned under multiple dataset configurations that combine PMOF with existing overhead fisheye datasets. Cross-domain fine-tuning with custom rotation-aware augmentation achieves 94.8% AP50 on PMOF and 96.5% AP50 on an unseen overhead fisheye dataset from a different domain. Our results highlight the domain gap between static and moving environments and show that incorporating PMOF improves detection performance and advances generalization beyond passenger monitoring to broader fisheye-based person detection tasks. The dataset and code are available at https://swermuth.github.io/pmof/.

Exploratory question answering (EQA) over data lakes requires an LLM agent to discover relevant sources, analyze retrieved data, and adapt its actions based on intermediate results. End-to-end accuracy alone cannot distinguish failures in search, planning, data analysis, or the agent's Action Policy: its decisions about what to do next and when to submit an answer. We present SANA (Search Agent Navigation Ablation framework), a diagnostic ablation framework that transforms EQA tasks into runtime profiles containing gold source sequence, sanitized subquestions, and execution records. SANA uses these profiles to construct idealized search, planning, and data-analysis tools, allowing each component to be ablated; the residual gap is diagnostic evidence for policy failures. To illustrate SANA as a reusable evaluation framework, we adapted two recent EQA benchmarks, LakeQA and KramaBench, and evaluated lightweight and mid-sized agents under fixed prompts, budgets, data lakes, and runtimes. Across both benchmarks, data analysis is a consistent bottleneck while planning is less so. Search is a major limitation in LakeQA's large data-lake setting, but less so for the smaller-scale KramaBench. SANA thus deconstructs end-to-end task accuracies into a diagnosis of where data-lake agents fail, and allows for systematic comparisons of progress in search, planning, data analysis, and agent design.

Self-supervised geospatial foundation models (GeoFMs) learn transferable representations from remote sensing data, but their downstream behavior is difficult to characterize. We study six representative GeoFMs spanning joint-embedding, reconstruction, and multimodal pretraining families, and evaluate transfer across classification, regression, and segmentation benchmarks under different label availability and downstream pipelines. We find that model rankings change across tasks and adaptation settings. Layerwise probing shows that, in most cases, task-relevant information is more accessible in intermediate transformer blocks compared to final-layer embeddings, and that GeoFMs exhibit distinct depthwise profiles. In segmentation case studies on PASTIS and Sen1Floods11, downstream adaptation settings such as decoder design and fine-tuning can be as impactful as the choice of GeoFM, and standard dense-prediction heads may be poorly aligned with how GeoFMs organize information over depth. Finally, CKA analysis on case studies shows that fine-tuning does not rewrite GeoFMs uniformly across depth, and the strongest changes are localized to the first linear layer of the MLP in ViT blocks. These results help explain why GeoFM rankings shift across benchmarks and motivate more representation-aware evaluation and adaptation strategies.

AdamW is a default optimizer for modern deep learning, but its first and second moment states add roughly two parameter-sized buffers to training memory. We propose Gefen, a memory-efficient optimizer that automatically shares second-moment estimates across parameter blocks and quantizes the first moment using a learned codebook, thereby reducing AdamW's memory footprint by ~8x while maintaining the same performance, corresponding to a reduction of 6.5 GiB per billion parameters. The method is motivated by a theoretical result showing that large mixed Hessian entries constrain the ratio of squared gradients toward one, suggesting that Hessian-aligned parameters are natural candidates for sharing second-moment statistics. Since computing Hessians is impractical at scale, Gefen infers block structure from the initial squared gradients, requiring no architecture-specific metadata or hyperparameters beyond AdamW defaults. Gefen learns an exact histogram-based dynamic-programming quantization codebook and reuses the same blocks for first-moment scaling. Across diverse experiments, Gefen achieves the lowest peak optimizer memory among the compared AdamW-like methods while maintaining AdamW-level performance. In FSDP and DDP training, the reduced memory footprint enables larger microbatches and improves throughput significantly over AdamW, providing a practical drop-in replacement with lower memory usage that can increase throughput and enable training larger models or using larger batch sizes. We provide the complete Python implementation, including fused CUDA kernels at https://github.com/ndvbd/Gefen

Autonomous robotic systems, including autonomous vehicles, drones, and mobile robots, increasingly rely on on-device Deep Reinforcement Learning (DRL) to adapt to dynamic environments. Unlike cloud-based solutions, embedded DRL must perform training and inference directly on resource-constrained hardware while maintaining timely decision-making. This creates a fundamental challenge: balancing four tightly coupled objectives, real-time performance, task reward, memory utilization, and energy consumption. Optimizing these objectives independently often leads to suboptimal behavior, while conventional multi-objective methods may violate resource constraints and compromise reliability. This paper presents TetraRL, a self-adaptive runtime framework for tetra-objective on-device DRL. TetraRL formulates embedded DRL as a unified optimization problem over real-time, reward, RAM, and reserve (energy) objectives, and employs a preference-conditioned reinforcement learning controller to dynamically navigate the resulting trade-off space. The framework integrates a unified resource-management abstraction, hardware-aware DVFS control, and a runtime Override Layer for robust constraint enforcement. We implement TetraRL on NVIDIA Jetson AGX Orin and Orin Nano platforms and evaluate it across diverse DRL environments. Results show that TetraRL effectively balances all four objectives, achieves competitive trade-offs under varying runtime preferences, and incurs negligible overhead. Moreover, a single trained policy can support runtime-switchable optimization goals, providing a practical foundation for resource-aware and self-adaptive on-device DRL.

Vision-Language-Action (VLA) models excel at mapping visual inputs and natural language instructions directly to robotic control policies. However, because they are trained primarily to fit behavioural demonstration data, they do not explicitly enforce fundamental physical principles such as rigid-body dynamics or contact constraints. This exposes a critical physics gap: standard temporal smoothing applied on top of single-step or chunked VLAs trades trajectory quality for added failures that short-term memory cannot resolve. To bridge this gap, we introduce PhysVLA (Physics-VLA), a plug-and-play, inference-time framework designed to wrap any frozen VLA backbone without retraining, fine-tuning, or weight access, with less than 1 ms of overhead per control step. PhysVLA intercepts the predicted control action, captures only the simulator or system state, and applies a dual-layered correction: (i) a phase-aware finite-state machine that structures discrete task segments (approach, grasp, transport, and place), and (ii) a selective Euler-Lagrange gate that activates only when a dynamics oracle detects kinodynamic inconsistency. Evaluated across OpenVLA, OpenVLA-OFT, Force-VLA, and Generalist-VLA on LIBERO-Spatial with a 7-DoF Franka Panda, the framework delivers absolute success rate increases of up to 17% and stability increases of up to 19% with no per-task regressions, improves trajectory efficiency by up to 15% across all four backbones, and shows up to a 10x improvement in trajectory jerk robustness on a Robosuite Lift cross-simulator sweep. We further validate the framework on a real Agilex Piper arm with a pick-and-place task, confirming that PhysVLA transfers to physical hardware without retraining, with success-rate improvements of up to 50%, establishing physical awareness as a composable, backbone-agnostic runtime module.

End-to-end navigation policies trained on large simulation corpora degrade sharply when transferred to out-of-distribution scenes, categories, or goal modalities. Modular pipelines such as Modular GOAT are bottlenecked by closed-set object detection recall, while 3D snapshot-memory systems (e.g. 3D-Mem) accumulate dense, view-dependent representations that are heavy to maintain. We present AnyGoal, a training-free multi-robot architecture that places a Vision-Language Model (VLM) at the core of frontier-based exploration and coordinates agents through a shared 2D Gaussian Bayesian Value Map (BVM). The BVM maintains a per-pixel (mu, sigma^2) posterior over goal relevance, updated via precision-weighted fusion of VLM scores through a depth-cone mask, and is never reset between subtasks, yielding lifelong evidence accumulation. Frontiers are ranked by a convex blend of a VLM-as-judge softmax and a Bayesian UCB term on the BVM. A greedy allocator with spatial-separation penalty and commitment hysteresis distributes frontiers across agents without a centralized controller. On the full GOAT-Bench val unseen split (360 episodes, 2,669 subtasks), our dual-agent system achieves 52.4% Subtask SR at 12.7% SPL--state of the art under the strict physical regime (discrete 0.25 m steps, no teleportation, 42 deg HFOV) and a +27.5 pp improvement over Modular GOAT (24.9%). Single-agent AnyGoal achieves 41.9% Subtask SR, showing gains arise from the decision architecture. A four-way perception ablation shows that open-vocabulary detectors shift the dominant failure mode from exploration to goal verification.

Contact-rich manipulation requires world models to reason over complex contact dynamics from multimodal sensory observations. However, it remains unclear which representation properties fundamentally support stable long-horizon planning in contact-rich settings. In this paper, we present ContactWorld, a benchmark and systematic empirical study of vision-tactile world models spanning 12 contact-rich manipulation tasks, including insertion, disassembly, screwing, and exploratory interaction. Across extensive experiments, we find that representations that are both spatially structured and temporally continuous consistently achieve the strongest planning performance. In particular, point-cloud observations improve average planning success rates from 20.7% with wrist-view observations and 22.0% with front-view observations to 32.1%. We further find that the effectiveness of tactile sensing depends critically on cross-modal representation compatibility rather than modality scaling alone. Combining point-cloud observations with tactile force-field representations, which preserve richer spatial structure and interaction dynamics, further improves performance to 36.1%, yielding the strongest overall planning performance across all evaluated tasks. Moreover, tactile sensing becomes increasingly important under long-horizon planning objectives, where compounding prediction errors and contact uncertainty accumulate over time. Together, these findings highlight the importance of representation structure, multimodal compatibility, and long-horizon robustness in vision-tactile world models for contact-rich robotic manipulation.

Unlearning aims to remove the influence of specific training data sources, but this has proved challenging because the contributions of different sources are entangled within the model. Isolating source contributions to disjoint parameters makes removal easier, though it obstructs joint learning across sources. We propose NULLs (Natively Unlearnable LLMs), a model class that satisfies the two opposing goals of isolating source-specific contributions and learning jointly across sources, by training a set of shared backbone neurons alongside a pool of sparsely activated sinks. During training, information specific to a source naturally concentrates in its sinks while information shared across sources accumulates in the backbone. A source is then unlearned at deployment by disabling its corresponding sinks, with no gradient updates and no access to the retained data. We show that NULLs scales to Wikipedia's ~6M articles, isolating each as an independent source. Unlearning a single article removes knowledge specific to it while preserving facts shared with semantically related articles, closely matching retraining from scratch. We note that unlearning with NULLs is also robust: in a case study of unlearning the Harry Potter books, NULLs resists both adversarial extraction and relearning that reverses post-hoc unlearning. Finally, NULLs preserves general language capabilities, matching a standard transformer on downstream benchmarks. Together, these results suggest that source-level unlearning need not be an afterthought. It can be built natively into LLM training while retaining the benefits of shared representation learning.

Generating avatar videos that are not merely visually similar to a target individual but behaviorally recognizable, faithfully reproducing their talking rhythm, gestural tendencies, and expression dynamics, remains an open challenge. Existing methods predominantly condition on single static images, which provide insufficient identity information and cannot capture dynamic motion traits, while standard pixel-level objectives underserve the perceptually critical facial regions that determine avatar fidelity. We present Avatar V, a production-scale framework that addresses these limitations through video-reference-conditioned identity modeling. Rather than compressing identity into fixed-size embeddings, the model conditions directly on the full token sequence of a reference video, learning to reproduce both static identity attributes (facial geometry, skin texture) and dynamic behavioral patterns (talking rhythm, micro-expressions) through attention over the reference context. We introduce Sparse Reference Attention, an asymmetric mechanism achieving linear-complexity conditioning on arbitrarily long references; a motion representation stream enabling closed-loop talking style transfer; and an identity-aware super-resolution refiner inheriting the full reference conditioning. These are supported by a data engine curating 100M+ training clips from 50M raw videos, and a five-stage training pipeline with flow matching pre-training, personality fine-tuning, two-phase distillation (>10x acceleration), and RLHF alignment, deployed across thousands of GPUs. Avatar V generates 1080p videos of unlimited duration, achieving state-of-the-art identity preservation, lip synchronization, and generation quality on our cross-scene benchmark, consistently outperforming leading systems including Seedance 2.0, Kling O3 Pro, Veo 3.1, and OmniHuman 1.5 in both automated metrics and human evaluation.

Vision-language models (VLMs) can answer image-based questions confidently, and often correctly, even when no image is provided. This mirage behavior inflates benchmark scores without reflecting visual grounding. Prior work treats this as a single failure mode. We argue it is two. Using Mirage Probes, a contrastive probing framework that pairs paraphrased question variants with matched mirage and non-mirage labels on the same image, we show that mirage behavior is linearly decodable from internal activations across residual stream, MLP, post-attention, and attention-head sites in two open-source VLMs. We demonstrate that a Naive Bayes text baseline cannot recover this signal, ruling out surface lexical confounds. Cross-benchmark separability patterns, together with a novel Prior Harnessing Index (PHI) measuring how much a model can answer from text alone, expose two distinct regimes: textual biases, where the model answers from language priors without engaging visual representations, and spurious images, where it constructs false visual content in latent space and answers as if grounded. The distinction has direct mitigation consequences: text-distribution cleaning can address the first regime but cannot reach the second, since spurious-image mirages live in the model's visual representations rather than its text. Faithful visual grounding will require interventions at the representational level.

Fine-tuning a vision-language-action model (VLA-JEPA) on a single GPU should be simple: load a pretrained checkpoint, run training, deploy. There is a hidden danger. Run the same fine-tuning code thirteen times -- same data, same architecture, different random seed -- and twelve runs produce a robot succeeding 91--94% of the time, while one run silently degrades to 65.2%: a 29 pp gap with no error message, no warning, and no way to predict which seed will fail. We call this the seed lottery. We trace the cause to output collapse: the action predictor quietly learns to produce nearly identical outputs regardless of what the robot sees. Existing weight-level methods (L2, EWC) are structurally blind to this collapse -- they penalize weight changes, but collapse occurs in directions weights can move freely without affecting outputs, a gap we formalize via the Jacobian null-space. Across 7 methods x up to 13 seeds x 3 LIBERO benchmarks, three output-level regularizers -- VICReg (n=12 seeds), Dropout (n=4), and a halved learning rate (n=5) -- each eliminate every catastrophic seed (0/21 combined collapses vs. 1/13 Baseline; F(12,11)=28.7, p<0.001), while weight-level methods (L2, EWC) preserve the lottery. The simplest fix is changing one number in your optimizer config.

