Physical AI Brief

This paper studies the next major bottleneck in agentic AI as system scaling, not only model scaling: the design of auditable, persistent, modular, and verifiable architectures around foundation models. We refer to this shift as scaling the harness: treating the structured execution layer around a foundation model as a first-class object of design, evaluation, and optimization. Although recent large language models enable agents to use tools, retrieve information, maintain memory, and execute long-horizon workflows, evaluation remains largely model-centric, often reducing agents to final-task success while treating memory, retrieval, tool use, orchestration, verification, and governance as secondary implementation details. This framing is increasingly inadequate because agent performance emerges from the interaction among the foundation model, memory substrate, context constructor, skill-routing layer, orchestration loop, and verification-and-governance layer. Together, these components form the agent harness, which translates model capability into long-horizon agent behavior. We study scaling the harness through three core bottlenecks: context governance, trustworthy memory, and dynamic skill routing, together with the orchestration and governance mechanisms that coordinate and constrain them. We further outline a research agenda for harness-level benchmarks that go beyond one-shot task success to measure trajectory quality, memory hygiene, context efficiency, communication fidelity, verification cost, and safe evolution over time. To make the discussion concrete, we develop CheetahClaws: https://github.com/SafeRL-Lab/cheetahclaws, a Python-native reference harness, and compare it with Claude Code and OpenClaw. Our main claim is that future progress in agentic AI will depend as much on system design as on stronger foundation models.

Masked diffusion models (MDMs) have emerged as a promising alternative to autoregressive models for language modeling, yet the effective design of transformer architectures for MDMs remains underexplored. In this paper, we show that selectively looping the early-middle transformer layers significantly improves both training efficiency and model performance in MDMs. We call this approach LoopMDM(Looped Masked Diffusion Model), which brings two key benefits: looping layers at training-time yields a depth-scaling effect without adding parameters, while varying the number of loops at inference-time enables flexible compute scaling. Despite the simplicity, the results are striking: across multiple pre-training corpora, LoopMDM matches the performance of same-size MDMs with up to 3.3 fewer training FLOPs, while its final performance outperforms them on various reasoning benchmarks, including up to 8.5 points on GSM8K. It even surpasses deeper non-looped MDMs trained with comparable per-step compute, indicating that selective looping is more effective than naive depth scaling. Furthermore, LoopMDM can scale inference-time compute by increasing the number of loops. Adaptively adjusting the number of loops throughout the sampling process further yields additional gains in compute efficiency while maintaining performance. Lastly, with attention analysis, we provide evidence that looping is effective in MDMs by promoting interactions among masked positions. Our code and weights will be publicly released.

The deployment of Large Language Models (LLMs) and Vision Transformers (ViTs) on edge devices is significantly constrained by memory limitations and the critical timing bottlenecks introduced by dense Multiply-Accumulate (MAC) arrays. In the ultra-low bit regime, logarithmic Power-of-Two (PoT) quantization provides a hardware-efficient alternative by replacing MAC operations with bit-shifts. However, the non-uniform exponential lattice is inherently limited by a \textbf{Low Angular Resolution Regime}, a structural flaw that becomes particularly pronounced at sub-4-bit thresholds, leading to a notable degradation of high-dimensional feature manifolds. To address this geometric limitation, we propose Orthogonal Residual Projection (ORP), an algorithm-hardware co-design framework. By formulating quantization as a dual-basis geometric projection, ORP adaptively synthesizes a higher-resolution residual lattice using strictly shift-and-add operations. Furthermore, ORP's analytical solver offers a practical alternative to computationally intensive gradient-based optimization, reducing the full-model calibration time for LLaMA-2-7B to approximately \textbf{15 minutes}. Extensive evaluations demonstrate ORP's applicability across modalities and its hardware efficiency. Under the 3-bit (W3/A16) constraint, ORP achieves a perplexity of 6.10 on LLaMA-2-7B, comparing favorably to conventional MAC-intensive baselines like AWQ without relying on asymmetric scaling, while maintaining competitive accuracy in 4-bit scenarios. At the silicon level, standard-cell RTL synthesis at a 28nm node indicates that ORP effectively mitigates the timing bottlenecks associated with dense multiplier trees.

Frontier LLMs now perform strongly across a wide range of physics evaluations, but it is hard to disentangle genuine reasoning from recall of established science. We introduce DiscoverPhysics, an interactive benchmark that asks a LLM agent to discover the laws of motion of a simulated world whose physics deliberately deviates from our own. We construct 22 worlds governed by, among others, screened and fractional-power gravity, multi-species couplings, hidden dark-matter-like particles, non-coordinate-free physics, and time-varying interactions. Each world is generated on demand by an N-body simulator, for which the agent proposes several rounds of experiments, observes raw trajectory data, and ultimately submits both a natural-language explanation of the world's physics and a Python implementation of the inferred law. Because solving a world requires the agent to design informative experiments and revise its hypotheses, the benchmark probes long-horizon reasoning over an experimental history. We evaluate submissions along two complementary axes: trajectory MSE on held-out particles and an LLM-judged explanation score following an expert-written rubric assessing conceptual understanding of each world. Across eleven frontier models, we find that the strongest agents pass only half of the worlds and consistently fail on those where latent structure must be uncovered. Open-source models lag substantially behind commercial models, both in their ability to design informative experiments and in extracting conclusions from the data. We further find that good predictive accuracy does not guarantee high explanation quality and that conceptual understanding depends on hypothesis refinement through well-chosen experiments.

Weakly supervised anomaly detection (WSAD) has developed in three primary directions: incomplete, inexact, and inaccurate supervision. However, these directions remain isolated, lacking a unified framework to assess whether they address unique challenges or share fundamental mechanics. This paper introduces WSADBench, the first benchmark that unifies evaluation across distinct weakly supervised scenarios, benchmarking diverse approaches from specialized WSAD methods to advanced tabular foundation models. WSADBench establishes standardized protocols to evaluate 36 algorithms across 4 modalities by systematically varying label quantity, granularity, and quality, revealing the performance boundaries of various methods. Based on over 700K experiments, WSADBench reveals four critical insights: (i) Strong intrinsic correlations exist between these weak supervision scenarios, challenging the isolation of current research directions. (ii) Specialized WSAD algorithms excel only in extreme label-scarcity regimes but are quickly dominated by tabular foundation models and general classification methods as supervision increases or in OOD scenarios. (iii) Unlabeled data shows inconsistent utility across settings, with marginal gains compared to label refinement. (iv) Models exhibit asymmetric sensitivity to different types of label noise. We release WSADBench as an open-source benchmark with code and datasets to facilitate future WSAD research: https://github.com/SUFE-AILAB/WSADBench.

Urban representation learning encodes complex urban environments into general-purpose embeddings for diverse downstream tasks and emerging urban foundation models. However, current evaluations are limited, typically focusing on one or two cities and tasks and relying on random splits that introduce spatial leakage, leading to inflated performance and weak support for cross-location generalization and fair comparison. To address this, we propose CityRep, a unified benchmark that evaluates urban representations across data modalities, cities, and tasks using spatially structured splits. CityRep consists of three key components: (1) a spatial unit-agnostic evaluation framework that supports heterogeneous urban representations through a standardized alignment module; (2) a unified evaluation protocol using block-based spatial splits to mitigate spatial leakage and enable rigorous model comparison; and (3) an extensible multi-city, multi-task benchmark suite spanning 8 cities and 8 tasks across regression, classification, and distribution prediction. We evaluate 11 representative urban representation models. Results show that performance is highly sensitive to the split protocol, with random splits inflating scores and altering model rankings. We also observe substantial variability across cities and tasks, underscoring the need for generalization-aware evaluation. CityRep is released as a reproducible benchmark with datasets, evaluation pipelines, and diagnostic tools to facilitate fair comparison and support future research in urban representation learning towards urban foundation models.

Length generalization remains a persistent challenge for neural networks: recurrent models tend to suffer from positional biases, while transformers are constrained by fixed computational depth. Regular languages provide a frequently used testbed for evaluating length generalization, as label prediction can be checked for any sequence length. We propose MLP-LDRU, a type of Log-Depth Recurrent Unit, which captures a class of associativity-biased operators designed to approximate recurrence through parallel reduction. We evaluate MLP-LDRU on 21 regular-language tasks, consisting of standard benchmarks and new prefix languages, where it achieves 100% out-of-distribution accuracy on 18 tasks and at least 99.9% on the remaining 3 when increasing max training length, outperforming comparable recurrent and attention-based models. We further evaluate MLP-LDRU beyond regular languages on ListOps and NLP classification benchmarks, where it performs competitively.

Online Terms of Service often function as contracts of adhesion, creating asymmetries that may expose consumers to potentially abusive clauses. In Chile, assessing such clauses is legally challenging because some provisions clearly violate mandatory consumer law, whereas others depend on broader standards such as good faith and contractual imbalance. We present a retrieval-augmented generation framework for the automated detection and classification of potentially abusive clauses in Chilean Terms of Service. Designed for local execution, it combines efficient clause detection, hybrid dense--sparse retrieval, reranking, and prompt augmentation to support medium-sized open-weight language models. We also introduce the Chilean Abusive Terms of Service Extended corpus, comprising 100 contracts and 10,029 annotated clauses in 24 legally grounded categories spanning illegal, dark, and gray clauses. Experiments comparing commercial and open-weight language models, fine-tuned encoders, and traditional baselines show that retrieval-augmented prompting substantially improves performance and enables local models to approach larger cloud-based systems at lower computational and token cost. The study also contributes a refined legal annotation scheme and a practical design for AI-assisted consumer contract review.

