Computation and Language
Understanding and Mitigating Hallucination Escape in Tool-Using LLM Agents
Peigui Qi, Kunsheng Tang, Yide Song et al. (+2 more)
Large
language models (LLMs) increasingly serve as autonomous
agents that invoke external tools. However, this capability introduces tool
hallucination, selecting incorrect tools or generating invalid calls. Existing mitigation methods report substantial improvements, yet we identify a previously overlooked failure mode that we term
Hallucination Escape. These methods reduce
hallucination on the tool configuration they are tuned on but increase it on other configurations, canceling out the gain. We further investigate this phenomenon and find that
hallucination rises sharply when a model's intrinsic tool-use tendencies conflict with the current tool configuration, and that existing methods reinforce rather than suppress these tendencies, which in turn contributes to
hallucination escape. Building on these findings, we propose EscapeGuard, a training-free inference-time method that combines conflict-aware gating with configuration-derived
attention enhancement to mitigate tool
hallucination while preventing
hallucination escape. Across six
benchmarks on various models, EscapeGuard reduces tool-selection
hallucination by 9.0 pp and suppresses
hallucination escape, lowering the cross-configuration mean by 23.7 pp and achieving an 89.1% net improvement in paired-query evaluation. We hope this work can encourage evaluation beyond a single tool configuration and pave the way for more reliable tool-using LLM
agents.
Read the full abstract ▾
All authors Peigui Qi, Kunsheng Tang, Yide Song, Weiming Zhang, Nenghai Yu
Artificial Intelligence
TimeNet: An Extensible Unified Data Infrastructure for Next-Generation Temporal Foundation Models
Martin Maritsch, Timo Stoffregen, Thomas Kaar et al. (+36 more)
Temporal Foundation Models (TFMs) aim to generalize across domains,
datasets, and tasks. Yet, their development remains constrained by fragmented, task-specific data formats, annotations, and processing pipelines. We introduce TimeNet, an open-source data standard and scalable infrastructure that decouples temporal data from task definitions and represents signals, metadata, annotations, and supervision in a shared, extensible data model. TimeNet supports
multimodal signals with regular, irregular, or ordinal time axes and expresses different task families (including classification,
forecasting, temporal localization, question answering, generation, and editing) as reusable views over the same recordings. This shared representation enables heterogeneous time-series
datasets to be combined for large-scale model training across domains, modalities, and tasks. We demonstrate TimeNet by transcoding
datasets with 1.5M task instances spanning diverse domains, modalities, temporal scales, and forms of supervision, while retaining practical I/O performance relative to native formats. TimeNet enables an existing TFN training pipeline to support joint training on a configurable number of heterogeneous
datasets through configuration changes alone. We show this capability by training TFM across multiple
datasets and tasks, obtaining a 14% F1 score improvement compared with models trained on individual
datasets. These results show that TimeNet provides the data and systems foundation needed to move beyond task- and
dataset-specific TFMs toward models that can learn jointly across heterogeneous domains, modalities, temporal scales, and forms of supervision from a common data model.