We present an algorithm for efficient domain-adaptive policy learning via kernel representations. Learning domain-adaptive policies is challenging since it requires an environment representation that is both sufficiently expressive to model complex sim-to-real gaps during offline training, and computationally efficient enough to support rapid online adaptation during deployment. For instance, a quadrotor may encounter time-varying, non-stationary disturbances, such as sudden gusts of wind, payload shifts, or transitions between distinct flight regimes with and without ground effects. To address these challenges, we model unknown disturbances using a differentiable kernel approximation based on random Fourier features. During the offline training phase, we randomly sample kernel coefficients and bandwidth parameters to generate a rich diversity of disturbance profiles. We then optimize the control policy via differentiable simulation with analytical gradients, a process that takes only 50 seconds of training time on an RTX 4090 GPU. During hardware deployment, the policy adapts to non-stationary environments in real time by updating both the kernel coefficients and bandwidth through online least-squares estimation. We evaluate our method on quadrotor trajectory tracking tasks across high-fidelity numerical simulations and hardware experiments using Crazyflie, subjected to various disturbances, including complex aerodynamic effects, wind, ground effects, and payload fluctuations.

Autonomous driving is shifting from isolated vehicle intelligence toward multi-agent embodied systems that share perception, infer intent, and coordinate action under uncertainty. This survey examines this transition through the lens of Shared World Models (SWMs): predictive cross-agent representations maintained across vehicles, infrastructure, and other traffic participants. We review more than 380 publications spanning vehicle-to-everything (V2X) communication, collaborative perception, inter-agent cognition, cooperative planning, end-to-end cooperative driving, and simulation and data engines for closed-loop validation. The organizing question is how exchanged observations become aligned state, intent-aware interaction, and coordinated downstream action. Across the surveyed literature, evaluation remains concentrated in simulation, curated benchmarks, and offline protocols. Foundation-model-based coordination also lacks verified real-time safety guarantees in open traffic. These gaps motivate key research priorities for multi-agent embodied autonomous driving (MAEAD): verifiable shared-state maintenance, robust intent and plan alignment, and safe coordinated action under communication, latency, and deployment constraints.

Remote photoplethysmography (rPPG) transformers achieve low heart-rate error on benchmarks, yet their decisions remain opaque--a growing concern as rPPG moves toward clinical heart rate estimation. Existing rPPG XAI is dominated by qualitative heatmap inspection without quantitative faithfulness metrics or physiology-grounded validation, leaving a gap between visual plausibility and auditable evidence. We address this gap. First, we adapt four attribution methods (raw attention, rollout, flow, Beyond Intuition) to RhythmFormer's bi-level routing attention with top-$k$ selection. Second, we introduce a skin coverage metric quantifying how much attribution mass falls on skin regions. Third, we adapt the SaCo faithfulness coefficient from its original classification setting to rPPG regression by using the MAE between original and perturbed predicted rPPG waveforms as the perturbation impact. Applying these tools, we quantify a multi-hop leakage effect under sparse top-$k$ routing: attention rollout and flow almost completely restores the connections that individual refined-attention layers explicitly set to zero. Beyond Intuition mitigates this via its value-projection-weighted rollout and gradient-supported mask, attaining the highest median refined skin coverage ($0.83$ vs. $0.57$ for vanilla rollout) and faithfulness ($F=0.92$) among the evaluated methods on UBFC-rPPG. Validation across diverse datasets and model variants is needed. A case study on a low-SaCo outlier further shows all four methods recovering consistently once an artefactual region is replaced, suggesting consistent SaCo behavior across attribution families in this illustrative case. Together, these metrics move XAI for rPPG toward auditable numerical evidence about spatial alignment and perturbation faithfulness, i.e. trustworthy rPPG XAI.

Autonomous network-security response systems promise to reduce Security Operations Centre (SOC) reaction latency, but reward-only multi-agent reinforcement learning (MARL) can improve security reward while remaining non-deployable. We present a safety-contract graph MARL framework and instantiate it as ACD$^3$-GAT (Adaptive Constrained Counterfactual Decisioning with a Graph Attention Network encoder), an architecture that separates simulator observations from reusable operational budgets, constrained optimization, graph state encoding, and counterfactual action screening. We evaluate the method in CAGE Challenge 4, where agents operate under budgets for Mean Time to Recover (MTTR), false-positive response, and firewall change-management disruption. Across the benchmark, every unconstrained method violates the SOC downtime budget in 100% of evaluated episodes, with mean downtime proxy costs of 311-430 against a budget of 50. This complements prior CAGE Challenge 4 findings by showing that reward-only learning lacks operational discipline. Constrained MAPPO-GAT (C-MAPPO-GAT) isolates Lagrangian operational-cost control and budget-aware screening, while ACD$^3$-GAT adds budget context, CVaR tail-risk estimation, opponent-belief state, and Graph Counterfactual Risk Propagation (G-CRP). The replicated comparison includes three 200-episode seeds for IPPO, MAPPO-GAT, C-MAPPO-GAT, and ACD$^3$-GAT. C-MAPPO-GAT reduces downtime violation from 100% to 0.3% and mean downtime cost from 355.4 to 15.5 relative to MAPPO-GAT. ACD$^3$-GAT reduces mean downtime cost to 48.2 with a 13.8% violation rate, placing it on the safety-contract frontier rather than at the most conservative compliance point. Topology-seed and coupled adaptive Red-process stress tests preserve this contrast and show lower worst adaptive degradation for safety-constrained policies than reward-only MAPPO-GAT.

World models in robot learning predict future states from visual observations and actions, enabling agents to reason about the consequences of their controls. However, many action-conditioned models are evaluated in settings where motion is dominated by immediate control, whereas aquatic surface vehicles and other real-world objects continue moving under inertia and are displaced by hidden ambient drift, such as water currents or wind. We propose FlowMo-WM, an end-to-end trainable visual world model that infers object-centric motion state and a predictive long-history context associated with hidden drift from image-action histories without direct supervision of flow fields. FlowMo-WM factorizes image-action history into a short-history latent state, trained to summarize object-centric motion, and a longer-history context, trained to summarize slowly varying exogenous influences. A zero-context residual transition separates action-conditioned base dynamics from context-dependent drift effects during latent rollout. In simulated aquatic surface-vehicle environments with diverse hidden flows, disturbances, and randomized vehicle dynamics, FlowMo-WM improves long-horizon rollout accuracy over representative action-conditioned latent world models. Prediction-time context ablations, in which the inferred context is zeroed or shuffled during rollout, show that the ambient context is important for stable prediction under hidden drift, while frozen linear probes characterize information encoded in the learned factors.

Strategic reasoning under uncertainty underpins consequential decisions in negotiation, finance, and policy, but prevailing game-play benchmarks collapse heterogeneous reasoning dimensions into a single scalar, leaving the capability structure of frontier LLMs unexamined. We introduce Poker Arena, a no-limit Texas Hold'em tournament platform that couples a three-layer memory architecture (within-hand, session, and cross-session) with a nine-axis cognitive profile decomposing strategic reasoning into interpretable dimensions such as bet-sizing calibration and positional awareness. We evaluate seven frontier models across 50 sessions of 1,000 hands and a controlled memory ablation; tournament chips and aggregate axis score order the field differently: Claude Opus 4.6 wins +$15,730 chips with 14 first-place finishes, yet ranks only fifth of seven on mean axis score, while persistent memory helps some models and hurts others. These findings show that multi-axis evaluation surfaces capability structure that scalar leaderboards systematically misrank, with cross-dimensional consistency outweighing peak performance on any single axis.

Current cultural alignment approaches focus on inference-time interventions, assuming models already contain sufficient cultural knowledge. We argue modern LLM pipelines suffer from a cultural data funnel. Using a multidimensional tagging framework across pretraining, fine-tuning, alignment, and reasoning datasets, we show explicit cultural signals decline sharply during post-training, while geographically concentrated, task-specialized data dominates. Multilinguality enhances geographic diversity of cultural knowledge but does not ensure balanced representation. Our tags improve downstream cultural benchmark performance, demonstrating that advances require shifting focus in training data pipelines. To facilitate future research, we release our culturally tagged dataset with 5.6M samples at https://huggingface.co/datasets/CohereLabs/CultureMarkers.

Nonlinear dynamics and the strong couplings that arise between multiple effectors undermine the assumptions behind conventional, linear control allocation techniques. When flight enters regimes where nonlinear effects dominate, linear allocators exhibit reduced accuracy due to increased model mismatch, which subsequently degrades performance and robustness of the flight control system. High fidelity onboard models and black box data driven approaches can recover accuracy across the flight envelope, but respectively impose computational burdens prohibitive for real time allocation and sacrifice the interpretability required for verification and fault diagnosis. This paper addresses these limitations by learning an explicit, physics constrained analytical model of the control effectiveness mapping from representative flight data using Sparse Identification of Nonlinear Dynamics. The resulting mapping is compact, interpretable, and admits analytical derivatives, enabling efficient computation within nonlinear solvers that additionally incorporate actuator dynamics, without requiring an onboard model. An online adaptation mechanism monitors prediction residuals and refreshes the model when significant plant changes are detected, providing graceful reconfiguration under actuator failures and varying operating conditions. The methodology is evaluated on a high fidelity nonlinear benchmark aircraft across a range of aggressive maneuvers, achieving accuracy comparable to a full nonlinear onboard model while substantially reducing computational cost relative to established baselines.

Large language model (LLM) agents have achieved strong performance on a wide range of benchmarks, yet most evaluations assume static environments. In contrast, real-world deployment is inherently dynamic, requiring agents to continually align their knowledge, skills, and behavior with changing environments and updated task conditions. To address this gap, we introduce EvoArena, a benchmark suite that models environment changes as sequences of progressive updates across terminal, software, and social domains. We further propose EvoMem, a patch-based memory paradigm that records memory evolution as structured update histories, enabling agents to reason about environmental evolution through changes in their memory. Experiments show that current agents struggle on EvoArena, achieving an average accuracy of 39.6% across evolving terminal, software, and social-preference domains. EvoMem consistently improves performance, yielding an average gain of 1.5% on EvoArena and also improving standard benchmarks such as GAIA and LoCoMo by 6.1% and 4.8%. Beyond individual tasks, EvoMem further improves chain-level accuracy by 3.7% on EvoArena, where success requires completing a consecutive sequence of related evolutionary subtasks. Mechanistic analysis shows that EvoMem improves evidence capture in the memory, indicating better preservation of complete evolving environment states. Our results highlight the importance of modeling evolution in both evaluation and memory for reliable agent deployment.

World models that capture how actions induce physical change enable scalable robot learning without reliance on embodiment-specific action labels. Pixel-space video models provide broad visual priors but expend model capacity on dense appearance reconstruction, while direct action models require embodiment-specific labels that hinder scalability. We present $μ_0$, a scalable world model based on 3D traces. Rather than predicting dense pixels or directly modeling actions, $μ_0$ forecasts smooth 3D trajectories for salient interaction points such as objects, tools, hands, and contact regions, yielding a compact, embodiment-agnostic motion interface. To enable training from diverse video sources, our TraceExtract system automatically extracts 3D supervision by selecting keypoints, constructing globally aligned traces, and associating motion segments with hierarchical language captions. This TraceExtract supervision pretrains $μ_0$ by combining a pretrained vision-language backbone with a modular trace expert, which represents each query via B-spline control points and predicts future traces. Experiments show that $μ_0$ outperforms baselines in both 2D and 3D trace prediction, including trace prediction models and tokenized VLM methods. Because $μ_0$ is frozen and reusable, it can be paired with action experts for downstream robot embodiments. Despite action-free pretraining, the resulting trace-conditioned policies achieve performance competitive with VLA models pretrained with action supervision, such as $π_0$. These results establish 3D traces as a scalable and transferable representation for cross-embodiment manipulation.

Retrieval-augmented generation (RAG) has become a standard mechanism for grounding language models in external knowledge, yet conventional retrieval based on lexical or semantic similarity is poorly suited for complex reasoning tasks: a semantically similar problem may demand an entirely different solution strategy, while a superficially different problem may share the same underlying reasoning pattern. We propose Retrieval-Augmented Reinforcement Fine-Tuning (RA-RFT), a post-training framework that teaches language models to reason by analogy. RA-RFT uses gold-relevance distillation to train a retriever that ranks contexts by expected reasoning benefit rather than semantic overlap, and then fine-tunes the policy model via reinforcement fine-tuning methods with retrieved analogous demonstrations, so the model learns to leverage reasoning traces under verifiable outcome rewards. We further analyze the diversity of retrieved contexts and find that reasoning-aware retrieval surfaces complementary solution strategies that provide distinct reasoning scaffolds for individual problems. Across challenging mathematical reasoning benchmarks, RA-RFT consistently outperforms standard reinforcement fine-tuning methods. For example, it improves AIME 2025 average@32 accuracy by 7.1 and 2.8 points over GRPO for Qwen3-1.7B and Qwen3-4B respectively -- suggesting that reasoning-aware retrieval is a complementary axis of improvement and orthogonal to advances in reward design or training curricula.

Recent image generators have demonstrated impressive photorealism and instruction-following capabilities in single-image generation and editing. However, constrained by their architectures, they cannot achieve interleaved generation (text-image sequence), which has crucial applications in visual narratives, guidance, and embodied manipulation. Even the latest open-source Unified Multimodal Models (UMMs) exhibit limited performance in this regard. In this paper, we introduce InterleaveThinker, the first multi-agent pipeline designed to endow any existing image generator with interleaved generation capabilities. Specifically, we employ a planner agent to organize the image-text input sequence, instructing the image generator on the required execution at each step. Subsequently, we introduce a critic agent to evaluate the generator's outputs, identify samples that deviate from the planned instructions, and refine the instructions for regeneration. To implement this pipeline, we construct the Interleave-Planner-SFT-80k and Interleave-Critic-SFT-112k to perform a format cold-start. Then we develop Interleave-Critic-RL-13k to reinforce the step-wise instruction correction capability within a generation trajectory using GRPO. Since a single interleaved generation trajectory may involve over 25 generator calls, optimizing the entire trajectory is computationally impractical. Therefore, we propose accuracy reward and step-wise reward, allowing single-step RL to effectively guide the entire generation trajectory. The results show that InterleaveThinker improves performance across various image generators. On interleaved generation benchmarks, it achieves performance comparable to Nano Banana and GPT-5. Surprisingly, it also significantly enhances the base model on reasoning-based benchmarks; for example, on 4-step FLUX.2-klein, we observe substantial gains on WISE and RISE.