Deep reinforcement learning (RL) agents commonly rely on high-dimensional neural representations, despite growing evidence that task-relevant value and policy structure may be intrinsically low-dimensional. In this work, we present a simple yet effective representation-level prior that inserts a fixed orthonormal projection to constrain encoder features to a low-dimensional subspace, requiring no auxiliary objectives, pretraining, or changes to the underlying RL algorithm. Under a linear realizability assumption, we prove that when the bottleneck dimension exceeds the intrinsic rank of the optimal value function in feature space, the bottleneck preserves expressivity and leaves the induced gradient dynamics unchanged up to an equivalent low-dimensional parameterization. Empirically, we find that across both single and multi-task benchmarks, baseline performance is either matched or improved once the bottleneck dimension exceeds a small task-dependent threshold; in many cases, value representations can be compressed to extremely low dimensions without loss, and the minimal sufficient dimension depends far more on environment complexity than encoder width. In addition, we analyze representation geometry and find that orthogonal bottlenecks stabilize feature norms and are associated with higher effective rank. Together, these results support a representation-space interpretation of the manifold hypothesis in reinforcement learning and position orthogonal bottlenecks as a lightweight, architecture-agnostic mechanism for shaping RL representations.

Large language model (LLM) development is currently driven by large-scale empirical iteration over data mixtures, reward models, routing strategies, and evaluation pipelines. Here, we argue that many central questions in LLM development and evaluation are inherently causal: What is the effect of adding a data domain during pretraining? How do annotator preferences change when LLMs generate text in a different style? Should a prompt be routed to a larger or smaller model given inference cost constraints? In general, causal methods are well-suited to such settings where interventions change outcomes but, surprisingly, are underrepresented in LLM development. Our contribution is threefold: (1) We explain how causal methods can help develop modern LLM development and evaluation: LLM development relies heavily on logged data, which are often subject to confounding and distribution shifts; evaluation uses learned but potentially biased judges; and deployment environments are non-stationary. These conditions make purely predictive approaches fragile and create opportunities for principled identification and estimation methods from causal inference. (2) We further map opportunities for causal methods in the entire LLM development pipeline, including pretraining, alignment, routing, agentic workflows, and evaluation. (3) We discuss new research opportunities around leveraging causal methods for LLM development and evaluation. Overall, we argue that causal methods are potentially underutilized for the LLM development and evaluation pipeline, despite the fact that such methods can ensure a reliable and scientifically grounded design.

Benchmarks increasingly guide deployment, procurement and scientific screening, yet a score supports only the response it records, not necessarily the deployment action. We introduce deployment-complete benchmarking, which tests whether benchmark evidence determines a deployment action. A benchmark is complete for a claim exactly when the action is constant on each evidence fiber; mixed fibers expose missing deployment information, and completion curves quantify the evidence required to resolve ambiguity. In controlled response spaces, benchmark-channel conformal coverage of 94.98% transferred poorly to an unmeasured deployment channel (10.07%), whereas response-rank intervals achieved 94.91% coverage; even zero benchmark error certified only 45.4% of candidates at the largest residual size. Public audits revealed incompleteness, including 97.9% mixed Tox21 fibers and zero median certifiable fraction in main Matbench and JARVIS audits. In held-out replays, certify-then-acquire reduced false decisions from 1.19% to 0.027% in Tox21 and from 20.3% to 0.128% in JARVIS, while changing model choice and identifying deployment-relevant probes. Deployment-ready benchmarks should report evidence, supported actions, ambiguity and completion cost rather than scores alone.

Large language models (LLMs) face a dual challenge in creative capability evaluation: existing benchmarks (e.g., Story Cloze Test, HellaSwag) measure models' discriminative ability over narrative continuation using multiple-choice recognition paradigms, rather than directly measuring creative generation capability; rubric-based scoring and LLM-as-Judge methods rely on subjective dimension assessment or natural language model outputs, and cannot provide objective, automated scoring mechanisms. This paper proposes QUIET (Quality Understanding via Interlocked Evaluation Testing), a diagnostic benchmark for LLM creative capability based on multi-blank cascaded story cloze. QUIET sets N blanks (10-20) in a story with complete structure, with each blank accompanied by an explicit content constraint, and cascade dependency relationships between blanks -- the content filled into earlier blanks constrains the feasible solution space for later blanks. The evaluated model (or human participants) fills all blanks in open-ended generation mode; the results are scored by an information-theoretic automated scoring protocol without human grading. The scoring protocol directly operationalizes the "calibrated surprise" theoretical framework (Zou & Xu, 2026a). For each blank k, a composite score is computed: score = satisfy * (1 + lambda * surprise), where lambda = 1.0. Here, "satisfy" measures how well the blank filling satisfies the content constraint (objective logical reasoning judgment, not subjective aesthetic scoring), and "surprise" measures the degree of surprise given that the constraint is satisfied. Creative answers that do not satisfy the constraint score zero; answers that satisfy the constraint but are mediocre score low; answers that satisfy the constraint and are surprising score high.

Despite the strong reasoning capabilities of large language models (LLMs), optimizing the execution efficiency of tensor programs remains challenging due to the need for precise, composable transformation decisions. Recent LLM-guided approaches frame tensor program optimization as an iterative decision process, but existing datasets provide only end-to-end optimized program pairs using token-inefficient representations, lacking verifiable step-level supervision and interpretability. As a result, LLMs struggle to make reliable single-step decisions in large combinatorial optimization spaces. We introduce Step-TP, a post-training dataset for tensor program optimization that provides grounded, atomic, step-level supervision with structured chain-of-thought (CoT) reasoning. Step-TP forms a closed reasoning loop over intermediate program states, enabling reliable multi-step optimization rather than outcome imitation. Its design is guided by four principles: (i) a token-efficient, verifiable intermediate representation (IR) that deterministically lowers to TVM TIR; (ii) atomic and composable optimization strategies that decompose complex trajectories into interpretable single-step decisions; (iii) structured CoT supervision coupled with explicit IR-to-IR state transitions; and (iv) strategy filtering to balance coverage while preventing shortcut exploitation. The dataset and implementation are available at a GitHub link, https://github.com/LIUMENGFAN-gif/StepTP.

Neural PDE solvers have followed the scaling trajectory of vision and language, with recent foundation models reaching billions of parameters. We argue that scale is a poor substitute for architectural inductive bias in this domain: structured priors deliver outsized parameter efficiency, and the pattern of where they succeed and fail is itself informative about what they capture. We instantiate this argument in WaveLiT, an architecture combining a discrete wavelet transform for lossless multi-resolution tokenization, an augmented linear attention block, a shared-weight multiscale feature pyramid, and a wavelet-domain auxiliary loss. Bespoke 1-10M-parameter WaveLiT models compete with foundation models of 100-1000$\times$ their size across eight TheWell benchmarks, with the largest gains on wave and acoustic-dominated benchmarks where the wavelet-multiscale prior fits the dominant dynamical structure and small per-step errors do not compound geometrically under rollout. Trained jointly across all eight benchmarks, a 10M-parameter foundation variant exhibits a structured, physically interpretable transfer pattern -- strongest where the wavelet-multiscale prior matches the dynamics, weakest on chaotic advection-dominated flows. The entire pipeline trains on a single GPU. The results suggest that small-model PDE performance is shaped by architectural inductive bias rather than scale, and that the structure of a prior's failures is a useful empirical signal about its content.

Recent research in time series forecasting frequently investigates the integration of textual and visual modalities with numerical models to better navigate non-stationary environments. Despite delivering solid numerical results, existing multi-modal approaches usually encounter a dilemma: prioritizing the minimization of average errors can result in excessively smooth forecasts that overlook essential fluctuations. To resolve this limitation, we introduce STaT, an innovative multimodal architecture for Symbolic-Temporal-Textual Alignment, which seamlessly unites three synergistic modalities. Specifically, the symbolic modality converts continuous time series into discrete tokens, facilitating the accurate identification of structural patterns and turning points; the temporal modality extracts inherent sequential dependencies; and the textual modality leverages domain semantics to steer the macroscopic forecasting trends. Comprehensive evaluations on eight real-world benchmarks indicate that STaT delivers exceptional performance, enhancing conventional magnitude indicators by up to 8.9% while simultaneously decreasing shape distortion by up to 8.5%.

The effectiveness of multi-agent LLM deliberation depends not only on the agents' individual predictions, but also on how they communicate and collaborate. We study this mechanism through the lens of Friedkin-Johnsen (FJ) opinion dynamics, a tractable model for analyzing stubbornness, influence, and opinion change in multi-agent systems that captures empirically observed deliberation patterns. We show that the FJ parameters are input-dependent, turning multi-agent deliberation into a mixture of experts. This perspective implies that multi-agent systems can outperform single agents and static ensembles when routing reflects agent competence. Since competence is latent in practice, we analyze how influence is established through observable proxies: agents' self-assessed confidence, their perceived confidence, and initial alignment with other agents' views.

Predicting stock price movements during Earnings Announcements (EAs) is a significant challenge due to market noise and high-impact price discontinuities. In this study, we evaluate whether pre-announcement news sentiment, firm fundamentals, and recent market dynamics jointly predict the directional price movement of equities on EA days. We construct a multi-modal feature space combining 15 fundamental metrics, 3 price-based technical indicators and sentiment scores derived from financial news articles processed using FinBERT. We compare a Long Short-Term Memory (LSTM) network and a Transformer-based architecture against a logistic regression baseline, and further assess all models with and without sentiment features to quantify their incremental value. Our results indicate that while the LSTM demonstrates higher precision through a conservative safe-bet strategy, the Transformer model exhibits superior sensitivity in identifying volatile movements, achieving a higher macro F1-score, with ablation experiments showing a consistent benefit from incorporating news sentiment.