Read the full abstract ▾
All authors Martin Maritsch, Timo Stoffregen, Thomas Kaar, Behsad Riemer, Maxwell A. Xu, Max Rosenblattl, Juncheng Liu, Nicolas Zumarraga, Yu Yvonne Wu, Denys Herasymuk, Sparsh Rastogi, Hyungjun Yoon, Bosong Huang, Arvind Pillai, Dmytro Lopushanskyy, Tony Chen, Robin Deuber, Yichen Liu, Shvat Messica, Dan Li, Jian Lou, Yuwei Zhang, Jaeho Kim, Renée Rosillo Garcia, Fan Wu, Robert Müller, Elgar Fleisch, Flora D. Salim, Dimitris Spathis, Yuzhe Yang, Aaqib Saeed, Daniel McDuff, Ming Jin, Markus Kreft, Kevin O'Sullivan, Robert Jakob, Azul Garza, Paul Schmiedmayer, Patrick Langer
Robotics
Reachability-Guided Sequential Quadratic Programming-Guarded Model Predictive Path Integral for Safe Nonlinear Predictive Control
Alexandre Didier, Jason J. Choi, Namhoon Cho et al. (+2 more)
Safe
robot control often requires combining long-horizon performance optimization with hard state and input constraints, but existing approaches tend to address this tradeoff partially. Sampling-based model predictive control (MPC) methods such as model predictive path integral (MPPI) are effective in handling nonlinear and nonconvex environments, yet their finite-sample rollouts and unconstrained weighted-average update can return an unsafe control. Deterministic nonlinear MPC can explicitly incorporate constraints, but its real-time safety and performance depends strongly on warm starts and local convergence. Hamilton–Jacobi reachability (HJR) provides rigorous safety certificates, but offline value-function computation remains practical only for reduced-order models. We propose ReSQ-MPPI, a reachability-informed generation–refinement architecture that combines these complementary strengths. An HJR value function computed offline for a reduced-order model guides online MPPI sampling toward safe, promising trajectory candidates. The MPPI solution is then refined by a small number of sequential quadratic programming (SQP) iterations in a full-order MPC problem. A key observation is that the standard MPPI inference step is an unconstrained weighted least-squares problem; ReSQ-MPPI replaces it with a constrained MPC refinement that recovers the MPPI update when it is feasible and minimally modifies it otherwise. Simulations in cluttered
navigation and autonomous racing environments demonstrate that ReSQ-MPPI improves safety and performance over standalone MPPI, MPC, and reachability-filtered sampling-based control baselines.
Read the full abstract ▾
All authors Alexandre Didier, Jason J. Choi, Namhoon Cho, Claire J. Tomlin, Melanie N. Zeilinger
Machine Learning
CEENs: Causality-enforced evolutional networks for solving time-dependent partial differential equations
Jeahan Jung, Heechang Kim, Hyomin Shin et al. (+1 more)
Despite the growing popularity of physics-informed neural networks (PINNs), their applicability in the long-time integration of partial differential equations (PDEs) remains constrained. We argue that this problem stems from the lack of consideration of temporal causality in the original PINN formulation, resulting in a bias towards satisfying governing equations at later times before learning the initial condition and hence leading to erroneous solutions. To this end, we propose a novel method that seamlessly integrates temporal causality into the training process. Drawing inspiration from classical numerical methods where the temporal causality is reflected, we divide the time domain into nonoverlapping subintervals, assign a unique neural network to each subinterval, and construct a loss function founded on the integral form of PDEs within these subintervals. The proposed networks undergo sequential training, beginning with the initial time step. Our method demonstrates significant improvement in accuracy for long-time simulations of various PDE problems where the original PINN method fails while it requires less computational cost and
memory compared to the PINN method. A parallelization
algorithm is provided to further enhance the computational efficiency, showing a significant speedup for solving time-dependent PDEs.
Read the full abstract ▾
All authors Jeahan Jung, Heechang Kim, Hyomin Shin, Minseok Choi
Data Structures and Algorithms
Fair Diversity Maximization via Local Search
Mohammad Ansari, Sina Azizeddin, AmirMohammad Bandari et al. (+2 more)
Diversity maximization is a fundamental optimization problem with applications in machine learning, data summarization, information
retrieval, and recommendation systems. In many such applications, the data are partitioned into groups, and the selected subset must satisfy prescribed group quotas. We study Fair Diversity Maximization: given a set of points in a metric space partitioned into $m$ groups, the goal is to select exactly $k_i$ points from each group $i$ while maximizing the minimum pairwise distance among the selected points. The best previously known approximation guarantee is $m+1$, which grows linearly with the number of groups. We show that this dependence on $m$ is not fundamental. We present a new local-search framework that yields a $4$-approximation for any constant number of groups, with no restrictions on the metric space or on the size of the selected set. To the best of our knowledge, this is the first constant-factor approximation whose guarantee is independent of the number of groups in this general setting. Our framework maintains all group quotas exactly while progressively eliminating violations of the diversity objective. We further develop a specialized
algorithm for two groups that achieves a $2$-approximation, improving the previous best factor of $3$. This factor is optimal: unless $\mathrm{P}=\mathrm{NP}$, no
polynomial-time
algorithm can achieve an approximation factor strictly better than $2$, even for the unconstrained case.