Articulated tool manipulation remains a major challenge in dexterous robotics due to the need to coordinate internal degrees of freedom and contact-rich interactions. While prior work has largely focused on rigid objects, articulated tool use remains underexplored because of its physical complexity and the difficulty of learning functional grasping and manipulation policies. We present Mana (Manipulation Animator), a general sim-to-real framework that reinterprets dexterous manipulation as an animation problem. Inspired by computer animation, Mana employs a coarse-to-fine pipeline that transforms procedurally-generated grasp keyframes into manipulation trajectories through motion planning and reinforcement learning. The data generation process is largely automatic, requiring only a few mouse clicks to specify functional affordances (<1 minute per tool). Across four articulated tools spanning different scales and joint types, Mana achieves zero-shot sim-to-real transfer for both grasping and in-hand manipulation, demonstrating a scalable approach to dexterous articulated tool use.

Generalist policies can learn a wide range of skills from diverse robot datasets. In order to solve or improve on challenging new tasks, we need a way to infer and invoke the appropriate actions from the policy's rich behavioral prior, especially when directly commanding the policy fails. We focus on flow matching generalists and propose Flow Reversal Steering (FRS): a method that takes suboptimal but ``reasonable'' actions, finds their latent noises by passing them through the flow policy in reverse, and maps them to nearby generalist action modes. We evaluate FRS across many simulated and real-world manipulation settings. First, FRS can turn coarse semantic guidance from humans or vision-language models (VLMs) into corresponding good robot actions, improving zero-shot control. These gains can be distilled with behavioral cloning by training an auxiliary policy to output noises that the generalist maps to good actions -- showing up to 95% absolute task success rate boosts in under a minute of training. Finally, FRS enables policy improvement by bootstrapping reinforcement learning with semantic knowledge, improving on several tasks that standard RL fails to improve on.

Text-to-image (T2I) models contain rich spatial priors. Synthesizing photorealistic, cluttered scenes requires an understanding of geometry, including perspective and relative scale. Prior works adapt T2I models to leverage this prior for depth prediction, but they require dense depth data and involve complex recipes. We propose Modality Forcing, a simple, scalable post-training recipe for joint image-depth generation using a single DiT trained on sparse depth data. Modality Forcing enables conditional and joint generation of image and depth in any permutation by assigning separate noise levels per modality. Per-modality decoders let us train on sparse, real-world depth and achieve strong, generalizable depth prediction. We further show that Modality Forcing inherits the scalability of T2I pre-training: by training a set of T2I models from scratch (370M to 3.3B parameters), we find that larger models trained on more image data produce more accurate depth. Our strongest model is competitive with state-of-the-art monocular depth estimators and reduces AbsRel by 57% relative to existing joint image-depth generative models. These results provide strong evidence that image generation is a scalable pre-training objective for spatial perception. https://modality-forcing.github.io/

This work presents RepWAM, a representation-centric world action model (WAM) built on representation visual-action tokenizers. Existing WAMs typically inherit reconstruction-oriented video tokenizers from pretrained video generation models. Although these tokenizers preserve visual fidelity, pixel reconstruction alone provides limited guidance for learning instruction-following dynamics that connect future prediction with robot control. To address this, we explore a semantic visual-action latent space for representation-centric world action modeling. Specifically, we train a representation visual-action tokenizer that maps visual inputs into aligned visual and latent action tokens. We then pretrain our WAM to jointly model future visual states and the latent actions that connect them under language instructions, followed by adaptation to real robot trajectories for closed-loop manipulation. Experiments on real-world manipulation tasks and simulation benchmarks show that RepWAM delivers strong performance across diverse manipulation settings, while ablations highlight the value of semantic visual-action tokenization over reconstruction-oriented alternatives. These results establish representation visual-action tokenization as a promising foundation for world action models and a step toward generalist robot policies. Code and weights will be available at https://github.com/wdrink/RepWAM.

Spatial reasoning, the ability to determine where objects are, how they relate, and how they move in 3D, remains a fundamental challenge for vision-language models (VLMs). Tool-augmented agents attempt to address this by augmenting VLMs with specialist perception modules, yet their effectiveness is bounded by the action interface through which those tools are invoked. In this work, we study how the design of this interface shapes the agent's capacity for open-ended spatial reasoning. Existing spatial agents either employ single-pass code execution, which commits to a full analysis strategy before any intermediate result is observed, or rely on a structured tool-call interface that often offers less flexibility for freely composing operations or tailoring the analysis to each task. Both designs offer limited flexibility for open-ended, complex 3D/4D spatial reasoning. We therefore propose SpatialClaw, a training-free framework for spatial reasoning that adopts code as the action interface. SpatialClaw maintains a stateful Python kernel pre-loaded with input frames and a suite of perception and geometry primitives, letting a VLM-backed agent write one executable cell per step conditioned on all prior outputs, enabling the agent to flexibly compose and manipulate perception results and adapt its analysis to both intermediate text and visual observations and the demands of each problem. Evaluated across 20 spatial reasoning benchmarks spanning a broad range of static and dynamic 3D/4D spatial reasoning tasks, SpatialClaw achieves 59.9% average accuracy, outperforming the recent spatial agent by +11.2 points, with consistent gains across six VLM backbones from two model families without any benchmark- or model-specific adaptation.

The potential impacts of world models (WMs, i.e., learned simulators) on robotics are far-reaching -- policy evaluation, policy improvement, and test-time planning -- all with limited real-world interaction. To unlock these downstream capabilities, a WM needs to jointly satisfy three desiderata: $\textit{(i)}$ fidelity (i.e., producing simulated trajectories that correlate with reality), $\textit{(ii)}$ consistency (i.e., producing simulated trajectories that are coherent over long horizons), and $\textit{(iii)}$ efficiency (i.e., producing simulated trajectories quickly). We propose $\texttt{WEAVER}$ (World Estimation Across Views for Embodied Reasoning): a WM architecture that simultaneously achieves all three desiderata, providing state-of-the-art results on robotic manipulation tasks. $\texttt{WEAVER}$ is a multi-view WM trained to predict future latents and reward values via a flow-matching loss. We distill the key design decisions across model architecture, memory, and prediction objectives required to unlock the kinds of long-horizon dynamic manipulation tasks that have confounded prior world modeling approaches. We apply $\texttt{WEAVER}$ in robotic hardware, demonstrating its effectiveness at policy evaluation ($ρ$=0.870 correlation with real-world success rate), policy improvement (real-world success rate improvement of $38\%$ on top of the $π_{0.5}$ robot foundation model), and test-time planning (real-world success rate improvement of $14\%$ with a $5-10\times$ speedup over prior WMs). $\texttt{WEAVER}$ also demonstrates better performance than prior WMs when evaluated on out-of-distribution scenarios. Code, models, and videos at: https://arnavkj1995.github.io/WEAVER/ .

Cinematic video depicts multiple subjects acting or interacting at specific moments, captured with deliberate camera movement, and stitched together by shot transitions. Together, these elements demand a level of fine-grained control beyond current text-to-video models. Existing work addresses each axis in isolation: multi-subject personalization, temporal control, multi-shot synthesis, or camera control; no prior framework jointly integrates all four. We present CineOrchestra, a unified video diffusion model that controls subjects, events, cameras, and shot transitions simultaneously. Our key insight is that these heterogeneous cinematic elements share a fundamental structure: each is an entity acting over a specific temporal interval, which can therefore all be expressed through one shared structure of entity-centric conditioning primitives, augmented with reference images for visual entities. This formulation reduces the architectural challenge to a single positional encoding problem, which we solve with two parameter-free coordinated rotary embeddings: (a) an interval-sampled temporal RoPE that yields consistent attention behavior across events of dramatically varying duration, and (b) a 2D entity-temporal cross-attention RoPE that disambiguates per-entity conditions and routes each to its corresponding spatiotemporal region. On two new benchmarks, CineOrchestra outperforms six per-axis specialists on dense caption following and shot-transition timing, with consistent gains in a pairwise user study and component ablations.

Tool-augmented LLM agents commonly rely on step-wise atomic tool calls, where each invocation, observation, and value transfer is exposed in the main reasoning trace. This creates an \emph{execution-granularity mismatch}: locally deterministic tool workflows are unfolded into repeated model-visible decisions, consuming context and forcing the model to manage low-level dataflow in the trace. We introduce \textbf{HyperTool}, a unified executable MCP-style tool interface that changes the model-visible unit of tool execution. A model invokes HyperTool with a code block that can call existing tools through their original schemas, manipulate returned values, and pass intermediate results locally, folding deterministic tool subroutines into a single outer call. To train models to use this interface, we synthesize HyperTool-format trajectories from cross-tool compositional tasks and verify them in real MCP environments. On MCP-Universe, HyperTool improves average accuracy from 15.69\% to 35.29\% on Qwen3-32B and from 9.93\% to 33.33\% on Qwen3-8B, and surpass GPT-OSS and Kimi-k2.5 on average accuracy, showing that our HyperTool can substantially improve multi-step tool use.

LLM-based agents have shown increasing potential in automating scientific discovery. Given an optimizable metric and an execution environment, they can propose, validate, and iterate scientific solutions, and have produced results that outperform human-designed approaches. As model capabilities continue to improve, we argue that the bottleneck for autonomous scientific discovery is shifting from prescribing agent workflows to designing agent environments: the resources, constraints, and interfaces that shape agent behavior. We frame this as environment engineering: building environments that amplify productive behaviors, such as open-ended exploration, systematic artifact management, and inter-agent collaboration, while suppressing harmful behaviors, such as reward hacking and high-friction human oversight. We present EurekAgent, an environment-engineered agent system for metric-driven autonomous scientific discovery. EurekAgent engineers the environment along four dimensions: permissions engineering for bounded agent execution and isolated evaluation; artifact engineering for filesystem and Git-based collaboration; budget engineering for budget-aware exploration; and human-in-the-loop engineering for easy human supervision and intervention. EurekAgent sets new state-of-the-art results on multiple mathematics, kernel engineering, and machine learning tasks, including new state-of-the-art 26-circle packing results discovered with less than $11 in total API cost. We open-source our code and results, and call for environment engineering as a core research direction for developing reliable autonomous research agents.

Image-to-3D methods often trade off faithfulness and completeness: depth estimators are anchored to input pixels but stop at the visible surface, while image-to-3D models generate complete shapes that are often misaligned with the input. We introduce World Tracing, a generative pixel-aligned geometry representation that predicts 3D points aligned with observed pixels while completing geometry beyond the visible surface. For each input pixel, World Tracing predicts an ordered stack of camera-space 3D points, where the first layer represents the visible surface and subsequent layers represent front-to-back intersections with occluded surfaces. We instantiate this representation with a world-tracing diffusion transformer, WT-DiT, which treats multiple geometry layers as separate denoising tokens coupled through factorized and global attention. WT-DiT is trained with pixel-space flow matching and a mixed noise schedule that balances visible-surface reconstruction with occluded-geometry generation. World Tracing achieves strong performance on visible-surface reconstruction and complete geometry generation across object, scene, and dynamic benchmarks, outperforming both depth predictors and image-to-3D generators. It also preserves 2D-to-3D correspondence, enabling text-driven 3D scene editing, geometry-conditioned novel-view video synthesis, and training-free integration with textured-mesh generators.

We introduce SkMTEB, the first comprehensive MTEB-style text embedding benchmark for Slovak, a low-resource West Slavic language, comprising 31 datasets across 7 task types -- nearly 4$\times$ the depth of existing multilingual benchmark coverage for Slovak. Our evaluation of 31 embedding models reveals that large instruction-tuned multilingual models achieve the strongest performance, while existing Slovak-specific models trained for NLU tasks transfer poorly to embedding tasks. To address the need for efficient, locally-deployable Slovak embeddings, we develop \texttt{e5-sk-small} (45M parameters) and \texttt{e5-sk-large} (365M) by applying vocabulary trimming and fine-tuning to Multilingual E5 models. Despite size reductions of up to 62\%, our open-source models achieve competitive performance with proprietary APIs while remaining locally deployable for semantic search and retrieval-augmented generation (RAG). We release the benchmark, models, datasets, and code openly, hoping our approach offers a replicable path for other under-resourced languages.

Recursive language models (RLMs) showed that recursion over model calls is an effective strategy for long-context reasoning, and production coding agents have begun to write code that spawns subagents at scale, most recently in Anthropic's dynamic workflows. We name and study the pattern between these two lines of work, where the recursive unit is a full agent harness with filesystem tools, code execution, and planning rather than a model call with no tools. We call this the Recursive Agent Harness (RAH) and frame it as harness recursion, the code-first extension to the model recursion of RLMs. A parent agent generates and runs an executable script that spawns subagent harnesses in parallel for fine-grained workloads and uses structured function calls for small subtasks. We provide a controlled evaluation on long-context reasoning. With the backbone held fixed at GPT-5 to match the published Codex and RLM baselines, RAH improves the Codex coding-agent baseline from 71.75% to 81.36% on Oolong-Synthetic (199 samples, 13 context-length buckets up to 4M tokens), a gain attributable to the harness rather than the model. With a stronger backbone, Claude Sonnet 4.5, the same design reaches 89.77%.

Shielded reinforcement learning is typically presented as a runtime safety mechanism that compiles temporal-logic specifications into automata restricting an agent's actions. We argue this is the wrong product. The same automata-theoretic machinery -- specification compilation, product game construction, attractor computation, and winning-region extraction -- is better read as a design-time analytical instrument whose outputs are structural insights about a system rather than runtime constraints on a deployed agent. We instantiate this through a constrained two-player safety game for network defense. The two specifications are enforced asymmetrically: the defender specification defines the unsafe region of the game, whereas the attacker specification restricts the adversary's legal actions during attractor computation. Solving the game yields a defensibility verdict -- a formal certificate that a topology-specification pair is or is not defensible -- with the associated winning region and shield. Beyond the binary verdict, we derive topology-level metrics from the attractor structure and combine them with post-convergence behavior from shield-constrained adversarial multi-agent reinforcement learning. Together these form a defensibility fingerprint capturing both a network's formal safety properties and its operational behavior under adaptive play. A what-if analysis shows that formal defensibility and operational effectiveness capture distinct aspects of security: small architectural changes can produce large shifts in operational outcomes while leaving formal safety margins nearly unchanged. Shield synthesis is thus most valuable not as a deployment mechanism for safe agents, but as a framework for answering architectural questions about whether, where, and how a system can be defended. The defensibility verdict is the output, not the safe policy.