Vision-Language-Action (VLA) models are increasingly deployed on real robots, where each predicted action is executed and each failure carries a safety cost. They reach high success rates on clean inputs but collapse under small adversarial perturbations. A $16/255$ PGD attack on OpenVLA-7B drops LIBERO success from above $95\%$ to under $5\%$. Empirical defenses recover some robustness at a cost in clean accuracy, but the literature does not say whether the trade-off has a theoretical floor. We prove that it does. For any VLA policy with discrete actions, the sum of capability (mutual information between policy action and oracle action) and robustness (mutual information preserved under adversarial perturbation, net of trivial channel leakage) is upper-bounded by a policy-independent budget: task entropy plus adversarial channel capacity. The proof is two applications of the Data Processing Inequality plus MI non-negativity. The pixel-level bound is loose on current models ($\sim 10^3$ nats), but an encoder-specific corollary restricts the channel to the policy-relevant subspace, reducing the budget from $\sim 5{,}000$ to $\sim 31$ nats on OpenVLA; the policy already consumes $\sim 24\%$ of this tighter budget, leaving limited room for simultaneous robustness improvement. We validate the bound across $252$ closed-form Gaussian-VLA cells and $48$ OpenVLA-7B $\times$ LIBERO $\times$ PGD cells (zero violations). We propose encoder-specific slack as a normalized comparison axis for defense papers, and release all code, manifests, and results.

We study how an e-commerce firm should make real-time fulfillment decisions in a two-layer distribution network when multi-item customer orders arrive sequentially and future demand is unknown. The central managerial tension is whether to use scarce front distribution center (FDC) inventory to save current fulfillment cost or preserve that inventory for future orders that may be more valuable to serve locally. We formulate an adversarial online model with multiple FDCs, one regional distribution center (RDC), multi-unit multi-item orders, and item-specific and time-varying variable costs. Our theoretical objective is to characterize when simple, interpretable, and implementable fulfillment rules can perform nearly as well as an optimal clairvoyant planner. We develop a family of Gated Priority-based Greedy policies, derive competitive-ratio guarantees under both time-varying and time-invariant cost structures, and establish matching or near-matching lower bounds for any online algorithm. Numerical experiments show that the proposed policies perform strongly relative to generalized myopic and forecast-based benchmarks. The analysis yields managerial guidance on when local inventory should be protected, when splitting orders is worth the fixed-cost burden, and how the relative magnitudes of fixed and variable costs determine the value of more sophisticated optimization.

Recent advances in uncertainty quantification increasingly emphasise the distinction between aleatory and epistemic uncertainty in machine learning, motivating the need for more unified frameworks. However, despite much progress in producing reliable predictions, existing methods often lack rigorous guarantees when generalising beyond the training domain. We propose a conformalised imprecise inference framework for robust extrapolation, which is model-agnostic and augments predictive models with imprecision and distance awareness. The proposed approach yields imprecise predictions (probability boxes) that remain valid under distributional shift, maintaining coverage while adaptively expanding uncertainty in extrapolation regimes. Experiments on synthetic and benchmark datasets demonstrate improved robustness and reliable coverage compared to standard probabilistic approaches, particularly under limited data.

Controlling partial differential equations (PDEs) with learning-based policies remains fundamentally limited by fixed-dimensional representations: policies trained for a specific sensor, actuator, or agent configuration typically fail when the configuration changes. This limitation is particularly severe in multi-agent PDE control, where policies do not scale across population sizes without retraining. We address this challenge by introducing Cardinality Invariant Neural Operator Control (CINOC), reformulating PDE control as an operator learning problem that maps state fields to continuous control functions and trains them end-to-end through differentiable PDE solvers, yielding policies that naturally adapt to varying sensor and actuator configurations. Remarkably, CINOC policies trained on small swarms exhibit cardinality invariance, allowing for zero-shot transfer to significantly larger populations as well as robustness to partial agent failure. This scalability arises from agents sharing a common policy and coordinating through their physical environment, which produces an emergent self-normalization effect. To explain this phenomenon, we provide a theorem grounded in mean-field theory demonstrating that policy gradients computed from finite-agent systems converge to those of a continuous control limit. Empirically, we validate CINOC on tracking, stabilization, and density transport across linear, nonlinear, chaotic, and turbulent PDEs.

We study the mean-squared error of $k$-fold cross-validation as a risk estimator, with particular emphasis on how its accuracy depends on the number of folds $k$. Despite the widespread use of cross-validation, principled guidance for choosing $k$ is largely absent, mainly due to the complex dependence between fold-wise error estimates. To obtain sharp and interpretable results, we focus on the majority algorithm in binary classification, a minimal yet nontrivial empirical risk minimization procedure. We provide a fine-grained analysis of its cross-validation behavior, showing that even this simple algorithm exhibits subtle and delicate phenomena for which existing theory provides loose and even vacuous bounds. Leveraging this analysis, we introduce a minimax framework for cross-validation risk estimation and prove that no empirical risk minimization algorithm can achieve an $O(1/n)$ minimax mean-squared error when the number of folds grows with the number of samples $n$; instead, a lower bound of order $Ω(\sqrt{k}/n)$ is unavoidable. Our results reveal fundamental limitations of cross-validation as a data-reuse strategy, clarify gaps and inaccuracies in prior theoretical work, and position the majority algorithm as a natural benchmark that any tight analysis of cross-validation should be able to explain.

This paper investigates large language model (LLM) abstention learning, specifically using ternary reward, which incentivize truthfulness in large language models. This paper extends that idea by moving from a ternary reward to a Trajectory-Informed advantage reweighting, dynamically re-weights the abstention reward during Group Relative Policy Optimization (GRPO) training. The objective of this work focuses on abstention learning instead of improving truthfulness, serving as an exploration into hallucination reduction. The novelty of this paper lies in methodological innovation, advantage re-weighting, and benchmark selection. Leveraging GRPO's multiple trajectories as a natural abstention signal, this method uses a reward signal to explore knowledge boundaries and encourage consistency. By demonstrating that trajectories can be used as a confidence indicator of the policy relative to the query, they are then used to dynamically calculate the abstention advantage. AbstentionBench is used as the evaluation benchmark, as this work aims to contribute to the field of abstention learning. All datasets on the benchmark were tested against this method and various baselines. Empirical results demonstrate that TIAR achieves state-of-the-art abstention F1 scores across five of six evaluation categories, outperforming the static ternary baseline on 17 of 31 benchmark datasets while fully preserving baseline accuracy.

We develop a branched signature kernel solver for linear and nonlinear ordinary differential equations driven by a \emph{single observed trajectory} of a possibly rough forcing signal -- a setting that arises naturally in earthquake engineering, finance, biology, and structural health monitoring, where the forcing is observed exactly once and the solver must respect the underlying physical law without recourse to an ensemble of realizations. Two ingredients are new. First, a \emph{count-sampling} construction turns the single observation into a hierarchical family of $N+1$ nested training paths on which the branched signature kernel can be evaluated; this allows the signature kernel machinery, originally designed for multi-realization regression problems, to operate on a single-trajectory observation. Second, a kernel-collocation framework places the ansatz either on the highest-order derivative of the solution (with lower derivatives recovered by integrating the kernel) or on the solution itself (after $m$-fold integration of the ODE). We prove a universal approximation theorem for the branched signature kernel, leveraging the Hairer--Kelly morphism to express branched signature evaluations through geometric signatures of time-extended paths. The offline solver is extended to a streaming Test/Train/Retrain protocol with closed-form online updates in the linear case and scalar Newton steps in the nonlinear case. Numerical experiments on six benchmarks (El-Centro earthquake displacement, the Solow capital-stock model, an fBM-driven second-order ODE, a forced Duffing oscillator, a path-dependent Arias-intensity-degraded oscillator with variable coefficients, and a noisy Kuramoto phase-oscillator system) show that the branched signature-kernel solver delivers accurate, stable predictions across all regimes.

Diffusion-based multimodal large language models (dMLLMs) decode by iteratively predicting tokens at multiple masked positions in parallel. This turns each decoding step into a position-selection problem: the model must choose not only which predictions are reliable in isolation, but also which positions should be committed together as context for later decoding steps. Existing confidence-based decoding ranks masked positions independently and commits the top-K positions, largely ignoring whether the committed tokens provide complementary visual grounding. We identify a step-level limitation of this strategy in multimodal settings: high-confidence tokens selected in the same step can rely on overlapping visual grounding, introducing visual redundancy among the committed tokens and leaving less complementary visual grounding available for later decoding. To quantify this effect, we introduce the Visual Redundancy Index (VRI), which measures visual grounding overlap among tokens committed in parallel. To control this redundancy during decoding, we propose Visual-Redundancy-Controlled Decoding (VRCD), a training-free inference-time decoding method that uses token-to-image attention to prioritize visually complementary positions. Across diverse multimodal benchmarks, VRCD reduces visual redundancy and remaining-position entropy with modest runtime overhead. In longer decoding experiments, it also achieves relative accuracy gains of up to 18.8% on M^3CoT and 6.9% on MMBench over confidence-based decoding. Code will be released at https://github.com/infiniteYuanyl/VRCD.