Read the full abstract ▾
All authors Mohammad Ansari, Sina Azizeddin, AmirMohammad Bandari, Pouria Mahmoudkhan, Hamid Zarabi-Zadeh
Computation and Language
Saying, Not Knowing: Aggressively GGUF-Quantized Small Language Models Still Write Rare Words They Can No Longer Define
Saurabh Kumar Singh, Yogeshwar Singh Dadwhal and Malhar Vedak
Post-training quantization to the GGUF format's mixed-precision K-quants is commonly how open-weight
language models reach consumer hardware, yet its effect on fine-grained lexical competence is uncharacterized. We audit 27 quantized artifacts across 13 families and four architecture backbones, 0.35B-14B parameters, evaluated down their published ladder to Q2_K (about 2.6 bits per weight), on 429 frequency-validated rare English words under two probes: surface inclusion of a
prompt-supplied word and its one-sentence definition, scored by a tiered multi-synonym matcher, its error measured by a blind LLM-judge census of every definition, with human verification. Three regimes emerge at Q2: total collapse into unusable builds, severe semantic dissociation in sub-2B models, and mostly robust preservation above about 3B. In every sub-2B artifact, definitions fall 20-67% below the artifact's baseline, typically several times the inclusion loss. Two controls separate rarity from task difficulty: within the rare set, loss rises with rarity in six of seven sub-2B artifacts, and on a 100-word common-word set rare words lose more than common words in all eight, significantly in six. Tokenizer vocabulary size does not predict the damage (Spearman rho=0.12); parameter count dominates (rho=0.72), confirmed within five of six same-tokenizer families. Q4_K_M remains lexically clean at >=1B. The damage is frequency-graded, provider-dependent, and not calibrated by WikiText-2 perplexity: across nine artifact-matched ladders, near-identical Q2 penalties (44.7%/47.6%) separate an artifact keeping its definitions (3.6%) from one losing them (43.6%). Aggressively quantized small models can keep generating fluent text while no longer knowing what it means, risking hardware-constrained deployments in domains where semantics carries consequences. Validation must be per artifact.
Read the full abstract ▾
Distributed Computing
Budget-Constrained Fault-Tolerant Mutual Visibility for Autonomous Robots under the Mobility Fault Model
Prakhar Shukla, Animesh Maiti, Shivam Kumar et al. (+1 more)
We investigate the mutual visibility problem for a swarm of $n\ge3$ autonomous mobile
robots under the budget-constrained mobility fault model. The
robots are opaque, so if three
robots are collinear, the middle
robot obstructs the visibility between the other two. Each
robot is assigned a finite movement budget, reflecting its limited energy, that bounds the total distance it may traverse during the execution. Moreover, an arbitrary number of
robots may become permanently immobile due to mobility faults. The objective is to design a distributed
algorithm that enables the non-faulty
robots to coordinate their movements so that, within a finite time, every non-faulty
robot attains unobstructed visibility of all
robots in the system, including the faulty ones, while respecting the prescribed movement budget. We consider luminous
robots operating under the $\mathsf{SSYNC}$ model with non-rigid movements, without any agreement on their local coordinate systems, and equipped only with a common fixed reference point. We present a deterministic distributed
algorithm that solves the problem despite an arbitrary number of mobility faults. The
algorithm guarantees mutual visibility for the non-faulty
robots, respects the movement budget of every
robot, provides collision-free movements for the
robots, and uses only 12 light colors.
Read the full abstract ▾
All authors Prakhar Shukla, Animesh Maiti, Shivam Kumar, Subhash Bhagat
Computation and Language
Ideological Stance Detection in a Low-Resource Language: Polarization in Bangladeshi Public vs Private University Discourse on Social Media
Safaruzzaman Shovo, Monowar Islam, Asif Hossain et al. (+2 more)
Public vs. private universities is a debatable issue, and it creates polarization on social media in Bangladesh. Debate on quality, jobs, and prestige is passionate among the students, parents, and graduates, the majority of whom speak Bengali, a low-resource
language. To measure this polarization, this paper introduces a manually annotated
dataset of 4,060 Bengali comments labeled as Pro-Public, Pro-Private, or Neutral. We evaluated the quality of our annotations by Fleiss's Kappa agreement that was 0.89, corresponding to a high agreement among annotators. The classical ML (SVM, Random Forest, XGBoost), BiLSTM network, hybrid BanglaBERT+XGBoost models and the state-of-the-art zero-shot LLMs (Claude Sonnet 4, DeepSeek-V3.1, Llama 4 Maverick, Kimi K2 Thinking, Qwen3-235B Thinking) models are evaluated. The accuracy of BanglaBERT+XGBoost is 91.81% and macro F1 score is 91.70%, which is higher than all the supervised baselines. The zero-shot Llama 4 Maverick Thinking achieves a macro F1 of 0.931 (overall accuracy of 93.31%) without any fine-tuning. All machine learning (ML), deep machine learning (DL) and
transformer models were outperformed by the zero-shot Llama 4 Maverick model. Polarization also is evident, in some ways more clearly in the Pro-Private comments, which emphasize modern facilities and timely graduation, versus the Pro-Public comments, which emphasize affordability and government jobs. Our findings open new directions for analyzing social media polarization in low-resource
languages.