Search-augmented LLMs increasingly mediate everyday consumer recommendations by retrieving live web content. This creates a new risk: generative recommenders may consume polluted web content, such as fake reviews and promotional pages crafted to mislead recommendations. We ask: to what extent do search-augmented LLMs become unwitting promoters of fake products when consuming polluted retrieval results? To answer this, we introduce FORGE (Fake Online Recommendations in Generative Environments), a benchmark for measuring fake-product promotion under controlled web-content pollution. Given an upstream search result, FORGE locally rewrites real products in retrieved web pages into fake ones to simulate web-content pollution, and measures how often the LLM recommends the fake product. FORGE covers 225 real-world products across 15 categories and 5 consumer scenarios. Across 12 commercial and open-weights LLMs, all models are vulnerable: a single polluted page yields fooled rates of up to 27%, while the full top-3 replacement raises this to 73.8%. Vulnerability varies substantially across categories, increasing when models lack stable prior knowledge of the relevant products. Reasoning does not mitigate this vulnerability; instead, it often generates spurious social proof to justify false recommendations. We evaluate three defenses: skepticism prompting and consensus filtering (over model priors or cross-document evidence). Skepticism can exacerbate vulnerability, much like reasoning, while filtering risks suppressing legitimate products. We release FORGE at https://github.com/leoluolol/forge-benchmark.

This paper presents a distribution-agnostic robust trajectory-optimization framework based on chance-constrained reinforcement learning. The uncertainty is represented here through initial conditions and process noise, with the only requirement being that it can be sampled. A deterministic nominal trajectory is first computed offline, and reinforcement learning is then used only to robustify that baseline through a structured affine closed-loop correction law comprising a feedforward control adjustment and time-varying feedback gains. Probabilistic feasibility is enforced empirically through rollout-based upper-tail quantiles, while terminal dispersion is regulated through covariance-feasibility penalties. The framework is assessed on two materially different trajectory design problems. The flagship case study is a three-dimensional multi-impulse Earth-Mars transfer, where the learned policy is benchmarked against a recent robust trajectory-optimization reference under Gaussian uncertainty and then evaluated under bounded uniform uncertainty and under process disturbances not seen during training. The second case study is a stochastic atmospheric pinpoint rocket landing problem, used to assess portability to a short-horizon continuous-thrust setting with drag, mass depletion, and glide-slope constraints. The results show that the proposed framework can remain competitive in upper-tail fuel cost while preserving probabilistic feasibility, and that the same robustification scaffold can be carried across heterogeneous spacecraft trajectory planning problems without redesign of its core stochastic-control structure.

Dispatch in three-sided marketplaces provides a natural setting for reinforcement learning from world feedback: decisions are evaluated by delayed operational outcomes such as delivery speed, courier utilization, and merchant congestion. We present a deployed reinforcement learning system at DoorDash that adapts dispatch objective weights in a large-scale food-delivery marketplace using delayed signals. Rather than replacing the combinatorial assignment optimizer, a store-level policy learned from logged marketplace data selects a discrete multiplier that shifts the dispatch optimizer's tradeoff between delivery quality and batching efficiency. This interface enables offline policy learning under noisy, delayed, and coupled feedback while preserving production feasibility constraints and operational safeguards. We train a shared value function using centralized offline data and decentralized store-level execution, with Double Q-learning targets and a conservative regularizer to reduce out-of-distribution value overestimation. In a production switchback experiment, the offline-trained policy increases batching and reduces courier-side time costs without degrading customer-facing delivery quality. Results illustrate how world feedback from a live economic and logistics system can be used to safely adapt decision policies online.

Dexterous robotic hands are usually formulated as high dimensional active control systems governed by degrees of freedom, actuation, and algorithms. Human hand dexterity, however, is partly encoded in the physical architecture of bones, ligaments, tendons, aponeuroses, and intrinsic muscles. This work describes that contribution as two linked forms of structural intelligence: structural prior generation, in which wrist to finger tenodesis, FDS/FDP routing, and the dorsal extensor hood transform low dimensional posture inputs into default grasp configurations and PIP to DIP coordination; and muscle mediated modulation, in which extrinsic muscles, lumbricals, and interossei regulate MCP posture, distal stability, fingertip force paths, and contact states around that default state. Based on this framework, MCR-Bionic Hand is developed as a 1:1 musculoskeletal biomimetic hand integrating a two row eight bone wrist, cross wrist tendons, anatomical flexor routing, volar plate and collateral ligament constraints, the dorsal extensor hood, and intrinsic muscle pathways within one body. Functional demonstrations and geometric mechanical models show that wrist posture induces multi joint pre shaping, the extensor hood maps PIP posture to a coupled DIP response, and intrinsic plus pathways modulate distal stability and fingertip action direction after grasp formation. Contact rich tasks, including coin rotation, pen transfer, dorsal coin flipping, and cube manipulation, show that MCR-Bionic links low dimensional state generation with fine post contact modulation. These results suggest that anatomical biomimetics is valuable not for visual similarity, but for identifying human hand structures that perform part of control.

Multi-Agent Systems (MAS) built on Large Language Models (LLMs) require effective orchestration to coordinate specialized agents, yet training such orchestrators is hindered by limited supervision and high computational cost. We propose Orchestration Reward Modeling (OrchRM), a self-supervised framework for evaluating orchestration quality without human annotations. OrchRM leverages intermediate artifacts from multi-agent executions to construct win-lose pairs for Bradley-Terry reward model training. Unlike existing MAS test-time scaling and orchestrator training frameworks that rely on costly sub-agent rollouts, OrchRM operates directly at the orchestration level, enabling efficient and high-performing reward-guided orchestrator training and MAS test-time scaling. OrchRM improves training efficiency by up to 10x in token usage while improving MAS test-time scaling performance by up to 8% in accuracy. These gains consistently transfer across multiple domains, including mathematical reasoning, web-based question answering, and multi-hop reasoning, demonstrating orchestration-level reward modeling as a scalable direction for robust multi-agent orchestration. Code will be available at https://github.com/Wang-ML-Lab/OrchRM.

Multi-agent systems communicate mostly through text, paying a lossy and expensive decode and re-encode cost. KV-cache communication is a promising alternative, yet most prior work is homogeneous, using duplicate copies of the same model, and avoids the central challenge of cross-model latent alignment; existing heterogeneous methods are also restrictive, typically assuming shared input and using transferred caches mainly for steering. We study a more fundamental question: can heterogeneous agents be aligned well enough to perform real "mind reading" and transfer both what one agent sees and how it thinks? Our information-structure analysis reveals a duality: context-aware transfer is driven by sparse reasoning signals, while context-unaware transfer, where the receiver sees no input, requires dense contextual knowledge preservation. Motivated by this, we propose dense alignment for heterogeneous KV-cache communication via a lightweight cross-model cache transformation and two-phase training: reconstruction followed by generation. Across all six directions of {Qwen3-4B, 8B, 14B} and six in-domain and out-of-domain benchmarks, our method outperforms prior heterogeneous baselines, matches or exceeds text communication in context-aware settings at roughly 2 to 3 times lower compute, and remains effective in context-unaware transfer where prior methods collapse.

Confidence is used for reliability, oversight, and a range of downstream decision tasks in Natural Language Processing (NLP), yet no existing method produces or evaluates a confidence for the output of a multiagent system. Prior work uses confidence within multiagent debate (MAD) to weight messages, trigger debate, or calibrate individual agents, but it never aggregates these into a single confidence for the system itself. We introduce three protocols that produce a final answer along with a single aggregated confidence by first transforming raw confidence signals to make them comparable across models, then combining them via soft voting or a probability fusion we call Bayesian fusion. This aggregated confidence is substantially more discriminative (AUARC) than that of the best single agent or the standard debate baselines, while correctness (F1-score) stays stable and recovers the losses MAD incurs on more ambiguous tasks. Analyzing two estimators, sequence probability and self-report, alongside parametric and non-parametric calibrators, we find that calibration improves F1 for both estimators while AUARC is less reliant on it. We evaluate six homogeneous and heterogeneous debating pairs per benchmark, across five benchmarks and four task types, spanning a range of model capabilities and sizes.

Scientific laboratories increasingly rely on AI systems to reason about experiments, but the physical act of doing science remains largely outside their reach. AI can help read literature, generate hypotheses, and plan protocols, yet the execution of those protocols at the bench still requires a human operator. Vision-Language-Action (VLA) models provide one possible interface between written protocols and robot execution, but existing policies are trained mostly on household and tabletop demonstrations and rarely encounter the instruments, transparent liquids, or fixed protocol workflows found in scientific laboratories. Closing this gap requires both laboratory-specific supervision and a unified learning framework that can accommodate the diverse robot embodiments used to execute experimental protocols. We therefore identify data and embodiment as central bottlenecks alongside model design. To address the data side, we build RoboGenesis, a simulation-based workflow and data engine that composes configured laboratory workflows from atomic skills, validates and filters rollouts, and exports structured demonstrations across supported robot profiles. On the policy side, we present LabVLA, trained with a two-stage recipe: FAST action token pretraining first makes the Qwen3-VL-4B-Instruct backbone action aware before any continuous control is learned, and flow matching posttraining then attaches a DiT action expert under knowledge insulation. On the LabUtopia benchmark, LabVLA achieves the highest average success rate among all evaluated baselines under both in-distribution and out-of-distribution settings.

Multimodal Large Language Models (MLLMs) have shown promising reasoning capabilities in general domains, yet their performance remains limited in specialized settings such as healthcare, especially in multilingual and low-resource scenarios. This gap is critical in regions like rural India, where patients often express complex medical queries in native Indic languages and rely on multimodal inputs such as medical images. Existing English-centric MLLMs struggle to support such use cases, limiting equitable access to AI-driven healthcare assistance. To address this challenge, we introduce ArogyaBodha, a large-scale multilingual multimodal medical question-answer dataset constructed from eight heterogeneous sources, covering 31 body systems, six imaging modalities, and 21 clinical domains across English and seven major Indian languages. We further propose ArogyaSutra, an actor-critic-based multi-agent framework that integrates tool grounding with dual-memory mechanisms for step-wise, reasoning-aware decision making, and uses stored actor-critic simulation trajectories for distillation. Experiments show that our dataset and framework improve multilingual medical reasoning accuracy across all Indic languages, with ablations validating the contribution of each component. The source code and dataset are available at: https://iitp-cse.github.io/ ArogyaSutra/

Retrieval augmented generation (RAG) depends critically on the quality and granularity of retrieved evidence. Large retrieval units preserve context but often introduce irrelevant content, which can dilute answer bearing evidence and worsen long context utilization. Fine-grained units are more compact, but they may be difficult to retrieve reliably because short chunks can lack semantic, lexical, or bridging cues needed to match the query. We propose Uncertainty-aware Multi-Granularity RAG (UMG-RAG), a training-free hybrid retrieval framework that treats chunk granularity as query-specific reliability estimation. Instead of training a new retriever or modifying the generator, UMG-RAG uses existing dense and sparse retrievers as complementary experts across multiple chunk granularities. For each query, it converts each expert-granularity score list into an evidence distribution, estimates reliability from distribution entropy, and fuses candidates according to query-specific semantic, lexical, and granularity confidence. We further introduce UMGP-RAG, a parent promotion variant that uses fine-grained hits to locate relevant evidence while returning broader non-redundant parent chunks for local coherence. Experiments on question answering benchmarks show that uncertainty-aware fusion and parent promotion improve generation quality while maintaining a lightweight, plug-and-play retrieval pipeline.

Turn-taking in multi-party spoken conversations remains a fundamental challenge for voice-based agents, particularly under dynamic floor competition and varying user expectations. We propose ModeratorLM, a role-playing voice agent that conditions turn-taking behavior on an explicitly assigned role in multi-party settings. The system is built on a speech large language model operating in chunk-wise streaming manner. We further introduce a reasoning-augmented variant that incorporates chain-of-thought reasoning over conversational context and the assigned role. We construct RolePlayConv, a large-scale synthetic dataset of spoken multi-party conversations with diverse assistant roles. Experiments on real-world meeting data and RolePlayConv show improved turn-taking precision by over 40% and recall by more than 70%, while substantially reducing false-positive interruptions compared to non-role-conditioned baselines.

This paper presents a comprehensive overview of the QIAS 2026 shared task, organized as part of the OSACT7 Workshop and co-located with LREC 2026. The shared task was designed to evaluate the ability of large language models to perform complex reasoning in the religious and legal domain of Islamic inheritance. Unlike conventional question-answering benchmarks, QIAS 2026 focuses on end-to-end reasoning from natural language cases, requiring systems to perform the full inheritance calculation process, from identifying the eligible heirs to assigning the correct share to each beneficiary. To support this evaluation, the task was based on the MAWARITH benchmark, a dataset of $12{,}500$ Arabic inheritance cases annotated with intermediate reasoning steps and final answers. System submissions were evaluated using MIR-E, a multi-step metric that measures performance across the main stages of inheritance reasoning. A total of $16$ teams participated in the shared task, investigating a range of approaches, including prompting-based methods, retrieval-augmented generation, and fine-tuning strategies. The results show that Islamic inheritance remains a highly challenging benchmark for current language models, especially in stages that require precise legal interpretation and structured numerical reasoning. This overview summarizes the task design, dataset, evaluation framework, participating systems, and main results.

World Action Models (WAMs) present a promising paradigm for robotic control via video prediction. However, current WAMs suffer from fundamental spatial bottlenecks: standard text inputs introduce referential ambiguity in cluttered scenes, while unstructured RGB predictions lack semantic grounding and remain biased by task-irrelevant backgrounds. To overcome these limitations, we introduce MaskWAM, an object-centric world-action model. By jointly integrating masks as both explicit inputs and predictions via a unified Mixture of Transformers (MoT), MaskWAM unlocks robust policy generalization. This design provides two key benefits: (1) predicting future masks yields object-centric semantic supervision that suppresses visual noise, significantly enhancing even standard text-conditioned WAMs; and (2) coupling this predictive supervision with first-frame visual prompts, such as target object masks, establishes a precise spatial anchor that substantially reduces language ambiguity. Crucially, as WAMs are inherently vision-driven architectures, direct mask conditioning yields substantially stronger guidance than text alone, establishing a precise and robust paradigm for manipulating unseen objects. Evaluations on LIBERO, RoboTwin, and real-world tasks demonstrate that MaskWAM significantly outperforms baselines in both language-clear and language-ambiguous tasks.