We study a stochastic multi-armed bandit problem where an agent is granted a free exploration budget before regret accumulates, a setting not captured by the classic regret minimization or pure exploration paradigms. The goal is to design an adaptive policy that strategically explores the bandit instance in the initial free exploration phase and minimizes the cumulative regret in the subsequent phase. We formalize this regret minimization with free exploration problem and identify an interesting regime where the free exploration budget scales logarithmically with the time horizon. To quantify the amount of regret saved with high probability as a result of the availability of the free exploration phase, we introduce a novel set of policies known as $(α,β)$-probably saving policies. We propose a two-phase, probably saving algorithm, UFE-KLUCB-H, which consists of a principled free exploration policy, UFE, and a history-aware regret minimization policy KLUCB-H. Instance-dependent upper bounds on UFE-KLUCB-H are derived, showing that UFE-KLUCB-H accumulates strictly less regret than policies that do not have access to a free exploration phase. Complementarily, we derive instance-dependent lower bounds based on novel multi-instance perturbation arguments tailored to the free-exploration setting, demonstrating the near-optimality of UFE-KLUCB-H for two-valued bandits. Our upper and lower bounds reveal sharp phase transitions in the accumulated regret depending on the amount of available free exploration. Simulations are conducted to demonstrate that forced exploration and adaptivity in the algorithm lead to greater regret savings.

Efficient benchmarking techniques aim to lower the computational cost of evaluating LLMs by predicting full benchmark scores using only a subset of a benchmark's questions. By reframing this problem as an instance of multiple regression with feature selection, we find that existing efficient benchmarking methods can be greatly improved by simply using kernel ridge regression at the prediction stage. Additionally, using an information-theoretic feature-selection algorithm called minimum redundancy maximum relevance (mRMR), we can further improve upon these methods by selecting question subsets that will be maximally useful for prediction. Except in very data-poor settings, these approaches consistently achieve smaller prediction errors (in both MAE and RMSE), and greater ranking correlation between predicted and true scores (in both Spearman $ρ$ and Kendall $τ$) across a range of benchmarks using both binary and continuous metrics. Furthermore, mRMR subsampling is much faster than competitor methods (which often involve fitting probabilistic models or running clustering algorithms), and is more likely to select the same questions under different random seeds or training data splits. Tutorial code can be found at https://github.com/sambowyer/mrmr_eval .

Multi-domain graph pre-training is a crucial step in constructing foundational graph models with cross-domain generalization capabilities. However, existing methods predominantly rely on jointly training all source domain graphs, resulting in high computational costs. Furthermore, it remains unclear whether all source domain graph data contribute equally to effective transfer. This paper empirically reveals significant data redundancy in multi-domain graph pre-training. Based on this finding, we propose the Multi-domain Graph Pre-training Framework, MDGMIX, which combines boundary-aware subgraph mixing with hierarchical discrimination. By selecting boundary nodes to construct challenging mixed-domain subgraphs, MDGMIX employs coarse-grained domain discrimination and fine-grained domain decomposition losses to decouple shared patterns from domain-specific patterns. During adaptation, MDGMIX employs a lightweight prompt weighting mechanism to transfer source domain knowledge. Extensive experiments demonstrate that MDGMIX consistently outperforms strong baselines in few-shot classification tasks while exhibiting superior time and memory efficiency. The code is available at: https://github.com/zhengziyu77/MDGMIX.

Concept unlearning aims to erase a target concept from a pretrained text-to-image diffusion model without retraining. Closed-form methods are attractive in this setting because they apply a single deterministic edit to the cross-attention weights and add no inference-time cost. Existing closed-form methods, however, represent the target concept through the text encoder's response to a few short anchor prompts that name it, and paraphrased prompts that evoke the concept without naming it consistently bypass the edit. We argue that the target should instead be represented in the cross-attention activation space. Text embeddings describe the user's prompt, while cross-attention activations describe what the model is about to render, and the latter generalize to paraphrase the anchor templates do not cover. Building on this observation, we propose PURE (Projection in U-Net Rendering for Erasure), a closed-form method that builds the forget and retain bases from per-layer cross-attention activations captured along a short denoising trajectory and applies a single linear projector to the cross-attention key and value weights. On a recent holistic concept-unlearning benchmark covering ten concepts across artistic style, intellectual property, celebrity, and NSFW categories, PURE significantly reduces target leakage under paraphrased and adversarial prompts while preserving retain concepts close to the unedited model, yielding the best overall forget-retain trade-off among evaluated methods.

In multi-stage recommender systems, reranking optimizes overall utility by capturing intra-list contextual dependencies, yet its central challenge lies in exploring optimal sequences within an exponentially large permutation space. Recent studies have shifted towards end-to-end generative frameworks, which typically leverage list-wise rewards or preference alignment to guide generator training. However, these methods still face two critical issues. First is the heuristic label bias. Existing methods often construct training targets based on simple rules, such as promoting clicked items to the top, while ignoring causal dependencies within the list context. Second is the credit assignment problem. Sparse list-level posterior rewards fail to directly guide intermediate steps in sequence generation, leading to ambiguous optimization directions. To address these issues, we propose DeGRe (Dense-supervised Generative Reranking), a generative reranking framework that bridges the gap between offline exploration and online efficiency through dense supervision. The core of DeGRe lies in its offline-online decoupled design. During the offline phase, we introduce a Lookahead Evaluator based on cumulative regression, which leverages beam search to actively mine high-value lookahead sequences in the unexposed space. During training, we transform the step-wise value estimations from the evaluator into dense supervision signals and distill them into a lightweight Online Generator. This mechanism enables the generator to internalize lookahead planning capabilities, requiring only a single efficient greedy decoding pass during online inference to approximate the global optimum. Experiments demonstrate that DeGRe outperforms baseline models on public benchmarks and industrial datasets. We have successfully deployed DeGRe on Taobao Flash Shopping, significantly improving online recommendations.

We prove that no reinforcement learning policy with confidence-gated autonomy can simultaneously achieve maximum helpfulness, optimal calibration, and full autonomy under rational oversight, whenever some tasks exceed the agent's reliable competence: the Behavioral Credibility Trilemma. The impossibility is geometric -- adding any non-affine autonomy incentive to a strictly proper scoring rule destroys strict properness, so an agent rewarded for both calibrated confidence and autonomous action systematically inflates its reported confidence on tasks below the principal's approval threshold. The Behavioral Perturbation Lemma quantifies the inflation (scaling as $w_A/(2 w_C)$ for the Brier score) and shows detection requires $Ω(1/Δ^2)$ observations. We prove the principal's optimal oversight rule is necessarily non-affine, making the impossibility unconditional and optimizer-independent across log-concave-density policy families. We formalize the Confidence-Gated Decision Problem, map existing methods onto the trilemma, and identify two constructive resolution pathways (commitment, domain separation). A 540-configuration Best-of-N experiment tests five pre-registered hypotheses, all strongly confirmed (effect sizes $d = 1.10$ to $5.32$), and adds a descriptive analysis of the achievable-$(H, C, A)$ surface geometry showing a plateau-truncated frontier consistent with the predicted inflation saturation.

Most of the world's offshore wind resource lies in waters too deep for fixed-bottom foundations, making floating offshore wind turbines (FOWTs) essential for deep-water deployment. As the industry scales toward $22$ MW class designs, tower fatigue becomes increasingly critical because larger structures amplify the coupled aero-hydro-servo-elastic loads induced by continuous wind and wave excitation. Accurate fatigue-damage prediction is therefore central to certification, design optimization, and cost reduction. Yet the field lacks a shared surrogate benchmark: studies report different simulations, splits, and metrics, making methods difficult to compare. We present FLOATBench, a public tabular benchmark with $582{,}120$ per-section fatigue-damage labels across three $22$ MW FOWT tower geometries, derived from $19{,}404$ high-fidelity OpenFAST simulations across the three towers ($6{,}468$ per tower: $1{,}078$ aligned wind/wave operating points $\times$ six turbulence seeds), labeled at $30$ cross-sections per tower. FLOATBench includes a regime-aware alpha-shape partition of the joint wind/wave operating envelope, stratifying test points into in-train, interpolation, and extrapolation regimes. It is paired with a reproducible evaluation harness covering three protocol levels: random validation (E1), within-tower regime-aware evaluation (E2), and cross-tower transfer (E3). The regime-aware protocol reveals rank shifts between global and extrapolation performance that random-split leaderboards cannot detect. To the authors' knowledge, FLOATBench is the first FOWT fatigue benchmark for tabular surrogate modeling, and offers an evaluation protocol that generalizes to engineering surrogates defined over physical operating envelopes. Dataset and code available at: https://github.com/Joao97ribeiro/FLOATBench.

Realistic physical systems are characterised by emergent interactions across multiple length and time scales, posing a significant challenge for predictive machine learning (ML) models. Most scientific ML models focus on a narrow range of interactions. While machine learning force fields (MLFFs) offer near-quantum accuracy, the ubiquitous message-passing layers miss long-range many-body effects. Here we introduce the Multiscale Structural Ensemble (MuSE), a hierarchical model that uses Soft Coarse-Graining Pooling to construct coarse representations from smooth fractional assignments of atoms to coarse nodes, enabling MLFF modules to operate across multiple scales. MuSE is architecture-agnostic and coupled with SO3krates, MACE, and PaiNN MLFFs for both molecules and materials. We demonstrate the power of MuSE through Hessian-based benchmarks, folding trajectories for biomolecules, and energy profiles in molecule-graphene nanostructures, where MuSE accurately captures quantum-mechanical interactions at relevant scales -- unlike other recent long-range ML models.