Read the full abstract ▾
All authors Safaruzzaman Shovo, Monowar Islam, Asif Hossain, Sameya Akhter, Md. Shamsul Islam
Computation and Language
XTurnix: Large-Scale Self-Supervised Turn Control through Two-State Binary Decisions
Zhanxun Liu, Yifan Duan, Hengtao Wu et al. (+7 more)
General turn-taking behavior in real-time dialogue systems requires deciding whether to keep listening or start responding while listening, and whether to continue or stop while speaking. Existing turn detectors use heterogeneous, task-specific label spaces and are often trained on limited annotations or evaluated on isolated utterances, making them difficult to use as a unified causal controller with comprehensive context. We propose XTurnix, a compact text-based model that formulates turn control as two binary decisions conditioned on the AI's current listening or speaking state and predicts a single control
token from the complete dialogue history. XTurnix is pretrained on 5.5 million causal action examples automatically derived from timestamped two-speaker transcripts, then fine-tuned on synthetic multi-turn examples with a flatter distribution across the four state-action labels. We evaluate XTurnix on four public
benchmarks and a balanced self-curated
benchmark. Across the public
benchmarks, XTurnix achieves the best results on all SemanticVAD and LiveKit splits, ties the native Smart-Turn model on Smart-Turn Bench, and achieves the highest incomplete-turn accuracy on Easy-Turn. On the self-curated
benchmark, it reaches 89.06% accuracy, more than 20 percentage points above the strongest third-party baseline at 68.75%, while maintaining F1 scores between 84.21% and 90.63% across all four categories. These results demonstrate unified listening- and speaking-state turn control in a single compact model. Code is available at https://github.com/xcc-zach/xturnix, with an interactive demo at https://huggingface.co/spaces/xcczach/xturnix-demo.
Read the full abstract ▾
All authors Zhanxun Liu, Yifan Duan, Hengtao Wu, Chen Yang, Qinyuan Cheng, Kun Wang, Xingyu Zeng, Xipeng Qiu, Chaochao Lu, Xie Chen
Computation and Language
GlitchPatch: Repairing Glitch Tokens in Frozen Language Models via Local Retokenization
Kunsheng Tang, Peigui Qi, Yide Song et al. (+3 more)
Glitch
tokens are anomalous vocabulary entries that can cause large
language models (LLMs) to produce outputs inconsistent with their inputs. Existing repair methods require access to model internals, making them impractical for frozen checkpoints. We investigate whether glitch
tokens can be repaired outside the model by optimizing the input tokenization. An empirical study on BPE merge-rule deletion reveals that (1)deleting a glitch
token's merge rule can fix a substantial fraction of failures, yet disrupting normal
tokens sharing intermediate merge nodes causes the overall glitch rate to rise, and (2)different decomposition granularities yield non-monotonic fix rates while collateral damage on normal
tokens grows monotonically. Motivated by these findings, we propose GlitchPatch, a repair framework for frozen
language models based on local retokenization, consisting of two stages: the offline stage uses Behavioral Path Optimization (BPO) to find the behaviorally optimal replacement
token sequence for each glitch
token and compiles validated replacements into a rule table; the online stage substitutes only the IDs of matched glitch
tokens in the canonical
token sequence, with no modification to model parameters or internal states. Experiments on ten models spanning six tokenizer families show that GlitchPatch achieves an 85.10% mean fix rate, outperforming the strongest baseline by 14.37 percentage points, and reduces the average glitch rate from 14.88% to 2.27%. GlitchPatch achieves a 0.00% RR in full-vocabulary evaluation and leaves rule-unmatched inputs unchanged by design. We further evaluate the practical impact of repair from the perspectives of time cost,
language understanding, and capability, supporting its deployment feasibility. We hope this work provides a practical option for improving tokenizer reliability.