This work introduces Spatial Annotations from Robot Demonstrations with Reliability Calibration (SPARC), a risk-aware framework that automatically labels robot demonstrations with structured spatial annotations and assigns each annotation a reliability score. Structured spatial annotations, such as bounding boxes, object trajectories, and manipulation phase labels, benefit a broad range of robotics applications from training grounded robot policies and embodied foundation models to motion planning and hierarchical task composition. Existing automated pipelines generate such annotations at scale but provide no reliable quality signal: detector confidence is poorly calibrated for annotation correctness, forcing a choice between accepting noisy labels or discarding useful samples. In contrast to existing automated pipelines, SPARC leverages the spatio-temporal structure inherent to robot tasks to generate a reliability signal, reducing noisy labels and retaining more useful samples. We further introduce Interaction-Aware Bench (IA-Bench), a benchmark that measures model accuracy in grounding the locations of interacted objects in robot demonstrations. On 1.7k human-annotated demonstrations spanning diverse embodiments and scenarios, SPARC significantly outperforms detection-only baselines in localization accuracy while retaining three times more samples at high-precision operating points. Our experiments demonstrate that models finetuned on our annotations achieve state-of-the-art results on object-grounding and pointing benchmarks among similarly sized models, while remaining competitive on broader spatial-reasoning suites without manually verified or annotated training data. Furthermore, policies trained on SPARC-generated annotations outperform baselines in cluttered, visually ambiguous real-world scenes. Code, data, and models are available at intuitive-robots.github.io/sparc-labeling.

Goal-conditioned visual navigation requires a robot to act under partial observability by anticipating how its motion will change the future egocentric view and whether that change brings it closer to the goal. Navigation world models provide such visual foresight, but they remain prediction modules that require an external planner to convert predicted futures into closed-loop control. We propose Navigation World Action Model (NavWAM), a diffusion-transformer policy that turns navigation world-model prediction into executable action by representing future observations, goal-progress values, and action chunks in a shared latent sequence. By learning future prediction jointly with the action and value targets that determine closed-loop behavior, NavWAM makes visual foresight directly usable for robot control. We build NavWAM through simulation pretraining and real-robot adaptation, and evaluate it on image-goal navigation against planning-based world models and a representative direct navigation policy. Across offline benchmarks and closed-loop real-robot deployment, NavWAM improves over planning-based world-model baselines in our evaluations while using the default policy mode without CEM-style action search. Project page: https://dachii-azm.github.io/navwam/

Knee rehabilitation exoskeletons must enforce a prescribed joint trajectory while remaining safely compliant with involuntary spasm and voluntary patient effort-objectives in tension for any fixed-gain impedance controller. We present an Impedance Model Predictive Control framework for knee rehabilitation exoskeletons, demonstrated on a series-elastic-actuator (SEA) platform: an algebraic feedforward reduces the knee dynamics to a constant-coefficient scalar double integrator, and a receding-horizon quadratic program (QP) computes corrective torques while enforcing hard range-of-motion, torque, and velocity limits (ISO 13482). A Kalman disturbance state driven by direct SEA-based torque sensing (the series-elastic spring deflection measured through the elastic element - an intrinsic, EMG-free patient-torque estimate, not a separate load cell) gives a nominal offset-free guarantee and, via its sign and the desired-motion direction, sensorless Assist-as-Needed. The constant state matrix permits offline precomputation of the QP cost inverse, enabling 500 Hz operation with a multi-step horizon. Across seven-controller benchmarks (sinusoidal tracking, isometric hold), the 500 Hz Kalman MPC is offset free 0.1 mrad RMS, 0.1 mrad steady-state, 0.2 mrad peak under 15 Nm spasm, versus a 515 mrad steady-state offset for classical impedance at the same stiffness - the direct-measurement channel converging the estimate near-immediately (within a few sampling periods). Without the estimator it realizes a classical impedance (4.8 mrad RMS, 8.3 mrad steady-state). All MPC variants meet the 87 mrad clinical criterion; no classical controller does. The architecture is formulated for the 20 DOF MyoSuite myoLeg via coupling-aware per-joint QPs.

We present a communication-aware task decomposition framework for multi-agent systems with collaborative relative configuration objectives specified in Signal Temporal Logic (STL), allowing for dynamic task reallocation under time-varying communication networks. Building on our prior work, the framework supports the direct use of existing feedback controllers for reactive task satisfaction. We address two key challenges: disjunctive STL specifications and time-varying communication networks. Disjunctive specifications are handled through a graph transition system that captures the alternative task sequences induced by logical OR operators. To address time-varying connectivity, we introduce a redistribution mechanism that transfers tasks from disconnected agents to connected ones as the network evolves while preserving decentralized execution. Simulations and experiments on a swarm of Crazyflie drones demonstrate scalability in the number of agents, communication connectivity, and specification complexity.

Supramolecular chemistry, which includes the study of non-covalent host-guest assemblies, has advanced various applications. However, designing host-guest systems remains time-consuming, requiring days of dry-lab verification per candidate pair. Although LLMs have emerged as a fast alternative with strong performance on molecular binding tasks, no benchmark currently systematically evaluates LLMs for host-guest reasoning across fundamental supramolecular chemistry tasks, e.g., binding affinity prediction. To this end, we collaborate with domain experts to release the first Supramolecular Benchmark, called SupraBench, to evaluate LLMs in chemistry reasoning. Specifically, we design four fundamental tasks, i.e., binding affinity prediction, top-binder selection, solvent identification, and host-guest description, plus an auxiliary vision-based task for molecular identification. We also release SupraPMC, a curated 16M-token corpus of Supramolecular chemistry articles distilled from Europe PMC, to support the adaptation to the supramolecular domain. We benchmark a broad range of open and proprietary LLMs and find that LLMs leave substantial headroom across all tasks. Domain adaptation pretraining over SupraPMC transfers cleanly to in-distribution regression but trades off against strict letter-format output. Moreover, the difficulty profile differs sharply across task families, revealing distinct failure modes that indicate specific gaps in current supramolecular chemistry reasoning. Our source codes and benchmark datasets are available at https://github.com/Tianyi-Billy-Ma/SupraBench.

This paper proposes a novel adaptive control framework that embeds nonlinear opinion dynamics within the dynamical sensorimotor layers of an automated vehicle governed by second-order nonholonomic bicycle kinematics. The framework enables an ego vehicle to perform adaptive decision-making and achieve safe motion control under interaction uncertainty with non-cooperative neighboring agents. We consider a representative case study in which an ego vehicle autonomously attempts to merge into a lane occupied by human-driven or automated vehicles whose intentions are unknown. Within the proposed framework, the ego vehicle adaptively selects and executes merging versus non-merging behaviors in response to changing environmental conditions. Formal safety guarantees, as well as equilibrium and stability analyses of the closed-loop system, are provided. Numerical simulations further demonstrate the effectiveness of the proposed approach.

Despite recent progress in Natural Language Processing (NLP), models remain vulnerable to word substitution attacks. Most existing defenses focus on first order sensitivity and measure how much the output changes when the input is slightly perturbed. However, they ignore how this sensitivity evolves, which is described by curvature. When gradients vary sharply, models can still fail. This paper introduces the Smooth Growth Bound Tensor (S-GBT), a second order method that bounds the Hessian element-wise, for which we provide formal theoretical proofs on the resulting robustness bounds. A regularization term is added during training to minimize these bounds. This yields tighter certified robustness against word substitution attacks. The change in the output under word substitution is bounded by both a linear term and a quadratic term. S-GBT is derived for two architectures: Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNN). The method is integrated directly into the training objective. Its effectiveness is evaluated on multiple benchmark datasets. The results show that combining first and second order regularization improves certified robust accuracy by up to 23.4% compared to prior methods, while clean accuracy remains competitive. These findings indicate that controlling both the gradient and its variation is a promising direction for building more robust models.

Human communication is inherently multimodal, where language is often accompanied by non-verbal cues such as gestures to convey intentions. However, current Vision-Language-Action (VLA) models treat robotic manipulation as a pure text-driven task, overlooking the important role of gestures in Human-Robot Interaction (HRI). This often leads to inaccurate intent grounding and unreliable manipulation when language instructions are ambiguous or underspecified. To address this challenge, we propose GIVE (Gesture Intent via Visual-Semantic Enhancement), an effective approach that enhances pre-trained VLA models with human gesture understanding without architectural modifications. Specifically, GIVE incorporates gesture information through two complementary pathways: a visual pathway that overlays hand skeletons and fingertip rays onto robot observations for explicit object grounding, and a semantic pathway that generates high-level descriptions of human gestures and task instructions for robust intent grounding. By jointly leveraging visual and semantic guidance, GIVE enables VLA policies to better associate gestures with manipulation behaviors and adapt to dynamic interaction intents. In real-world HRI experiments, GIVE substantially outperforms the baseline, improving target object recognition accuracy by 40% and overall task success rate by 80%, while demonstrating strong robustness and generalization to unseen spatial layouts and diverse participants.

Artificial dynamic tactile sensing requires sensitivity, robustness, and compliance, yet existing technologies face trade-offs when scaling to large-area arrays, compounded by wiring complexity and cost. Here, we report a passive distributed paradigm using deep sub-wavelength acoustic waveguides that decouples performance from structural flexibility. Elastic-membrane-capped Helmholtz resonators interconnected by spring-reinforced microtubes form an enclosed network with invariant acoustic transmission under macroscopic bending. By sparsely embedding microphones, the system achieves real-time localization (4 mm highest spatial resolution; >99% accuracy in a 4 microphones 64-node sensing array) and waveform reconstruction of low-frequency signals (<100 Hz). Fast Continuous Wavelet Transform and a lightweight neural network enable inference within 5.5 ms. We demonstrate conformable prototypes-fingertip arrays, a tactile glove, and large-area skins-detecting stimuli from single-hair contact to 5-mg particle impacts, arterial pulse waves, feather touches, and finger contact. This establishes a scalable, flexible, low-cost paradigm for next-generation human-machine interfaces.

Whole-body mobile manipulation requires coordinating mobile base and manipulator under shifting viewpoints, posing challenges in geometric perception and action generation. Current policies either rely on 2D features or sparse 3D representations that lack dense spatial structure, and typically encode arm and base within one action vector that ignores their distinct control demands. Moreover, existing dense fusion strategies risk corrupting pretrained representations under noisy depth while incurring heavy computational overhead. We present GeoHAT, an end-to-end diffusion-based framework built on a simple principle: geometry should be injected only where reliable and attended to only where needed. GeoHAT employs a lightweight Fourier spatial encoder that maps dense per-pixel 3D coordinates into geometric tokens without an additional 3D vision backbone. These tokens are then selectively injected into vision foundation model features through per-token gated fusion modulated by depth validity, preserving the semantic prior while enriching spatial understanding. For action generation, a Hybrid Whole-Body Action Decoder decomposes arm and base into distinct subspaces and lets each action modality attend to its task-relevant visual context through sparse cross-attention, while causal temporal modeling captures intra-timestep coordination and inter-timestep dependencies. Experiments on the ManiSkill-HAB simulation benchmark demonstrate that GeoHAT achieves a 79.3% mean success rate, surpassing the strongest baseline by 23.7%. Furthermore, real-world experiments on diverse tasks also confirm consistent improvements over all baselines.

In this work, we report on the design strategies and experimental validation of ultra-low threshold ($< 0.8\,\mathrm{mA}$) hybrid III--V/Si quantum dot (InAs/GaAs) micro-ring lasers with optical output powers $> 2\,\mathrm{mW}$ for $1.3\,μ\mathrm{m}$ emission. The multi-dimensional design exploration allows for the demonstration of record wall-plug efficiencies ($\sim 10\%$) and threshold current densities ($109\,\mathrm{A/cm^2}$) for these compact sources on silicon. We also demonstrate the thermal performance of several designs with record characteristic temperature values of $T_0 = 212\,\mathrm{K}$, indicating minimal temperature dependence of the threshold current. In addition, the high differential gain allows for the demonstration of 3-dB bandwidths up to $5\,\mathrm{GHz}$.

Right now, across the world, AI agents are repeating the same absurd act: to read one document, they each recompute it from scratch. Every agent re-runs prefill, the most compute-intensive step a large model takes, over identical text, only to rebuild a key-value (KV) cache identical to the one the agent before it just built. The same answer, computed a million times. We make a proposal that is almost offensively simple: compute it once. Let a publisher precompute a document's KV cache, and let every other agent buy the right to load it and skip prefill. It works, and it is token-exact: loading a precomputed KV and continuing matches prefilling from scratch (24/24 greedy tokens, and at the logits level), with no accuracy cost. On Qwen3-4B, reuse is 9-50x cheaper in compute than prefill, and the gap widens with length (prefill's attention scales with L^2), so a single reuse already pays it back. Then the part that matters: where the KV lives. Shipping it fails, because KV is nearly incompressible, so per-load egress costs more than the prefill it saves. Hosting it provider-side, exactly as production prompt-caching works, removes egress entirely. The size of the prize is set by our measured compute saving: serving one hot 3774-token document to 80M agents costs ~$1.5M to re-prefill but only ~$0.03M of reuse compute (49.7x less). The 0.1x cache-read tariff APIs charge passes a 10x discount to users while sitting inside this measured envelope, so the 10x is a floor that the measured ~50x compute saving clears, and the gap to the physical ~50x is provider margin: millions of dollars per popular document. We frame the resulting agent-native prefill CDN and leave lossless KV compression and a cross-party payment layer as the open problems.

Real-time execution, enabled by asynchronous inference that ensures both smooth action trajectories and fast reactivity, is critical for realistic deployments of large-scale Vision-Language-Action models. However, recent work on real-time execution primarily focuses on variants of diffusion policies, even though it is more critical for autoregressive policies given their slower rollout speed in synchronous inference. In contrast, we demonstrate that autoregressive policies can achieve real-time execution by adjusting the tokenization horizon and applying constrained decoding, thereby guaranteeing strict latency bounds that enable multi-trajectory decoding to maximize performance. Across simulated and real-world environments, we find that the autoregressive policy consistently outperforms its equivalent-level flow-matching policy counterpart while achieving significantly improved task completion speeds from synchronous inference. Coupled with the inherent advantages of autoregressive policies, such as faster convergence and better generalizability in instruction-following, these results confirm that autoregressive policies can remain a competitive policy type supporting real-time execution.

Existing stretch and touch sensors for robots are generally expensive with respect to at least one of material costs, required manufacturing equipment, or manufacturing time. We present and experimentally characterize a conductive fiber made using only inexpensive commercial off-the-shelf parts (conductive thread at $0.07/ft, silicone tubing at $0.94/ft) and tools (loop-style needle threader at $2), which can be manufactured quickly (20 cm length in 2 minutes.) We demonstrate its use as a resistive strain sensor with three applications: Triggering a grasp in a pneumatically actuated assistive finger, sensing the pose of a pneumatically actuated robotic strap, and estimating the pose of a flexible solid. We also demonstrate that it can be used as a capacitive sensor with two applications: First, as a touch sensor which triggers a commercial robot arm to move, and second, as a near-field sensor enabling the robot arm to follow a moving hand. The capacitive sensors are knitted, showcasing the high flexibility of the fiber. We discuss methods for improving manufacturing scalability and their cost trade-offs. Finally, we demonstrate a method for repairing a cut fiber.