High-quality data is scarce in large language model (LLM) training, yet how to schedule its use jointly with training dynamics lacks theoretical guidance. We extend functional scaling laws by incorporating a data-quality dimension, and solve the joint data-quality and batch-size scheduling problem in asymptotic closed form. The solution reveals two regimes and a dual role of high-quality data. In the noise-limited regime, high-quality data should be used as a signal amplifier: lowering the batch size converts cleaner data into more signal without amplifying noise. In the signal-limited regime, it should be used as a noise suppressor: late placement reduces terminal noise without sacrificing signal accumulation. Existing curriculum-style pipelines primarily exploit the second role by placing cleaner data late, but miss the first role because conventional decay schedules reduce update intensity exactly when high-quality data becomes available. Guided by this, we propose Drop-Stable-Rampup for LLM midtraining: upon the quality transition, drop the batch size, hold it stable to accumulate signal, then ramp up to suppress terminal noise. On a 15B Mixture-of-Experts model midtrained on 108B tokens, Drop-Stable-Rampup improves average accuracy over Warmup-Stable-Decay (WSD) by +1.70 and over Cosine-decay by +2.98, with particularly large gains on mathematical reasoning benchmarks such as GSM8K (+4.23) and MATH (+2.80).

Graph neural networks for node classification are typically trained by gradient descent over hundreds or thousands of epochs. Recent work has shown that, when properly tuned, classic GCN/SAGE/GAT architectures can match graph transformers on many node-classification benchmarks. We ask a complementary question: how much of this performance can be recovered by deterministic closed-form solvers, and what guarantees does this enable? We introduce a routed closed-form framework selected by adjusted homophily. For assortative graphs, we use SGC-style propagation followed by Ridge regression; for heterophilous graphs, we introduce LCF-Net, a layer-wise closed-form graph feature-refinement network whose per-layer Ridge solves are capped by a Gaussian kernel-Ridge head. Across 14 benchmarks, including ogbn-arxiv and ogbn-proteins, our closed-form predictors match or beat the best vanilla 2-layer GCN/SAGE/GAT on 9 of 9 measured datasets, tie tuned deep recipes within one standard deviation on 9 of 12 small benchmarks, and exceed the OGB-leaderboard plain GCN on both large graphs. The remaining heterophilous gap closely tracks the gain from vanilla 2-layer to deep SAGE, suggesting that the residual difference is primarily architectural. Because our predictors are explicit solutions of deterministic linear systems, modified graph inputs can be re-solved to obtain retrain-equivalent parameters. We formalize exact graph-object unlearning for label, feature, edge, node, and subgraph modifications, prove K-hop locality for Ridge components, and verify exactness across 109 configurations. On ogbn-arxiv, localized updates give $21$--$45\times$ speedups over full re-solving and roughly $10^{6}\times$ speedups over gradient retraining. Structural-inversion experiments further quantify the privacy floor of exact retraining and the additional leakage of approximate graph-unlearning methods.

Accurate reconstruction of magnetic fields in inaccessible regions is vital for many high-precision experiments in physics. Traditional methods, such as spherical harmonic expansion, often suffer from truncation errors that limit their precision. This study proposes an advanced Physics-Informed Neural Network (PINN) framework for high-precision 3D magnetic field mapping. Unlike conventional data-driven models, the proposed PINN integrates Maxwell's equations directly into the loss function, enforcing divergence-free and curl-free conditions across the entire domain. A key innovation is the inclusion of explicit physics-residual losses at measurement locations, ensuring rigorous physical consistency beyond random collocation sampling. Validation using simulated data achieves a reconstruction accuracy of $10^{-4}$, a tenfold improvement over existing PINN benchmarks. Furthermore, experimental validation using a custom coil assembly demonstrates robust reconstruction with sub-percent relative accuracy, reaching the $10^{-3}$ level under ambient conditions. This AI-driven methodology provides a robust, high-precision solution for field monitoring and measurement in complex experimental environments where direct sensor placement is restricted.

Policy loss estimation remains a fundamental and long-standing challenge in reinforcement learning (RL) for diffusion language models (dLLMs). We introduce Reinforcement Learning from Denoising Feedback (RLDF), a novel training paradigm that leverages feedback obtained from rollout and training processes to facilitate accurate and efficient policy loss estimation. To balance the trade-off between computational efficiency and estimation effectiveness, RLDF optimizes the model toward the clipped clean state $\hat{x}_0$ from intermediate noisy states $x_t$, combined with weighted timestep sampling over $t$. Extensive experiments demonstrate that RLDF achieves consistent and substantial improvements in both performance and generalizability across two representative dLLM architectures, LLaDA and Dream, on multiple reasoning benchmarks. Our work lays a principled foundation for scalable reinforcement learning in diffusion language models. We build Drift, a training framework for dLLMs, available at https://github.com/ant-research/Drift.

Autonomous AI agents increasingly issue side-effect-bearing actions: database mutations, refunds, payments, external commitments. We propose the Actuarial Action Interface (AAI), a deterministic runtime contract that prices each such action against a contractually fixed safe default under a time-consistent risk mapping, and gates execution against a per-boundary reserve capital budget. We then develop the Authority Frontier, an evaluation primitive measuring how much autonomous authority the runtime releases at each level of reserve capital. The framework provides (i) a deterministic quote-bind-commit protocol with toll-bounded capability tokens; (ii) a universal seven-class action taxonomy mapping heterogeneous tool calls to comparable authority units; (iii) replay determinism and pathwise reserve coverage under alpha-spending; (iv) cross-domain normalization via full reserve demand C_full and capital metrics Capital@k. We instantiate AAI across four agentic environments (database mutation, customer-service refund, and the public tau-bench retail and airline tool-use traces) and report a live Postgres panel in which three Azure-hosted models propose actions through the same contract. The frontier exhibits a common low-reserve refusal and intermediate-release pattern across domains, with saturation only where the budget grid reaches full reserve demand; required reserve capital varies by 22x (Capital@50 from 289 to 6457). The framework does not force domains into the same shape; it surfaces each domain's actuarial geometry. In the live panel the contract prevents realized loss across all three models at low budget while differing in underwriting persistence under denial: model identity is an actuarial underwriting variable. The contribution is a benchmark-ready evaluation framework for runtime actuarial control of autonomous-agent side effects.

Weak-to-strong (W2S) generalization is a promising framework for scalable oversight, yet existing evaluations often test students under matched train--test distributions. Therefore, we study W2S preference learning under zero-shot distribution shift and find that strong students trained on weak preference labels can appear successful in-distribution while failing to transfer across preference datasets. We provide evidence for a representational failure mode in which weak-supervised fine-tuning can pull the strong model toward source-domain features instead of maintaining broadly transferable preference representations. To mitigate this, we propose Representation Anchoring (Anchor), a simple yet effective regularizer that constrains excessive drift from the pretrained strong model's representation space during fine-tuning, while still allowing task-relevant adaptation. Across preference domains, datasets, and model families, Anchor consistently improves out-of-distribution transfer while maintaining competitive in-distribution performance. Together, our evaluation protocol, transfer-aware metrics, and method expose hidden brittleness in current W2S reward modeling and provide a practical path toward more robust preference transfer.

Reinforcement learning with verifiable rewards (RLVR) has driven breakthroughs in domains such as math, tool-use, and software engineering, yet its extension to computer-use agents (CUAs) has been bottlenecked by the scarcity of scalable training data with deterministic rewards. Constructing such data for CUAs requires consistent task instruction, executable environment, and verifiable reward. However, hand-curated benchmarks achieve high reward fidelity but cover few applications and LLM-as-judge-based datasets scale broadly but lack reliable verification. We present CUA-Gym, a scalable pipeline that co-generates task instructions, environment states, and reward functions. Concretely, a Generator agent constructs the initial and golden environment states, and a separate Discriminator agent writes the reward function from the task specification. An orchestrator agent drives the two through iterative rounds upon execution. Generated tuples then pass a final filter combining LLM majority voting and agent rollouts, ensuring quality beyond the per-task adversarial loop. To address the scarcity of training environments, we further synthesize CUA-Gym-Hub, a broad suite of high-fidelity mock web applications grounded in real-world software-use distributions, expanding the scale of CUA RLVR data by magnitude. Using this pipeline, we construct CUA-Gym, a dataset of 32,112 verified RLVR training tuples grounded in 110 environments. Trained with GSPO on CUA-Gym, our CUA-Gym-A3B and CUA-Gym-A17B achieve 62.1% and 72.6% on OSWorld-Verified, outperforming prior open-source CUAs at comparable scales, with performance scaling smoothly in both data volume and environment diversity. The same checkpoints also improve on the held-out WebArena benchmark, indicating transfer beyond the training environments. We will open-source the full synthesis pipeline, dataset, CUA-Gym-Hub environments, and models.

Single-pass uncertainty quantification (UQ) methods for classification represent uncertainty by predicting a tractable distribution over the class probability vector. While existing approaches primarily focus on enhancing the expressiveness of this distribution, they often provide limited insight into how predictive uncertainty is structured and aggregated, resulting in weak interpretability. We introduce the courtroom analogy, which conceptualizes uncertainty-aware classification as a structured debate among class-specific advocates. Each advocate forms a probabilistic opinion, and a final verdict is reached by aggregating these opinions using input-dependent plausibility weights. In this framework, each advocate's opinion is modeled as a Dirichlet distribution whose concentration parameter is decomposed into shared evidence and class-specific advocacy. This yields a structured mixture of Dirichlet distributions with semantically interpretable parameters. To instantiate this formulation, we propose Mixture of Dirichlet EXperts (MoDEX), a single-pass neural architecture that predicts the courtroom parameters, enabling efficient and expressive UQ while explicitly modeling uncertainty aggregation. We demonstrate that MoDEX enjoys strong theoretical properties and achieves state-of-the-art UQ performance across diverse benchmarks, yielding interpretable uncertainty estimates with meaningful semantics.