Read the full abstract ▾
All authors Kunsheng Tang, Peigui Qi, Yide Song, Peijun Huang, Weiming Zhang, Nenghai Yu
Cryptography and Security
JASPER: Special Session on Joint Reliability And Security Assessment of SPlit Computing for Edge Robustness
Enrico Magliano, Giuseppe Esposito, Amir Hossein Shahdadian et al. (+13 more)
Split Computing (SC) enables efficient deployment of Deep Neural Networks (DNNs) by partitioning inference between edge devices and cloud servers. However, intermediate feature representations are simultaneously exposed to hardware faults and
adversarial attacks, which are traditionally evaluated independently. This paper presents a unified framework for the joint assessment of reliability and security in Split Computing. First, reliability is characterized through
neuron-level fault injection using the Mean Relative Accuracy Degradation (MRAD) while security through feature-map-aware
adversarial attacks simulations using the Attack Success Rate (ASR). Based on these complementary analyses, the Joint Vulnerability Score (JVS) is introduced, along with a confidence-aware extension that jointly captures prediction errors and confidence degradation. The framework is evaluated on ten Split Computing configurations based on ResNet-50 trained on ILSVRC-2012. Experimental results show substantial differences across compression strategies, with MRAD ranging from 44.3% to 61.2% under fault injection, while
adversarial attacks achieve up to 98.8% ASR. Furthermore, the proposed joint metrics reveal vulnerability trends that remain hidden when reliability and security are analyzed independently, providing a more comprehensive methodology for designing dependable Split Computing systems.
Read the full abstract ▾
All authors Enrico Magliano, Giuseppe Esposito, Amir Hossein Shahdadian, Rama Mounika Kodamanchili, Juan David Guerrero Balaguera, Juan Esteban Rodriguez Condia, Annachiara Ruospo, Roberta Siciliano, Stefano Di Carlo, Maksim Jenihhin, Marco Levorato, Alessandro Savino, Matteo Sonza Reorda, Christian Herglotz, Michael Hübner, Mahdi Taheri
Distributed Computing · Cross-listed from quant-ph
Structural Conditions for Distributed Quantum Advantage
Sabina Drăgoi, María Gragera Garcés and Lirandë Pira
Circuit cutting runs a
quantum computation on processors smaller than the
circuit, at the price of classical knitting whose cost grows exponentially with the number of cut gates. Keeping this cost affordable is necessary but not sufficient for an advantage, since knitting classically easy subcircuits is itself classically easy. We formulate three requirements for distributed
quantum advantage under a stated budget: affordable knitting, classical difficulty that survives the cut, and, for variational
circuits, resolvable gradients. We prove that under stated assumptions knitting stays affordable when subcircuits grow behind a bounded interface and becomes exponentially expensive when fixed-width subcircuits multiply. We turn the requirements into screening criteria and apply them to eighteen
circuit families. We identify finite local-depth
circuits with bounded interfaces as a setting in which the requirements can coexist, with hardness established only in the worst case. As a classically verifiable proof of principle, we knit one gate joining two field-perturbed toric-code patches on an IBM Nighthawk processor for up to 142
spins, and confirm that the reconstruction can at least resolve the contact correlation beyond independent execution for up to 98
qubits.