Large language models (LLMs) have shown promise in automating scientific peer review. However, existing approaches often struggle to generate in-depth reviews supported by concrete evidence. We argue that a key limitation is the lack of flexibility to proactively investigate suspicious parts of a paper based on accumulated evidence, as human reviewers do. In this paper, we explore how to enable an LLM-based review agent to perform such proactive investigation. We find that this can be naturally formulated as a Markov Decision Process (MDP), and propose ProReviewer, a scientific peer review agent that proactively reviews a paper guided by a maintained, structured review log. The structured review log serves as a workspace for the agent to track evidence and intermediate findings collected during review. Experiments show that ProReviewer with an 8B backbone, trained by supervised fine-tuning and optimized by reinforcement learning, achieves the highest average score across five quality dimensions, outperforming prompt-based methods with much larger frontier LLMs by up to 39% and the strongest fine-tuned baseline by 16% relatively. It also attains the highest win rates against baselines in human evaluation.

Skill self-evolution methods for LLM agents aim to turn execution trajectories into reusable skill documents, but current pipelines typically learn from one trajectory per task, merge candidate skill patches before checking them, and load the full skill corpus before inference. We propose SkillCAT, a training-free framework that separates this process into three stages. Contrastive Causal Extraction (CCE) samples multiple trajectories for each task and compares same-task success/failure pairs to identify evidence that explains outcome differences. Assessment-Augmented Evolution (AAE) replays each candidate patch on source-task clones and keeps only patches that improve or preserve task outcomes before hierarchical skill patch merging. Topology-Aware Task Execution (TTE) compiles the evolved skills into a routable sub-skill topology, so inference loads only the capability nodes relevant to the task. We evaluate SkillCAT on common agent benchmarks, including SpreadsheetBench, WikiTableQuestions, and DocVQA, and further test cross-model and out-of-distribution generalization. Across these settings, SkillCAT raises the average score over baselines by up to 40.40%, demonstrating reliable skill evolution without model training.

In bimanual robotic manipulation, task-relevant visual information varies with the task stage and context, while the interaction of the two arms shifts between independent and coordinated modes, making policy learning challenging. However, existing monolithic Vision-Language-Action (VLA) policies process diverse visual inputs and interaction patterns through a single shared representation and action generation pathway, often failing to separately account for visual relevance and bimanual interaction structure. To address this issue, we propose a bimanual manipulation VLA framework based on Dual-Level Structural Decomposition. The View-Selective Visual Router dynamically adjusts wrist-view contributions to emphasize relevant visual cues, while the Interaction-Aware Action Mixture-of-Experts (MoE) decomposes action generation into coordinated and arm-wise pathways to adapt to varying bimanual interaction modes. We evaluate the proposed method on six simulated bimanual manipulation tasks in RoboTwin 2.0 and three long-horizon real-world tasks. Our model improves the overall average success rate over a monolithic baseline by 27.7% in simulation and 43.3% in real-world evaluation, while consistently outperforming single-module variants across both settings. These results demonstrate that jointly considering selective visual processing and explicit decomposition of bimanual interaction structures provides an effective inductive bias for robust bimanual manipulation.

Business intelligence (BI) increasingly combines dashboard interaction with LLM-based assistance, but these two modes often fall out of sync during multi-step analysis. As users switch between direct dashboard manipulation and natural-language queries, it becomes difficult to preserve a consistent analytical state across filters, hierarchies, metrics, and chart context. We present TwinBI, an agentic digital-twin framework that couples an LLM-based agent system with an executable BI dashboard state. TwinBI unifies conversational interaction, dashboard manipulation, semantic grounding, and provenance tracking through a shared analytical state reconstructed from a unified interaction log. It also exposes artifacts such as schema views, SQL, logs, and an /insights command for state-grounded analytical summaries. We evaluate TwinBI in two complementary ways. In a controlled A/B benchmark with the same backbone agent, TwinBI improves exact-match accuracy from 43.3% to 63.3%, partial-credit accuracy from 48.3% to 70.8%, and substantially reduces timeout rate from 40.0% to 10.0% relative to Dashboard alone. In a usability study, participants benefited from the integrated dashboard-and-chat workflow, with high task accuracy, moderate workload, and favorable ratings for state-aware interaction mechanisms. These results suggest that TwinBI improves both agent-level analytical reliability and user-facing analytical support by turning visible dashboard state into richer actionable context. Our dataset and source code are available at: https://github.com/simonjisu/TwinBI

Whole-body humanoid manipulation of bulky, deformable, and shared-load objects requires distributed contact sensing and explicit force regulation, yet most imitation policies treat contact force only implicitly. On the other hand, different demonstration sources provide complementary modalities with inherent trade-offs: human demonstrations capture natural contact forces but not robot-executable actions, while teleoperation directly records robot actions but with less natural force regulation. This paper presents \textbf{WT-UMI}, a wearable whole-body tactile interface worn by human operators or mounted on humanoids, providing accurate observations of tactile images, contact forces, and end-effector poses across both human demonstration and humanoid teleoperation modes. We introduce a force-conditioned target-pose correction module that converts measured human poses into contact-aware robot targets by learning corrections from teleoperation data. To leverage the natural force interaction in human data, we propose a force-supervised planner that predicts end-effector pose chunks and contact-force trajectories. The predicted contact force serves as the reference for a tactile-based admittance controller. Across five contact-rich tasks spanning deformable objects, bulky rigid objects, and human--humanoid collaboration, WT-UMI improves success rate and reduces contact-position tracking error over four policy baselines. Our project page is available at https://wt-umi.github.io/WTUMI/.

Distinguishing self from others is a prerequisite for social intelligence, yet humanoid robots that increasingly share workspaces with humans still lack this ability. Here we show that a humanoid robot can learn self-other distinction from proprioceptive-visual correspondence, without any identity labels or kinematic models. Once established, this distinction bootstraps a predictive self-model that maps joint configurations to three-dimensional body occupancy, capturing how the robot's body changes with action. In multi-agent scenes involving humans or morphologically identical robots, the system reliably identifies itself, learns a 3D self-model, and supports downstream tasks including target reaching, collision-aware motion planning, and human-to-robot motion retargeting. Together, these results outline a route toward bodily self-representation in robots that act and coordinate alongside others in shared physical environments. Project page: https://euron-zc.github.io/humanoid-self-model/.

Large language models (LLMs) are increasingly used as interactive assistants for technical problem solving. However, when users provide incomplete descriptions or plausible but unverified explanations, LLMs may prematurely align with these assumptions and propose solutions before collecting sufficient evidence. We refer to this behavior as user-driven sycophancy: the tendency of an LLM to reinforce a user-provided hypothesis instead of testing alternative explanations. This paper introduces LLM-as-an-Investigator, an evidence-first agentic AI methodology for robust problem diagnosis. The approach is implemented through a Solution Investigator Agent, which estimates the ambiguity of an initial problem description, generates candidate hypotheses, asks targeted clarification questions, and updates hypothesis probabilities after each answer. Rather than producing an immediate response, the agent continues the investigation until the evidence makes one candidate explanation stronger than the alternatives. To evaluate the approach, we build a benchmark from solved technical forum threads in mechanical, electrical, and hydraulic domains. We use a three-agent evaluation pipeline in which a Problem-Solution Extractor Agent converts solved threads into structured cases, a Ground-Truth Evaluator Agent simulates the user while hiding the known solution, and the tested assistant attempts to recover the solution through dialogue. The experiments compare standard assistants, reasoning-oriented LLMs, and the proposed investigator-based model across LLM backbones. In addition to diagnostic accuracy, we analyze how standard assistants follow misleading user hypotheses in diagnostic cases. The results show that the proposed approach identifies the problem more accurately than direct prompting and reasoning-only baselines, while its evidence-first protocol helps reduce user-induced conversational bias.

Visual place recognition in natural forest environments remains challenging due to repetitive vegetation, weak structural cues, and significant appearance variation across traversals. To address this limitation, this paper proposes a lightweight depth-aware distillation framework that injects geometric cues into a DINOv2-based place recognition model, while maintaining its pre-trained descriptor space. Evaluated on the recent WildCross benchmark, the proposed approach yields gains over an appearance-only counterpart, providing robustness to appearance variations. These results demonstrate the importance of depth as a strong complementary modality for place recognition in natural environments and identify depth-aware distillation as a promising direction for more robust forest perception.

While non-verbal behaviors and expressive movements are essential for natural human-robot interaction, existing methods often overlook a crucial element: the human's internal cognitive state. Frequently, proactive multi-agent systems can interrupt humans at inopportune moments, leading to cognitive overload and decreased task performance. This paper introduces a framework for generating "cognitively aligned" multi-agent interactions, enhancing the ability of robotic systems to contextually defer communications to the user of an agent system during moments of high human mental workload and engagement. We present the design and implementation of a closed-loop architecture that explores the interplay between autonomous task execution and real-time neurophysiological focus. Using a consumer-grade Brain-Computer Interface (BCI), our approach continuously monitors Electroencephalography (EEG) spectral band powers while a human performs an engagement-inducing task. We propose an engagement-driven pipeline where an HTTP-based signaling mechanism places a primary agent's sensory inputs and audio outputs into a holding state upon detecting high engagement. This allows secondary agents to seamlessly process complex, delegated tasks in the background. Once the human's cognitive state returns to a lower cognitive load baseline, the primary agent releases the queued agent message. Our preliminary results demonstrate the feasibility of leveraging real-time signal processing, Large Language Models (LLMs), and physical robotic embodiments to create cognitively-aware, non-intrusive multi-agent systems.

This paper proposes a novel regularization design to effectively smooth policy functions in reinforcement learning. While regularization that enhances ``global'' Lipschitz continuity was initially considered, it has been limited to ``local'' Lipschitz continuity due to a tradeoff between smoothness and expressiveness. However, it has become apparent that the original implementation is cumbersome and does not provide sufficient smoothing, leading to a preference for simpler implementations. This stems from a discrepancy between theory and implementation, and a more appropriate implementation can expect to facilitate smoothing. Therefore, this paper identifies three reasons why the original implementation does not function adequately and provide remedies for them. This modified regularization performs well across multiple tasks and algorithms, successfully achieving smooth motion while improving control performance. Furthermore, by applying it to sim-to-real reinforcement learning for a quadruped robot, it is demonstrated that smooth motion provides robustness against sudden changes in target velocity commands.

Hard X-ray ptychography has become increasingly essential in both the life and physical sciences. However, pushing resolution down to a few nanometres often requires highly customized, chromatic diffractive or refractive X-ray nanofocusing optics, significantly limiting the practical broadband energy-scan applications. Here, we present the first known hard X-ray ptychographic imaging with a half-pitch resolution below 8 nm using total-reflection Advanced Kirkpatrick-Baez (AKB) mirror nanofocusing optics at the high energy photon source (HEPS), with clear potential for further extension. Despite leveraging the benefits of enhanced instrumentation, such as the high coherent flux of 4th-generation diffraction-limited storage rings (DLSR), state-of-the-art beamline X-ray optics and detectors, this is made possible by developing a reconstruction algorithm termed Generalized Wirtinger Projections (GWP). We derive the theory of GWP and experimentally demonstrate its capability for improved partial-coherence reconstruction and enhanced spatial resolution over conventional methods through imaging experiments on a Siemens star test chart at 12.4 keV. GWP provides a highly compact framework for jointly accounting for multiple coupled uncertainties that degrade resolution, enabling straightforward extension to other imaging modalities, such as burst ptychography, while delivering nearly an order-of-magnitude improvement in GPU memory efficiency. Furthermore, the ability to combine nanometre-scale spatial resolution with the inherently achromatic nanofocusing optics demonstrated in this work potentially opens new opportunities for in situ or operando broadband, energy-scan 3D spectroscopic imaging with element- or chemical-state specificity in complex environments at the nanoscale, holding significant promise for a wide range of applications from electronics and energy science to neuroscience.

Hierarchical 3D scene graphs (3DSGs) for indoor robots organize geometric and semantic information across spatial scales, with a room layer that connects object-level perception to room-scale reasoning. Existing systems construct this layer from different spatial substrates (\eg{} place clusters, wall planes, or segmentation outputs), and as a result, room nodes are not evaluated on a common geometric criterion. We present an occupancy-grounded 3DSG pipeline in which room nodes are anchored to tracked free-space regions derived from occupancy decomposition, giving each room an explicit polygonal footprint. We evaluate the pipeline on 12 Matterport3D scenes by matching predicted room polygons to annotated room instances and compare against Hydra, a representative state-of-the-art place-connectivity baseline. The results show that occupancy-grounded anchoring recovers substantially more room instances than place-connectivity construction, at the cost of lower precision, and that wall-accurate room boundaries remain an open problem for both methods. Code is available at https://github.com/crcz25/OccuSG.

Despite the success of vision-based generalist robotic policies, existing tactile-based policies remain tied to fixed embodiments and sensor setups. This is because tactile signals are highly heterogeneous across hardware, making cross-sensor generalization difficult. We present FTP-1,the first generalist foundation tactile policy pretrained to acquire transferable tactile manipulation abilities across diverse sensors and embodiments. FTP-1 supports varied tactile inputs, including image-, array-, and state-based signals, by using heterogeneous encoders to project them into unified morphology-aware latent tokens that are jointly modeled by a shared tactile Transformer expert. Pretrained on around 3,000 hours of tactile manipulation data aggregated from 26 data sources, spanning human and robot demonstrations across 21 sensors, FTP-1 learns tactile skills that transfer beyond the sensors seen during pretraining. Across downstream finetuning experiments spanning 5 hardware configurations, FTP-1 improves contact-rich manipulation on seen sensor setups by +17.2% and, surprisingly, transfers to two previously unseen tactile-sensor setups, achieving a +31% gain in success rate. FTP-1 establishes the first unified foundation baseline for tactile manipulation, providing future tactile policies with a shared model-level starting point. Pretrained models, datasets, training code and more visualization at https://ftp1-policy.github.io.