In the past decade, numerous studies have applied deep neural networks (DNNs) to decode auditory attention (AAD) from Electroencephalogram (EEG) signals via stimulus reconstruction. However, the influence of dataset balance on the decoding performance of stimulus reconstruction-based AAD remains unexplored. In this study, three publicly available EEG-AAD datasets - KUL, DTU, and NJU cEEGrid - are used to construct both balanced and unbalanced experimental conditions. We hypothesize and demonstrate that stimulus reconstruction-based DNN decoders tend to produce overestimated decoding performance on unbalanced datasets. To address this issue, we propose a leave-one-paired-envelope-out (LOPEO) cross-validation protocol. Experimental results confirm that LOPEO effectively prevents inflated decoding accuracy on unbalanced datasets. While balanced datasets are generally preferred in experimental design, LOPEO provides a principled evaluation framework for unbalanced datasets that have already been published, filling an important gap in the field.

Reinforcement Learning has become a standard paradigm for aligning Large Language Models with human intent and task requirements. While Group Relative Policy Optimization offers an efficient, value-model-free alternative to Proximal Policy Optimization, adapting it to real-world multi-reward settings remains challenging. Standard scalarization practices, such as Reward Combination and Advantage Combination, suffer from significant drawbacks: Reward Combination frequently generates advantages with excessively large squared magnitudes that lead to training instability, while Advantage Combination relies on static hyperparameters and ignores cross-objective correlations. To address these limitations, we propose Dynamic Variance-adaptive Advantage Optimization (DVAO), which dynamically adjusts combination weights based on the empirical reward variance of each objective within a rollout group, effectively up-weighting objectives with a stronger learning signal while suppressing noisy ones. We mathematically prove that DVAO maintains bounded advantage magnitudes for stable training and introduces a self-adaptive cross-objective regularization mechanism. Extensive experiments on mathematical reasoning and tool-use benchmarks using Qwen3 and Qwen2.5 models demonstrate that DVAO significantly outperforms baseline methods, achieving a superior multi-objective Pareto frontier and robust training stability.

We study optimal experimental design for multinomial logit (MNL) bandits, where an agent repeatedly selects a subset of $K$ items from a ground set of size $N$ and observes single-choice feedback. Unlike linear or generalized linear bandits, MNL bandits have a combinatorial action space, which makes classical optimal design approaches and naive optimization over all subsets computationally intractable. We propose a computationally efficient optimal design framework for MNL models that achieves both statistical efficiency and scalability through two complementary approaches: (i) an exact or certified-approximate reformulation of the design oracle as a $0$-$1$ mixed-integer linear program (MILP) with solver-certified early stopping, and (ii) a fully polynomial-time lifted design that replaces the nonlinear objective with a tractable surrogate. Using the Kiefer-Wolfowitz equivalence theorem, we establish near G-optimality guarantees and characterize the induced statistical-computational trade-offs. As an application, we develop a best assortment identification algorithm for MNL bandits with linear utilities and non-uniform revenues, and prove an instance-dependent sample complexity of $\tilde{O}\big(\frac{d \log N}{Δ^2}\big)$, where $d$ is the feature dimension, $N$ is the number of arms, and $Δ$ is the minimum revenue gap.

We study nonstationary generalized linear bandits (GLBs), where the expected reward is modeled through a nonlinear link function with an unknown time-varying parameter. This framework encompasses a broad class of reward models, including linear, Bernoulli, and binomial rewards. Existing approaches are predominantly based on maximum-likelihood estimation (MLE), using sliding-window, restart, or discounting mechanisms to handle nonstationarity. Although these methods achieve statistically efficient regret guarantees, they generally require revisiting past observations at every round, which leads to computation and memory costs that grow with time; moreover, several of them rely on a non-convex projection step. In this paper, we propose DOMD-GLB, a new algorithm for nonstationary GLBs that utilizes discounted online mirror descent (DOMD) for parameter estimation, thereby incurring only $O(1)$ computation and memory costs per round. We prove dynamic regret bounds of order $\tilde{O} \big(c_μ^{-1/2} d^{3/4} P_T^{1/4} T^{3/4}\big)$ in drifting environments and $\tilde{O}\big(c_μ^{-1/3} d^{2/3} Γ_T^{1/3} T^{2/3}\big) $in piecewise-stationary environments, where $d$ denotes the feature dimension, $T$ the time horizon, $P_T$ the path length, $Γ_T$ the number of change points, and $c_μ$ a curvature parameter associated with the link function, while substantially improving computational efficiency over prior work. To the best of our knowledge, this is the first algorithm for nonstationary GLBs with per-round computation and memory costs independent of time.

Neural network (NN) dynamics models and control policies achieve strong performance in robotics, but providing sound guarantees under uncertainty remains difficult, especially for closed-loop NN systems. Existing reachability tools provide formal over-approximations, yet are often non-differentiable, overly conservative, or too slow for modern learning and online planning pipelines. To address this, we present a parallelizable, differentiable reachability framework in JAX for continuous- and discrete-time systems with analytical and NN-based dynamics and controllers. Our framework combines Taylor-model flowpipe construction with CROWN-style linear bound propagation through a unified representation that preserves affine dependencies while supporting GPU-batched computation and automatic differentiation. Building on this reachability primitive, we develop (i) a certified training method that encourages reachability-friendly dynamics models and controllers, and (ii) a reachability-aware sampling-based MPC scheme with gradient-based refinement. Experiments on non-prehensile manipulation and quadrotor tasks, including hardware and higher-dimensional evaluations (up to 72D), demonstrate practical online planning while maintaining certified reachable-set over-approximations under bounded uncertainty.

In many industrial domains, the Functional Mock-up Interface (FMI) is used to exchange simulation models as Functional Mock-up Units (FMUs) across different partners using various modelling tools. This opens up the possibilities for simulation-based verification and validation using FMUs for ensuring reliable system behaviour. However, deriving effective test oracles for these simulation models remains challenging due to the absence of explicit expected outputs. This limits the applicability of conventional testing approaches, which require access to the internal workings of the systems. Metamorphic testing (MT) addresses this limitation by leveraging metamorphic relations (MRs), but extracting such relations from specifications remains largely a manual and error-prone process. To address this challenge, we propose an LLM-powered multi-agent workflow for specification-based metamorphic testing of FMU-based simulation models. The approach takes functional and interface specifications as input and orchestrates multiple agents to extract requirements and derive MRs. These MRs are expressed using Given-When-Then patterns to structure input conditions (Given), transformations (When), and expected output behaviours (Then). These relations are then used to generate metamorphic test cases, execute simulations, and evaluate output consistency across multiple sessions. We evaluate the approach on a Lube Oil Cooling system FMU, demonstrating its ability to automatically generate meaningful MRs and corresponding test cases. Preliminary results indicate that the proposed workflow can effectively support the systematic verification and validation of dynamic simulation models by reducing manual effort and improving test generation.

Coordinating micro-robotic swarms in physiologically realistic, time-dependent fluid environments remains an unsolved challenge for biomedical and environmental applications. We present a hybrid Computational Fluid Dynamics - Multi-Objective Multi-Agent Reinforcement Learning framework that directly couples a high-fidelity incompressible Navier-Stokes solver with decentralized proximal policy optimization to learn physically consistent swarm control strategies in oscillatory flow. Sixteen magnetically actuated micro-robots navigate a pulsatile arterial waveform, simultaneously optimizing upstream progression, energy conservation, and motion smoothness, reconciled using PCGrad surgery. Without PCGrad, energy efficiency and smoothness rewards collapse to near zero within 10,000 training steps while progress exhibits persistent large-amplitude oscillations, confirming that gradient conflict resolution is a structural requirement rather than an optional refinement in this domain. The converged policy achieves a progress reward of 6.5-7.0, a sustained energy efficiency of 0.63-0.65, and near-maximum smoothness (0.97-0.99), representing improvements over brute-force baselines on the primary objective while both baselines yield negative energy efficiency throughout. Training reveals three emergent behavioral phases: a collective two-layer hydrodynamic throttling formation that suppresses peak channel velocities during forward flow, a cycle-synchronized ratchet mechanism that exploits flow reversals for upstream repositioning, and an individualized final approach as agents near the success boundary. These results establish that time-dependent fluid-agent interactions can be captured directly within multi-objective reinforcement learning loops, offering a physically grounded paradigm for micro-swarm control in biomedical navigation, environmental monitoring, and industrial microfluidics.

Sampling-based model predictive control methods, such as Model Predictive Path Integral (MPPI), offer derivative-free optimization and robustness in complex robotic systems. However, standard MPPI relies on cost-based soft penalties that cannot guarantee hard-constraint satisfaction, severely limiting its applicability to highly constrained tasks such as closed-chain manipulation. To address this, we propose Manifold-Constrained MPPI (MC-MPPI), a real-time sampling-based control framework that enforces manifold-based equality constraints while preserving the computational advantages of MPPI. The key idea is to decouple the constrained optimal control problem into latent-space planning and execution-level correction. At the planning stage, a Variational Autoencoder (VAE) learns a low-dimensional latent representation of the constraint manifold, enabling MPPI to efficiently generate near-feasible candidate trajectories without per-sample modification. Since this reference enables accurate linearization of the equality constraints, an execution-level Quadratic Programming (QP) controller resolves the residual manifold mismatch in a single solve rather than through iterative projection. Experiments on a 14-DoF closed-chain dual-arm system in both simulation and real-world settings demonstrate that MC-MPPI operates stably at 100 Hz, reliably navigates dynamic environments while effectively maintaining hard equality constraints, and significantly outperforms baseline methods in tracking accuracy. Supplementary videos and implementation details are available at https://rcilab.github.io/mcmppi.