Read the full abstract ▾
Computer Vision
Detecting Defects that Matter: An Application-Driven Benchmark for Anomaly Detection in Manufacturing and Retail Logistics (VAND 4.0 Challenge)
Lars Heckler-Kram, Dorian Henning, Ashwin Vaidya et al. (+6 more)
Existing Anomaly Detection
benchmarks are saturated and often unrealistic. As part of the VAND 4.0 Challenge, we introduce a hidden-test, application-driven
benchmark across two deployment-critical domains: industrial manufacturing and retail logistics. In the Industrial Track (MVTec AD 2), the results reveal that unsupervised anomaly
segmentation remains challenging: the best regular-setting method achieves only ~57% pixel-level $SegF_1$, indicating substantial room for improvement. Zero-shot approaches trail by ~15 $SegF_1$ points, confirming that task-specific training on normal data remains essential for precise defect localization. Robustness to distribution shifts remains a key open challenge and DINOv3-backbones clearly dominate this track. In the Retail Track (Kaputt 2), the results reveal that (1) supervised defect detection is approaching saturation for common defect types; (2) the best off-the-shelf VLM approach trails specialized models by ~28 AP, confirming that currently VLMs cannot replace fine-tuned detectors, (3) reference images did not prove helpful for top-performing approaches. Performance collapses on rare defects (spillage ~53 AP, missing units ~27 AP), where the supervised ceiling is bounded by data availability. To drive future progress in this domain, we provide a new low-prevalence retail AD
dataset (Kaputt-Rare). Across both tracks, computational efficiency is assessed as a first-class metric combining performance, throughput,
memory, and power consumption. We introduce a novel metric for measuring efficiency and reveal that that top-performing methods rely on heavy architectures while efficiency is largely neglected. Overall, we conclude that the community needs (a) more efficiency-aware method development, and (b) true anomaly detection approaches for rare defects and shifting conditions. https://sites.google.com/view/vand4-cvpr2026/challenge
Read the full abstract ▾
All authors Lars Heckler-Kram, Dorian Henning, Ashwin Vaidya, Jan-Hendrik Neudeck, Ulla Scheler, Anton Milan, Samet Akcay, Paula Ramos, Sebastian Höfer
Robotics
AgenticTactileVLA: Contact-Guided Execution-Time Supervision for Generalizable Dexterous Manipulation without VLA Retraining
Elizaveta Semenyakina, Ivan Snegirev, Mikhail Kiselev et al. (+4 more)
Vision-
language-action policies may predict a transferable manipulation strategy yet fail to realize it reliably on the encountered object: objects compatible with the same grasp differ in geometry and compliance, and visual feedback degrades under closure occlusion. AgenticTactileVLA is presented as an execution-time supervisor that shifts part of object-specific adaptation from prediction to physical interaction. A fixed VLA provides the approach and hand targets; the supervisor decides whether to remain transparent, refine finger flexion, retain or release the corrected configuration, return control to the VLA for retry, or select a compliant hand-control regime. It uses finger-position and motor-effort feedback as proprioceptive contact evidence and requires neither tactile sensors nor VLA retraining. On a Unitree G1 with a BrainCo Revo2 hand, a randomized matched-block evaluation on five objects held out from VLA training yields 61.3% completion for the base VLA, 72.0% for unconditional close-to-stall control, and 84.0% for the supervisor under a shared budget; the gain is positive on every object and persists under moderate pose perturbations. Ablations show the gain is not explained by extended closure alone, and that selective triggering reduces correction episodes by 65.7% with no detected change in completion. A retention audit shows acceptance predicts retention in 88.9% of held-out cases, while compliant objects expose conservative false rejection. A thin-walled-cup study demonstrates contextual routing to compliant control, matching an always-compliant reference. These results suggest that contact-guided execution-time adaptation can improve the object-level generalization of a fixed VLA to held-out objects by adapting physical realization without object-specific retraining.
Read the full abstract ▾
All authors Elizaveta Semenyakina, Ivan Snegirev, Mikhail Kiselev, Miguel Altamirano Cabrera, Artem Lykov, Hajira Amjad, Dzmitry Tsetserukou
Machine Learning · Cross-listed from stat.ML
Gaussian Flow Dynamics: Simulation-Free Neural SDE Learning Beyond One-Time Marginals
Grigory Bartosh and Christian A. Naesseth
Simulation-free training of latent
Stochastic Differential Equations (SDEs) relies on a variational posterior process whose one-time marginals are tractable, typically Gaussian. Such marginals, however, do not determine the underlying dynamics: many processes share the same marginals while differing in their temporal structure, and existing parameterizations fix this structure implicitly, which restricts the posterior family and biases the learned model. We introduce Gaussian flow dynamics, which construct
stochastic processes directly from smoothly evolving Gaussian marginals while making the marginal-preserving, or gauge, degrees of freedom explicit and parameterizable. The construction admits state-dependent
diffusion coefficients and recovers every linear SDE with additive noise and a non-degenerate Gaussian initial distribution. Building on it, we propose Gauge Matching, a simulation-free method for latent SDE learning that combines Gaussian flow dynamics with the SDE Matching objective. Gauge Matching costs at most quadratically in the latent dimension per step, like SDE Matching, but learns the temporal structure of the posterior beyond its one-time marginals. It comes within a nat of Helmholtz-SDE, which computes the gauge from the prior Jacobian at cubic cost, on the linear
benchmark where the exact posterior is known, matches it on nonlinear systems, and applies where Helmholtz-SDE does not, to state-dependent noise.