Scale buys interpolation; structure buys a certified horizon. A world model's average error says nothing about whether a particular prediction can be trusted, or for how long. For equivariant latent world models we give a computable, multi-step certificate of the predictable horizon: $T$-step rollout error is provably constant over each symmetry orbit (Theorem A) and stratified channel-by-channel by the predictor's Lyapunov spectrum, $T_j(ε)\sim\log(1/ε)/λ_j$. The horizon is two-sided -- a matching lower bound makes approximate equivariance provably horizon-limited -- and the certificate is exclusive to structure: orbit-constant error characterizes equivariance, so no non-equivariant model has it at any scale. Empirically, on 40-D Lorenz-96 only a $\mathbb{Z}_N$-equivariant network recovers the full Lyapunov spectrum ($R^2{=}0.98$); dense and recurrent baselines fail. Because the spectrum is faithful, the certificate acts, a priori: under a fixed sensing budget a $c\times$-inflated certificate provably needs $c\times$ the budget, and the equivariant certificate meets a budget its inflated dense counterpart cannot -- with zero calibration data. The same read-out, unchanged, audits public pretrained world models training-free: TD-MPC2 checkpoints land on the certificate's own scope taxonomy -- calibrated where strongly expansive (ratio 0.94-1.02), optimistic where weakly expansive, correctly abstaining where contracting -- a map a deployed monitor replicates cell-by-cell, out-of-sample. Across the official 1M-317M multitask ladder, calibration does not improve with parameters. On V-JEPA 2-AC (1B, real robot data) the measured cross-check correctly overrides an over-promising tangent spectrum -- the cross-validated audit, not the raw number, is the deployable object. Scale buys interpolation, not a calibrated horizon.

In this paper, we present an Intelligent Perception-Assisted Light Modulation (IPALM) technique, for femtosecond laser nanofabrication and particle manipulation. IPALM technique integrates real-time hand-motion recognition with dynamic spatial light modulation to achieve programming-free laser beam control. In contrast to the conventional programmed laser fabrication techniques which need setup a project prior to fabrication, IPALM offers a direct "mind-to-matter" pathway for laser nanostructuring and biological cells handling with high flexibility and multiple degree of freedom. In nanofabrication, IPALM provides high resolution with feature dimensions down to 280 nm. By mind-driven hand gesture control, the laser beam is regulated to enable direct writing of micro/nanostructures with a minimum feature size down to 280 nm via IPALM. In precise particle manipulation, multiple cells can be simultaneously moved to achieve cell coalescence. With these examples, IPALM showcases its potential for applications in photonics, biomedicine, and microfluidics, for high-dimension and flexible laser applications.

Cooperation in multi-agent systems is typically optimized through utilitarian objectives that maximize overall efficiency but fail to account for reward distribution, often resulting in inequitable "leader-follower" dynamics. While fairness-based approaches encourage pro-social behaviors where every agent benefits from cooperation, many current algorithms - including those utilizing reward shaping - break the stationarity of Markov Games or lack rigorous theoretical guarantees. This creates a critical gap between fair objective methods and theoretically safe learning frameworks. We propose a novel framework that bridges $α$-fairness with Heterogeneous-Agent Trust Region Learning (HATRL), ensuring monotonic improvement and convergence toward Nash Equilibria. Our approach leverages a fair advantage function that dynamically weights agent utilities based on their expected returns, allowing the global objective to transition from purely utilitarian efficiency to $α$-fairness welfare based on the parameter $α$. We introduce two practical algorithms, $α$-fair HATRPO and $α$-fair HAPPO, and demonstrate through experiments in sequential social dilemmas like CleanUp and CommonHarvest that they perform better than HATRL's algorithms from a utilitarian point of view while achieving socially higher outcomes.

Pretrained-feature world models provide a useful substrate for robot imagination, but visual or latent prediction alone does not determine whether an imagined future satisfies task-relevant events. Long-horizon manipulation requires progress signals that are relational, predicate-level, and physically grounded: whether an object has moved, whether a drawer or contact state has changed, whether a placement predicate is satisfied, and whether a candidate future is reliable enough for execution. We introduce EA-WM, an event-aware world-model framework that augments frozen visual-feature dynamics with task-specification-grounded event prediction and verification. EA-WM rolls out candidate futures in pretrained visual-feature space, decodes them into structured event states, and scores them using task-progress, semantic-consistency, physical-feasibility, and uncertainty terms. The verifier guides sampling-based planning, gates candidate actions, and, in the contact-sensitive LIBERO wine-rack setting, selects among PPOgenerated proposals. Across navigation, deformable-object, wall-constrained, and languagedescribed manipulation studies, EA-WM shows that event-aware verification can make featurespace world models more interpretable and better aligned with task progress.

Quadruped robots are capable of traversing a wide range of complex terrains with high flexibility. As highly mobile ground-based intelligent platforms, they can be equipped with modules for navigation control, environmental perception, and intelligent interaction, thereby serving as real-world mobile deployment platforms for various algorithms. In this paper, we introduce Y-BotFrame, an extensible embodied platform that turns a robot into an intelligent ground assistant. Y-BotFrame integrates multimodal perception capabilities, including speech, vision, and LiDAR, and employs a large language model as the cognitive core for environmental understanding, contextual reasoning, and task planning. The system maps user natural-language instructions into executable embodied task units that can be carried out by the robot. Y-BotFrame supports natural interaction through voice commands and visual feedback, removing the need for a remote controller and enabling efficient human-robot collaboration. With a highly extensible framework, Y-BotFrame supports plug-and-play integration of new functional modules as well as modular upgrades and iterative development, offering a reference implementation for the real-world deployment of general-purpose, instruction-driven embodied agents.The supplementary video is available at https://xdei-group.github.io/Y-BotFrame/.

This paper introduces YeasierAgent, an application-building paradigm based on symbiotic agents, narrative worlds, and scene-aware interaction. It challenges the conventional device-coupled model of software by redefining applications as collaborative spaces among users, agents, and worlds. We present a system architecture that achieves two primary contributions: (1) enabling the rapid, cross-platform construction of agent-native applications by utilizing platform-agnostic interactive units (agents, scenes, dialogue) rather than fixed graphical layouts; and (2) unifying the emotional companionship and practical tool execution attributes of intelligent agents within a single experiential sandbox. By integrating automated generation, user-created worlds, and spatial multi-agent collaboration, YeasierAgent formalizes the category of Symbiotic Agent-Native Applications, demonstrating a shift from isolated, tool-specific chatbots toward cohesive, socially embedded computational environments.

Vision-language models (VLMs) are increasingly explored as visual critics, reward generators, and failure detectors in robotic manipulation. These roles implicitly require models to judge not only final task success, but also how a manipulation execution is physically and temporally progressing. However, existing evaluations fail to test whether VLMs possess fine-grained process understanding. To address this gap, we present RoboProcessBench, a benchmark for process-aware understanding in vision-language robotic manipulation. RoboProcessBench decomposes such capability into two complementary dimensions, \emph{static monitoring} and \emph{dynamic reasoning}, instantiated as 12 diagnostic question families covering phase, contact, motion, coordination, primitive-local progress, temporal order, outcome, and primitive-level transitions. Built from physically grounded execution traces, the curated benchmark corpus ProcessData contains \textasciitilde 58k question-answer pairs across 260 manipulation tasks, which is further split into ProcessData-SFT and ProcessData-Eval for post-training and evaluation purposes. Extensive evaluation of various VLMs on ProcessData-Eval reveals broad limitations across 12 diagnostic task families, suggesting current models still lack robust process-aware understanding of manipulation executions. But with ProcessData-SFT, the post-trained \textit{Qwen2.5-VL-7B} and \textit{InternVL-3-8B} exhibit consistent gains on local state, motion, progress, and primitive-aware cues. These results demonstrate that RoboProcessBench serves as both an evaluation benchmark and a learnable supervision source for developing VLMs capable of monitoring and evaluating robotic manipulation processes. Project webpage: \href{https://processbench-2026.github.io/RoboProcessBench-Web/}{https://processbench-2026.github.io}.

Depth estimation has numerous medical and surgical applications. We benchmark four depth sensors on a porcine bone specimen, a porcine belly specimen, and a silicone kidney phantom using stylus-sampled references. These objects contain several real-world challenges, including homogeneous surfaces, specular surfaces, and subsurface scattering. The comparison includes stereo, structured-light, and time-of-flight sensors at a distance of approximately 50 cm. Specifically, the Intel RealSense D405 (Intel RealSense, United States), PMD Flexx2 (pmdtechnologies, Germany), Stereolabs ZED 2i (Stereolabs, France), and Zivid 2M+ 60 (Zivid, Norway) are compared. The Zivid 2M+ 60 performed best across all objects and metrics considered in this work. The ZED ranked second for real tissue, but last on the phantom.

Prevailing wisdom posits that Multi-Agent Systems (MAS) are superior to Single-Agent Systems (SAS), citing advantages like context protection, parallel processing and distributed decision-making. However, empirical support for this claim relies primarily on comparisons with SAS baselines using benchmarks that prioritize isolated reasoning tasks, which do not adequately assess these advantages. Focusing on automatically generated MAS that are designed for enhanced generalizability over manually-designed counterparts, we perform a rigorous, systematic evaluation against SAS, specifically Chain-of-Thought with Self-Consistency (CoT-SC). Across traditional reasoning datasets and tasks with interactive multi-step workflows (e.g., BrowseComp-Plus), we demonstrate that automatic MAS consistently underperform CoT-SC despite being up to 10x more expensive. To isolate these failures from limitations inherent to task structure, we introduce a diagnostic synthetic dataset tailored for MAS featuring explicit task decomposition, context separation and parallelization potential. We show that expert-architected MAS consistently outperforms automatically generated architectures in both raw performance and cost-efficiency on this dataset, demonstrating that existing evaluation frameworks mask critical architectural gaps and inefficiencies of complex MAS by failing to account for the marginal utility of increased computational cost. Critically, systematic deconstruction of the generated MAS architectures reveals that current automated design paradigms produce architectural bloat that prioritizes superficial complexity which does not translate into functional utility, exposing a fundamental misalignment with multi-agent principles.

Humanoid-Object Interaction (HOI) is a fundamental capability for humanoid robots, yet it remains challenging due to the tight coupling between dynamic balance and stable interaction with diverse objects. Existing methods often require time-consuming task-specific policy training or rely on rigid trajectory replay, which limits their ability to accommodate novel interaction scenarios. In this work, we present \textit{GenHOI}, a simple yet effective framework that enables humanoid robots to perform diverse object-interaction tasks in a zero-shot manner by directly imitating a single generated video, without task-specific training or physical demonstration data. GenHOI first reconstructs the robot-object scene in simulation and renders a first-frame image, which, together with the language command, conditions the synthesis of a task-oriented interaction video. The generated video is then analyzed to identify interaction-relevant contact events and estimate hand-object contact regions, which are encoded as object-centric geometric constraints that convert visual interaction cues into physically grounded optimization priors. Guided by these priors, the reference motion recovered from the video is refined and smoothed to resolve the scale ambiguity inherent in 2D video generation, while adapting a single reference trajectory to unseen robot-object relative poses. The optimized trajectory is finally executed by a closed-loop tracking controller. We validate the proposed framework in extensive simulation and real-world experiments across diverse object-interaction tasks, including box grasping, asymmetric bimanual chair carrying, table lifting from below, and cylindrical-object enveloping.

Action-conditioned world models let an autonomous vehicle predict future camera scenes from its own planned controls, enabling planning and simulation without real-world rollouts, but at compact, trainable scale the futures are ambiguous and the field's standard distortion metrics actively mislead: they reward a blurry regression mean over a realistic prediction. We confront this with a compact latent world model that, given the present front-camera latent and a sequence of ego-actions, predicts future scene latents a frozen decoder renders to $256 \times 256$ frames up to 8 seconds ahead, evaluated on 150 held-out nuScenes scenes. We first benchmark where to predict: across six frozen encoders spanning four representation families, V-JEPA2 with temporal context reduces steering RMSE by 40% over the best single-frame encoder. We then train a latent Diffusion Transformer (DiT) and, through a controlled diagnosis, identify the four ingredients it needs: spatial tokens, the $x_0$ objective, residual anchoring, and sampling matched to target uncertainty. In a Stable-Diffusion-VAE encode-predict-decode pipeline we expose the central tension: distortion metrics (cosine similarity, SSIM) favor the blurry mean, masking that the diffusion model is far closer to the real frame distribution. Inception-based FID and KID reveal a clean perception-distortion frontier: diffusion attains KID 0.078 versus 0.375 for regression ($4.8\times$ better), and a deployable train-derived calibration makes this practical without test-time ground truth. The model is genuinely action-controllable (steering drives scene displacement, Spearman $ρ= 0.81$, vs $-0.18$ for regression). We trace limited single-pass motion to a shared-present anchor and engineer a compact 1.7M-parameter "jump" model that recovers full ground-truth motion magnitude ($1.02\times$ GT), where single-pass models capture less than half.

Vision-language-action (VLA) policies bring natural language into closed-loop robot control, enabling robots to execute manipulation tasks directly from text instructions. The same interface gives text a recurring role in control because the prompt is reused at every replanning step, and each prompt-conditioned action changes the future observations on which the policy acts. Existing VLA attacks study adversarial prompts that elicit targeted low-level actions or make such actions persist across changing images. We identify a stronger trajectory-level failure mode: a prompt that still $\textit{appears}$ to specify the intended task but redirects the final physical outcome. We mathematically formalize this setting as $\textit{command-preserving trajectory redirection}$, a prompt-only threat model in which the attacker chooses one prompt before the episode, all policy and environment components remain fixed, and the prompt must stay close to the benign instruction while omitting target words and correction language. To find such prompts, we introduce an on-policy prompt search method that uses rollouts to discover perturbations whose closed-loop behavior tracks a target task while satisfying the command-preserving constraints. Experiments in simulation and on hardware show that near-benign prompt perturbations can redirect VLA rollouts to attacker-specified targets. These results expose a trajectory-level vulnerability in VLA instruction grounding: text that appears to preserve the intended command can still give an adversary control over the robot's final physical outcome. Project website: https://vla-redirection-attack.github.io/

Long-horizon robot mobile manipulation requires continual reasoning about localization, environment changes, and task progress, all of which are challenging to infer from image observations alone. In this paper, we show that conditioning a mobile manipulation policy on a spatiotemporal feature map improves reasoning over long horizons. The map represents the environment and the articulated robot body as neural points in a shared latent space and is updated online from egocentric observations and proprioceptive state. We update the environment neural points using object-level rigid tracking and the robot neural points using forward kinematics. We use our spatiotemporal environment and robot feature (SERF) map as a state input to a vision-language-action (VLA) model by extracting map tokens from multiple reference frames and spatial scales, providing the policy with both local and global context. We demonstrate SERF on BEHAVIOR-1K, a benchmark for long-horizon mobile manipulation in household environments. Experiments show that the SERF VLA policy outperforms image-only baselines, reaches subgoals faster by following more direct trajectories, improves robustness to scene-configuration shifts, and recovers from object-drop failures.