This paper presents a novel passivity-based semi-autonomous attitude control framework, with a particular focus on attitude kinematics defined on the special orthogonal group $SO(3)$. While human-robot interaction facilitates the successful execution of complex tasks, ensuring stability of human-in-the-loop systems on the $SO(3)$ manifold remains a largely unsolved challenge. We first propose a new control architecture in which a multi-robot system preserves invariance of the average information fed back to the human operator through so-called stealthy control, and the human intervention is mediated through a virtual leader, which is coupled with the robots via a passivity-based attitude synchronization law. We then rigorously prove closed-loop stability of the proposed human-in-the-loop system under the assumption that the human behaves as a passive system. To support this analysis, simulation studies are conducted to identify the human operator as a dynamical system, and to examine passivity properties of the identified model.

This paper presents reinforcement learning (RL) policies for dynamic quadrupedal locomotion in planetary exploration scenarios. Building on a taskoptimized quadruped with a 5-bar leg design, we develop RL policies for walking, vertical jumping, forward jumping, and in-flight attitude control, explicitly tailored to the reduced gravity on Mars. These policies jointly enable such robots to overcome obstacles larger than themselves through coordinated jumping and precise in-flight reorientation for safe landings. We demonstrate Sim2Real transfer of the attitude control policy on the Olympus quadruped through single-axis reorientation tests, while all locomotion policies are validated in simulation. A complete Mars exploration mission scenario demonstrates coordinated policy deployment across challenging terrain. Experimental results show 90° attitude reorientation in 2.6 seconds, with simulations demonstrating 3.1 meter vertical jumps and 3.9 meter forward jumps under Martian gravity conditions. - Supplementary video: https://www.youtube.com/watch?v=qlSJ3P87A4A

The rapid growth of Electric Vehicle (EV) adoption challenges power distribution networks through peak load spikes, voltage instability, and transformer overloads from uncoordinated charging. While Model Predictive Control (MPC) and standard Reinforcement Learning (RL) methods have addressed these issues, existing approaches rarely treat real-time carbon intensity or fluctuating renewable energy (RE) availability as primary scheduling objectives, leaving substantial decarbonisation potential unrealised. This paper proposes an emission-aware RL strategy based on the Soft Actor Critic (SAC) algorithm, with a multi-objective reward that penalises carbon emissions, curtailed on-site renewables, and unmet user demand. The agent is trained within a unified benchmarking framework on the EV2Gym platform, incorporating behind-the-meter solar and wind profiles, time-varying EirGrid carbon intensity data, and realistic workplace EV behaviour across 25 Electric Vehicle Supply Equipment (EVSE) units. Nine control strategies, including heuristics, emission-aware MPC variants, and the proposed RL agent, are compared under five renewable penetration scenarios (0%-50%) over ten independent runs each. The RL agent achieves a carbon intensity as low as 23.96 grams of carbon dioxide per kilowatt-hour under 50% wind penetration, representing up to 87% emission reduction versus the uncontrolled baseline, and outperforms the external graph-based Power Distribution Network (PDN) benchmark. Transformer overload remains below 7 kWh across scenarios, against up to 1093 kWh for the As Fast As Possible (AFAP) heuristic, and renewable self-consumption reaches 52% under combined wind and solar supply. Embedding carbon intensity forecasts into the RL state and reward aligns charging with low-emission periods while preserving grid compliance and user satisfaction.

The deployment of learning-based models in safety-critical control systems demands mathematical guarantees that standard regression architectures cannot provide. This paper presents an integrated framework that bridges Neural Ordinary Differential Equations (Neural ODEs), measurement-induced geometric structures, and Koopman operator theory, with the explicit aim of producing data-driven models whose stability certificates are computable, not merely conjectured. Three complementary components are developed and analyzed. First, ControlSynth Neural ODEs enforce global convergence through tractable linear matrix inequalities (LMIs), enabling complex nonlinear dynamics to be captured without sacrificing boundedness guarantees. Second, the ICODE formulation incorporates extrinsic environmental inputs into the learned vector field, while measurement-induced bundle structures confine state trajectories to physically admissible manifolds. Third, a systematic ISS verification pipeline certifies the input-to-state stability of Koopman-identified models via a convex $L_2$-gain LMI, converting an otherwise intractable robustness question into a solvable semidefinite program. The certified model is embedded in an ICODE-MPPI controller, which uses continuous-time residual learning inside a stochastic sampling loop to deliver robust path tracking under parametric uncertainty and persistent disturbances. Numerical experiments on a vehicle path-tracking benchmark and a nonlinear mechanical oscillator demonstrate up to a 61\% reduction in tracking RMSE and a 54\% reduction in state estimation error relative to uncertified baselines, with near-zero LMI violation rates across all evaluated disturbance levels.

Ring-like communication graphs appear in UAV formations, cyclic patrols, perimeter monitoring, and other multi-agent tasks in which agents exchange information mainly with neighboring vehicles along a closed route. When measurement and actuation noise are persistent, a useful augmentation should improve both the convergence rate of consensus and the steady-state disagreement level. This paper studies the addition of a single weighted chord to a connected weighted cycle. The central observation is that a chord is not just a generic rank-one edge update: it splits the cycle into two complementary resistance arcs, and this resistance split governs both the algebraic-connectivity gain and the Kirchhoff-index reduction. We first derive exact chord-induced effective-resistance and Kirchhoff-index update formulas, giving a closed-form coherence objective. We then prove that, under bounded conductances and small resistance discrepancy, near-antipodal resistance-balanced chords are near-optimal for algebraic-connectivity improvement; an i.i.d. bounded-conductance model yields the same conclusion with high probability. Finally, because the best convergence-rate chord and the best coherence chord need not coincide, we formulate the design as a finite Pareto problem and introduce RBAPS and AW-RBAPS, two resistance-balanced screening rules that retain only linear or near-linear candidate sets. Numerical experiments show that AW-RBAPS remains effective beyond the formal moderate-heterogeneity regime and approximates the exhaustive Pareto front with mean hypervolume ratio $0.9987$ while evaluating about $10.1\%$ of admissible chords.

A critical challenge facing clinicians managing chronic disease interventions is sustaining long-run patient health given limited information and resources. Digital therapeutics (DTs) provide a cost-effective way to manage interventions at scale through repeated interactions (e.g. daily treatment recommendations), but patient success is highly dependent on their adherence. Behavioral psychology suggests that both treatment recommendations and past adherence affect future adherence, yet existing decision support frameworks for DTs model only recommendation effects or treat adherence as exogenous context, leaving a key gap in model and algorithm development. To address this gap, we present a DT decision support framework that captures both recommendation and adherence effects, allowing clinicians to better plan treatment recommendations. We model a patient's time-varying capacity for engagement with treatment using a linear dynamical system (LDS) that captures both recommendation and adherence effects, endogenously connected to adherence behavior with a logit link. We establish finite-time identification guarantees for this model, extending LDS results to our setting. Next, we propose an optimism-based algorithm, UCB-BOLD, for online treatment selection and prove that it achieves sublinear regret. We evaluate UCB-BOLD against benchmarks via ablation studies on a synthetic patient cohort generated using micro-randomized trial data. DT decision support tools can include dynamical models to enable decision makers to efficiently use the data in DT settings to improve patient health through effective resource allocation. While myopic or heuristic approaches suffice for some patient types, the benefits of explicitly planning around recommendation and adherence effects are significant for others; UCB-BOLD achieves 2-3x lower conditional value-at-risk regret than the next-best benchmark.

This paper addresses the problem of reaching consensus under input saturation and intermittent communication, which can hinder the convergence of the system. We propose a method that translates the consensus into an equivalent stability problem. Then, we compute bounded sets that enclose the initial conditions and the evolution of trajectories leading to local input-to-state stability for systems interconnected over directed intermittent topologies. Our contributions include sufficient conditions for stability and stabilization of multi-agent systems under intermittent interactions and saturating inputs, with the ability to evaluate disturbance tolerance and rejection based on the regions that enclose the system's trajectories. We define disturbance rejection in terms of the $\mathscr{L}_2$ gain, and formulate stability and controller design conditions as convex optimization problems. Our method enable the maximization of regions that ensure local input-to-state stability, we provide numerical examples highlighting the trade-offs between mean frequency of intermittent interactions, disturbance energy, and convergence region size.

In industrial scenarios involving multi-agent collective decision-making, centralized decision-making may not be admissible due to restrictive access to individual local information, while the conflicts between participants' self-interest and global performance may also impede collaborative distributed decision-making. This paper proposes a mechanism-driven distributed decision-making method, wherein incentives are employed and designed to motivate participants to collaborate in a distributed fashion even though each participant's decision is driven primarily by self-interest. Focusing on optimization problems with coupled objective functions and coupled constraints, we design a distributed optimization algorithm tailored for this class of problems and provide guarantees for its convergence. Furthermore, we design two incentive mechanisms, the shadow pricing mechanism and the Vickrey-Clarke-Groves mechanism, and demonstrate that participants are willing to engage in distributed collaboration under these mechanisms. The mechanism drives the execution of the distributed algorithm, and the optimal result of distributed computation guides the determination of incentives in the mechanism, both of which are interrelated to form a closed loop. Finally, numerical experiments illustrate the effectiveness of the proposed algorithm and mechanisms.

Recent advancements in vehicle autonomy have drawn interest in understanding the impact of autonomous vehicles on traffic systems. In this paper, we study a traffic assignment problem in a mixed-autonomy setting where both human-driven and autonomous vehicles coexist. We model the interaction as a simultaneous routing game where human drivers are self-interested and aim to minimize their own travel times, while autonomous agents are altruistic and aim to minimize the total social cost. The standard nonatomic congestion game analysis establishes the existence of equilibrium to this game under convex cost functions, and does not have any implication of its uniqueness. In this work, we formulate the equilibrium as a variational inequality (VI), which enables us to establish the equilibrium existence without convexity assumption, and guarantees the uniqueness of the aggregated link flow and social cost at equilibrium under a specific class of cost functions. Leveraging this VI framework, we provide sufficient conditions under which including autonomous agents improves, deteriorates, or has no effect on social cost. While the possibility of deterioration has been established in prior work, our results complement existing worst-case bounds by explicitly characterizing sufficient conditions under which each outcome occurs, thereby providing a deeper understanding of mixed-autonomy traffic systems. Furthermore, we consider a centralized scenario where a social planner optimizes the routing of autonomous agents, and show that the same equilibrium is achieved as in the decentralized scenario when assuming convex costs.Finally, we conduct numerical experiments that illustrate how social cost changes with the amount of autonomous vehicles under different system parameters.

Modern radio-frequency (RF) instruments, such as vector network analyzers (VNAs), already provide mature remote-control interfaces. However, practical RF measurement workflows still rely on manual operation or custom scripting, which is time-consuming and expertise-intensive. This paper presents RF Instrument Agent (RFIA), a natural-language agent framework for reliable task-driven RF instrument control. RFIA adopts a decoupled intent--planning--execution architecture, where the LLM is used only for task understanding and high-level planning, while instrument-facing operations are handled by a deterministic runtime. Verified skills, workflow templates, RF analysis tools, instrument-specific rules, and retrieval-assisted SCPI knowledge are organized in a structured knowledge base, and hybrid execution graphs are used for closed-loop measurement tasks. A hardware-in-the-loop prototype is implemented on a commercial VNA and evaluated using a 16-task benchmark covering configuration, query, acquisition, rule-aware operation, RF-data analysis, and closed-loop measurement. RFIA handles all benchmark tasks under predefined execution and safety policies, including one expected safety rejection. Hardware-in-the-loop results with both a 230B-scale MiniMax-M2.7 model and a smaller 27B-scale Qwen3.6-27B model confirm that the decoupled architecture supports reliable natural-language RF measurement automation across different LLM backends.

Manipulating fragile deformable containers, such as disposable plastic cups filled with liquid, demands real-time grip-force adaptation within an extremely narrow force margin: insufficient force causes slip, while excessive force irreversibly deforms the thin wall. Existing approaches struggle to achieve such force-sensitive manipulation tasks. We propose a noise-statistics-based calibration-driven reflex control paradigm with vision-based tactile sensing: by analyzing the sensor's intrinsic noise characteristics (via a brief static-hold-and-unload protocol), we directly derive all controller thresholds, eliminating external force calibration, trial-and-error manual tuning, or material-specific physical models. Instantiating this paradigm, we present TactileReflex, a three-channel closed-loop controller that extracts three image-level proxies, shear intensity ($S_y$), contact intensity ($F_n$), and center of pressure ($C$), from dual visuo-tactile sensors and drives prioritized reflex channels at ~12 Hz for slip suppression, weight-adaptive release, and force protection. Each channel closes the loop directly on its proxy via noise-derived thresholds. Ablation demonstrates that only the full three-channel system is able to prevent irreversible container deformation (5/5 success vs. at most 1/5 for partial configurations). In a dynamic pouring task, fixed-effort baselines fail in all 10 attempts due to pose drift, while TactileReflex achieves 9/10 success across two water volumes. As a self-contained and interpretable controller, TactileReflex can serve as a plug-and-play safety layer beneath high-level manipulation pipelines, including haptic-free VR teleoperation and vision-language-action (VLA) policies.

This paper addresses connectivity preservation in leader-follower multi-agent systems with unknown control-affine dynamics and local state information. We introduce the distributed data-driven zeroing control barrier function (3D-ZCBF) framework, which ensures the controlled invariance of safety sets by identifying derivative bounds from input-state data without requiring explicit models of high-dimensional agent dynamics. In this work, we derive the explicit, decoupled safety conditions necessary to maintain connectivity for leader-leader, and follower-follower pairings. These individual constraints, along with the leader-follower conditions, are aggregated into explicit system-wide conditions that formally guarantee the preservation of the entire communication network. Furthermore, we provide a quantitative analysis demonstrating how the size of the collected data set and the accuracy of the learned Jacobian bounds impact the feasibility of the safety certificates. The proposed conditions are implemented via a projection-based controller, and simulations confirm that these explicit 3D-ZCBF requirements effectively maintain system-level connectivity using only local, two-hop information.

Embodied agents, which couple intelligent decision-making with physical actuation in the real world, impose far more stringent and heterogeneous communication requirements than purely software-based agents. While 6G promises sub-millisecond latency, ultra-high reliability, native intelligence, and integrated sensing, systematic studies on how to exploit these capabilities for embodied agent communication remain limited. This article investigates 6G-enabled communication systems for embodied agents from both conceptual and engineering perspectives. First, we review the concept, embodiment value of embodied agents, and clarify their distinctions from disembodied agents. Then, we analyse the symbiotic relationship between embodied agents and 6G networks. We highlight how key 6G enablers can support the stringent requirements of human-robot interaction. Furthermore, we demonstrate the proactive role of embodied agents in bolstering communication networks through coverage extension, environmental sensing, and physical world understanding. Building on these insights, we propose a hierarchical communication architecture for human-robot remote interaction, comprising a human-intent perception layer, an open radio access network (O-RAN)-based transport layer, an intelligent intermediary layer, and an embodiment layer. To validate its feasibility, we implement an end-to-end prototype that integrates a haptic device, an industrial robotic arm, an intermediary platform, and a 5G O-RAN testbed. Experimental results demonstrate millisecond-level latency and stable closed-loop operation, confirming the practicality of the proposed architecture and providing a reference for future 6G-embodied agent research and industrial deployments.

This paper investigates continuous-time motion planning under Signal Temporal Logic (STL) specifications. The goal is to generate smooth robot trajectories that satisfy high-level logical and timing requirements while respecting low-level motion constraints. To this end, we propose an efficient framework that combines timed-automata reasoning with graphs of convex sets (GCS). An STL specification is first represented by a timed automaton, which is then coupled with a convex decomposition of the configuration space to form a joint transition system encoding both task progress and region occupancy. Based on this joint transition system, the STL motion-planning problem is reformulated as a shortest-path problem over a GCS, whose solution induces a smooth Bézier-spline trajectory satisfying the STL specification, smoothness requirements, and velocity bounds. We establish the soundness of the proposed formulation and analyze its computational complexity, showing that, once the timed automaton and convex decomposition are fixed, the convex relaxation scales polynomially with the configuration-space dimension and the Bézier degree. We further develop a compact timed-automaton construction for an expressive STL fragment using dedicated templates and Boolean composition. Numerical experiments on low-dimensional benchmarks, a $3$-D quadrotor, a $30$-DoF humanoid, and a hardware experiment on a UR-3 robot arm demonstrate that the proposed method efficiently solves complex STL motion-planning problems and produces smooth executable trajectories.

We study deception in adversarial graph traversal, where a mobile agent seeks to reach a goal with minimum cost while an adversary alters edge costs to increase the total traversal cost. Unlike prior works that assume fixed observer-deceiver roles, we model this problem with two-sided incomplete information in which both players possess private information and update beliefs from observed actions. To solve the resulting indefinite-horizon game, we develop an adaptation of the Extensive-Form Double Oracle (XDO) algorithm. While the standard XDO algorithm is designed for finite games, the proposed adaptation ensures bounded computation despite endogenous game termination. We show that the proposed algorithm terminates in finite time and returns an epsilon-Nash equilibrium. Finally, we use Value of Information to characterize the deceptive and counter-deceptive behaviors that emerge from equilibrium strategies.

METANET is a widely used second-order macroscopic traffic flow model for freeway networks, supporting applications across traffic simulation, ramp metering, and variable speed limit control. The predictive accuracy of any traffic model, however, hinges on careful calibration to real-world conditions. Despite its widespread use, there have not been open-source tools for calibrating METANET's parameters. Without open-source calibration, results cannot be easily reproduced or extended to other networks. This work provides an open-source METANET calibration, simulation, and data visualization tool. The calibration is formulated as a nonlinear program (NLP) solved via the interior-point method (IPOPT), with joint ramp flow estimation. We validate our calibration on real-world freeway data from two widely used traffic monitoring systems: Interstate-24 MObility Technology Interstate Observation Network (I-24 MOTION), one of the largest open-road trajectory instruments in the country, and loop detector data from the Caltrans Performance Measurement System (PeMS), which spans nearly 40,000 detectors across California freeways and serves as a standard benchmark in traffic research. Models calibrated using our method are able to reproduce these datasets' observed traffic patterns across diverse network geometries and traffic conditions including complex stop-and-go congestion waves. As large-scale traffic monitoring infrastructure continues to expand, open-source calibration tools are essential for translating growing volumes of sensor data into validated models that can support real-world traffic control. The complete code is publicly available at https://github.com/woxsao/metanet-calibration to support reproducible research in freeway traffic modeling and control.