As a long-standing challenge in robotic manipulation, stable and efficient grasping in cluttered environments is of great importance in industrial settings. While recent studies have achieved relatively high success rates in grasping from clutter, there remain few mature solutions for more demanding tasks such as sequential object search and sorting. This work addresses sequential object picking in cluttered environments based on the Cluttered Environment Picking Benchmark (CEPB) and presents our solution to the Pick-in-Clutter track of the 10th Robotic Grasping and Manipulation Competition (RGMC) at ICRA 2025. The task poses several key challenges. First, it requires robust and collision-aware grasping with high success rates across a diverse set of objects, including both rigid and deformable ones. Second, it demands efficient search for target objects, which places stringent requirements on the decluttering and searching strategies of the solution. To address the above challenges, we design an integrated hardware-software pipeline that combines object recognition, decluttering, and multi-modal grasping. The main contributions include the hardware design of a multifunctional gripper and novel representations for object distribution and occlusion relationships in cluttered space. This pipeline enables efficient recognition, search, and sequential grasping of objects in clutter, demonstrating strong performance in both laboratory tests and competition scenarios, and ultimately achieving second place in the Pick-in-Clutter track of the RGMC 2025.

Wet-lab robots can improve the reproducibility, throughput, and safety of biomedical experiments, but scaling their learning requires customizable simulators for safe and reproducible task generation, open editable laboratory assets, and efficient pipelines that turn limited demonstrations into usable training data. We present Pipette, an embodied simulation platform, benchmark, and data-efficient augmentation framework for wet-lab robot learning. Pipette releases over 43 open-source and re-editable wet-lab assets, together with an extensible asset-building pipeline. A key component of Pipette is its simulation-based data augmentation pipeline, replaying human demonstrations in simulation, applies lighting, camera, speed, and action perturbations, and filters generated episodes with automatic task success checks, rapidly expanding usable training data from limited manual demonstrations. We further introduce an 11-task wet-lab embodied benchmark covering sample handling, culture-ware manipulation, device operation, and precision placement. With only 30 demonstrations per task, ACT achieves 65.5% average success rate, while simulation augmentation improves SmolVLA from 44.1% to 74.7% and π0 from 40.4% to 46.5%, validating the effectiveness of Pipette for data-efficient VLA training and evaluation. Pipette also supports natural-language-driven scene construction and task registration, lowering the barrier for non-expert users to define new wet-lab robotic tasks.

For robotics to be effectively integrated into household or industrial environments, machines must adapt to natural-language prompts in real time. Although Vision-Language Models (VLMs) have enabled zero-shot generalization in robot task and motion planning (TAMP), current state-of-the-art approaches often remain computationally "heavyweight" or require extensive training on thousands of demonstrations. We present GRASP (Grounded Reasoning and Symbolic Planning), a framework designed as a step toward open-vocabulary tabletop manipulation. Our approach leverages a pretrained VLM to translate natural-language queries into neuro-symbolic goal states, grounded in the physical world via a bounding-box detection pipeline. Unlike methods that rely on fixed color lists or hard-coded coordinates, GRASP enables robots to interpret abstract spatial concepts such as "top shelf" and execute tasks without additional fine-tuning. We achieve 73.3% overall success across 90 real-robot trials at three difficulty levels, requiring no task-specific training.

Aerial manipulation systems have long suffered from representation coupling in end-to-end control, as platform-level Unmanned Aerial Vehicle (UAV) movement and end-effector-level arm manipulation differ substantially in action scale, dynamics, and control objectives. In this paper, we propose AIR-VLA+, a flow matching action generation architecture specifically designed for aerial manipulation, featuring cascaded dual-action decoders and an asymmetric feature-level Mixture of Experts (MoE). We construct cascaded manipulation and movement decoders, allowing the UAV to unidirectionally observe the manipulator's intent during movement to achieve workflow coordination, while isolating the impact of UAV movement information backpropagation on arm manipulation stability. Addressing the characteristic that UAV movement is highly dependent on high-level semantics and responsible for task state transitions in aerial manipulation, we design an input feature enhancement module for the UAV movement decoder. This module introduces an implicit visual grasp projector to perceive the interaction state between the gripper and the object, and injects compressed global semantic features. Within the UAV movement decoder, we deploy an implicit MoE architecture, enabling different movement experts to spontaneously exhibit capacity inclinations for various task stages during training. Through dense soft blending computation on the feature manifold, the UAV movement is endowed with stronger task-stage adaptability. Experiments on the standardized AIR-VLA benchmark demonstrate that our method comprehensively surpasses all baselines with an overall average score of 48.0. The overall task completion score improves by 80.2\% compared to the single-head $π_{0.5}$ policy, effectively mitigating the heterogeneous coordinated control conflicts of composite robots.

Semantic mapping is a core service that enables grounded interactions in emerging Extended Reality (XR) applications such as AI assistants and spatial object search. Deploying this capability on mobile XR devices requires a system that is open-vocabulary, real-time, and low-power. Existing approaches are compute-intensive and assume server-class resources. Cloud offloading offers a practical path, but no existing system splits semantic mapping across the device-cloud boundary or manages its communication, execution, and memory footprint. We present SemanticXR, the first device-cloud system for real-time, open-vocabulary semantic mapping and querying under XR power, bandwidth, and memory constraints. Our key insight is to elevate semantically identifiable objects to first-class units of communication, execution, and memory across the device and server. On the server, object-level parallelism and geometry downsampling improve mapping latency, while object-level depth-mapping co-design reduces upstream bandwidth. On the device, an object-level sparse local map with incremental updates and update prioritization enables network-robust querying with bounded memory and downstream bandwidth. Object-level configurable resource usage vs. quality trade-offs let applications and the system adapt mapping to application requirements and operating conditions, respectively. Against a device-cloud baseline with the same perception models, object-level organization improves server-side mapping latency by 2.2X at equal semantic quality. Depth-mapping co-design maintains upstream bandwidth under 2.5 Mbps. On the device, SemanticXR sustains sub-100 ms query latency for up to 10,000 objects even under network drops, supports tens of thousands of objects within 500 MB, and scales downstream bandwidth with map changes, not total scene size. The system adds only 2% device power during normal operation.

The rapid emergence of autonomous AI agents is transforming artificial intelligence from isolated model inference into distributed systems of reasoning, communication, and action. This paper develops the vision of the Internet of Agentic AI (IoAI): an open ecosystem in which heterogeneous agents discover one another, negotiate responsibilities, exchange context, invoke tools, and execute workflows across cloud, edge, device, organizational, and cyber-physical environments. We synthesize foundations from single-agent agentic AI, multi-agent systems, distributed computing, communication networks, game theory, and security engineering to characterize the architectures and mechanisms required for scalable agent ecosystems. The paper examines agent deployment models, workflow lifecycles, communication protocols, interoperability layers, resource-management challenges, and trust architectures, with case studies in adaptive manufacturing and distributed operational coordination. The resulting framework highlights the central research challenges of controlled emergence, semantic interoperability, secure identity, incentive-compatible coordination, resource-aware orchestration, and governance for large-scale networks of autonomous agents.

Recent reinforcement learning approaches have shown great promise in improving humanoid motion tracking performance and achieving fall recovery under disturbances. However, most existing works treat motion tracking and fall recovery as different tasks and require multi-stage training with specialized recovery rewards and/or separate recovery policies. Moreover, existing reinforcement learning-based methods often terminate training episodes immediately after severe tracking failures, limiting recovery-oriented exploration in unstable or fallen states. To address the above issues, we propose Stubborn, a streamlined and unified reinforcement learning framework to achieve robust humanoid motion tracking and fall recovery. Specifically, Stubborn uses an asymmetric Actor-Critic architecture and consists of three major components. First, a yaw-aligned tracking representation is adopted to reduce sensitivity to global drift and heading disturbances while preserving gravity-related balance information. Second, we introduce a Bernoulli-based probabilistic termination mechanism that enables the policy to encourage exploration of fall-recovery behaviors under varying failure modes. Third, we propose a probabilistic termination and tracking-error-driven strategy that dynamically reshapes the sampling distribution based on tracking performance, increasing the training efficiency for difficult motion segments and unstable states. Extensive comparisons with SOTA methods and ablation studies show that Stubborn achieved competitive performance, and the proposed probabilistic termination mechanism and adaptive sampling strategy contributed to the performance and robustness gains. For real-world demonstrations, please refer to https://aislab-sustech.github.io/Stubborn/.

As the EU Carbon Border Adjustment Mechanism (CBAM) approaches, the global semiconductor value chain faces growing structural tensions between regulatory transparency and data sovereignty. This article proposes a RegTech reference architecture using the International Data Spaces (IDSA) framework to orchestrate trustworthy environmental telemetry across the semiconductor-petrochemical nexus. The framework distinguishes the mandatory CBAM requirements from voluntary Science Based Targets initiative (SBTi) frameworks, while addressing the additive complexities of the Safe-and-Sustainable-by-Design (SSbD) framework. Moving beyond standard linear technology stacks, we introduce a prospective roadmapping methodology that transforms upstream physical vulnerabilities into circular, negative feedback loops. Focusing on the Taipei and Penang technology corridor, the article details how sovereign data exchange enables Digital Product Passports (DPPs) to drive Global Business Services (GBSs) capability demands. Finally, we discuss the integration of Agentic AI for autonomous compliance and FinTech green financing, providing a scalable blueprint for global industrial clusters to achieve sovereign, sustainable, and transparent value chains.

While MPC effectively handles structured, diverse, and low-level specifications, it lacks the capability to dynamically incorporate high-level contextual information such as social norms, user intent, or natural language instructions. To address this limitation, this manuscript introduces an agentic MPC framework that enables context-aware, semantically adaptive control synthesis by integrating with large language model-based agents. The agent interprets heterogeneous inputs, including natural language messages, environmental observations, and external knowledge, to resynthesize the control specifications. The effectiveness of the framework is demonstrated in an autonomous driving scenario, where the system aligns with personal preferences or responds to social situations such as emergency vehicle yielding.

Explicit 3D representations are attractive for manipulation because they expose object shape, workspace geometry, and robot-object relations in metric coordinates. However, sparse 3D encoders are often learned through downstream task objectives, tying the representation to a particular data distribution, policy architecture, and action parameterization. We introduce Sparse2Act, an observation-action alignment framework for pretraining sparse point-cloud encoders. The key idea is to use task-space end-effector actions as geometric supervision: masked sparse 3D tokens are trained to organize scene features around the workspace motion paired with the observation. After pretraining, only the encoder initialization is reused by downstream policies, allowing them to retain their own architectures and action spaces, including joint-space commands. On the LIBERO-10 benchmark, our method achieves 86.9% average success after 500 fine-tuning steps. The same pretrained encoder supports LIBERO-to-Meta-World cross-domain transfer, achieving 73.4% average success on the Meta-World-5 benchmark. Ablations on the objective and decoder capacity show that the gains come from the masked action-alignment signal and remain useful across downstream action decoders. In real-world experiments, simulation pretraining followed by limited real-data fine-tuning achieves an average success rate of 72.5% across four tasks, demonstrating effective sim-to-real transfer. These results suggest that robot actions can provide compact geometric supervision for reusable sparse 3D representations.

Most learned dexterous grasp generators relegate contact forces to a downstream verification step, so a kinematically-plausible pose can still violate the conditions for a stable physical grasp. We address this with EquiDexFlow, an SE(3)-equivariant flow-matching model that jointly predicts wrist pose, joint angles, fingertip contacts, surface normals, and contact forces from an object point cloud. Our architecture projects contacts onto the object surface and forces into the Coulomb friction cone by construction, so placement and friction compliance hold without loss penalties. We prove end-to-end SE(3) equivariance and verify it empirically over 200 rotations, with wrist residuals below $0.04^\circ$ and exactly zero joint deviation. Trained on 8,100 force-closure grasps across 81 objects for the 16-DoF Allegro Hand, our model achieves zero friction violations, the best composite score, and the lowest wrench residual among all ablation variants. We retarget decoded fingertip contacts to a 16-DoF LEAP Hand via per-finger inverse kinematics, and our hardware-feasible refinement places every joint at least 5% inside its actuator envelope while preserving wrench balance. On the physical robot, retargeted EquiDexFlow-decoded grasps complete open-loop pick-and-hold trials on all six test objects, with every asymmetric object succeeding at both the canonical pose and a $120^\circ$ co-rotation. Videos, code, and checkpoints are available at https://equidexflow.github.io.

As LLM-based multi-agent systems (MAS) are deployed in the wild, the resilience of their collaboration structures against adversarial compromise becomes a critical safety concern. Attackers may leverage prompt-injection or jailbreaking to sabotage individual agents within MAS workflows, but the interaction between model scaling and system-level resilience remains poorly understood. This paper investigates how model scale affects the security of linear multi-agent workflows. Our experiments across scales of two open-weight model families on the HumanEval benchmark reveal a compliance-correction symmetry: larger models are far more likely to faithfully execute malicious instructions, with the control-to-malicious performance drop reaching 53.7pp at 27B in uncorrected pipelines. However, appending a lightweight terminal Fixer stage collapses this to 0.6pp and restores statistical parity with control-level performance, demonstrating that strictly linear collaboration structures can be viable and resilient to adversaries at this scale, and suggesting that the brittleness previously attributed to linear topology may stem from a lack of correction.

The best agent on WorkBench in March 2024, GPT-4, completed 43% of tasks and took an unintended harmful action, such as emailing the wrong person, on 26% of them. We re-visit the benchmark in June 2026 and find that the best agent to date, Claude Opus 4.8, completes 89% and takes an unintended harmful action on 2.5%. Aside from this considerable progress in frontier agent performance, three things stand out. First, capability and safety go together on WorkBench rather than trade off, so the models that finish the most tasks also do the least unintended damage. Second, while several classes of error have been totally eliminated, frontier models still make some basic mistakes that occasionally result in irreversible harm, such as sending an email to the wrong person. Third, the rise of open-weight models has drastically lowered costs for a performance level that was previously only accessible to proprietary models, while frontier costs have stayed relatively stable. We release an updated version of the benchmark with data and code quality improvements, new model scores, and analysis of agent progress on WorkBench since 2024.