Read the full abstract ▾
Numerical Analysis
Arbitrarily High-Order Structure-Preserving Parametric Finite Element Methods for Geometric PDEs via Local Pullback Flow Maps
Weizhu Bao, Yifei Li and Dongmin Wang
We develop arbitrarily high-order structure-preserving parametric finite element methods for
geometric PDEs including surface
diffusion and volume-preserving mean
curvature flow based on local pullback flow maps. The central idea is to reformulate the
geometric PDEs on an arbitrary intermediate hypersurface and represent the subsequent
evolution through a local pullback flow map. Using admissible local pullbacks, we derive two formulations from the corresponding pullback identities for the Laplace-Beltrami operator, referred to as the conformal and equidistribution formulations. We discretize both formulations using arbitrary-degree isoparametric finite elements and Runge-Kutta collocation methods with positive weights. For the conformal formulation, weighted averages of the normal-Jacobian vector ensure exact preservation of the enclosed area or volume, while algebraic stability of the Runge-Kutta method additionally guarantees dissipation of the perimeter or surface area. For the equidistribution formulation, a path-averaged normal-Jacobian vector and a
geometric discrete gradient guarantee both exact preservation of the enclosed area or volume and dissipation of the perimeter or surface area, without requiring algebraic stability. Numerical experiments confirm the expected high-order accuracy and structure-preserving properties.
Read the full abstract ▾
Systems and Control · Cross-listed from cond-mat.mtrl-sci
Kilovolt-class Vertical (011) e̱ta}-Ga2O3 Schottky Diodes for High Voltage and High Temperature Applications
Emerson J. Hollar, Aaron M. Adams, Nolan S. Hendricks et al. (+2 more)
We report kilovolt-class vertical (011) e̱ta}-Ga2O3 Schottky diodes utilizing high-permittivity dielectric TiO2/Al2O3 field-plate for high voltage and high temperature applications. A systematic study was performed with Pt/(011) e̱ta}-Ga2O3 Schottky barrier diodes (SBDs) with varied diameters from 100 {\mu}m to 300 {\mu}m, for both with and without field-plate, that revealed excellent consistency of reverse blocking performance regardless of diode area. The field-plate SBDs achieved superior breakdown voltages (3.90 - 4.16 kV) compared to the diodes without field-plate (3.06 - 3.16 kV) owing to effective edge termination. Furthermore, we explored high-temperature performance of the field-plate (011) e̱ta}-Ga2O3 diodes that revealed excellent forward conduction properties and high rectification ratio (~10^9) throughout the temperature range (25 - 150 C). At reverse bias, the field-plate diodes also exhibited kV-range breakdown voltage with no evident increase in leakage current up to the explored elevated temperature of 150 C. The low area-dependence of breakdown voltage, excellent forward transport properties, and minimal reverse leakage at both high-voltage and elevated temperature demonstrate the exciting potential of (011) e̱ta}-Ga2O3 SBDs in high-temperature power switches. Thus, our work demonstrates the strategy of advancing the performance of vertical e̱ta}-Ga2O3 SBDs by utilizing the advantageous (011) e̱ta}-Ga2O3 epilayers with low background doping, reduced killer dislocation effects, and effective field management for high-voltage and high-temperature applications.
Read the full abstract ▾
All authors Emerson J. Hollar, Aaron M. Adams, Nolan S. Hendricks, Andrew J. Green, Esmat Farzana
Artificial Intelligence
TrustMed-RL: Long-Horizon Reinforcement Learning for Evidence-Grounded Clinical Diagnosis
Wenxin Zhan, Yizheng Jiao, Haifeng Song et al. (+4 more)
Medical
language models can produce correct diagnoses despite incomplete investigations and unsupported
reasoning. To support long-horizon, evidence-grounded diagnosis, we introduce TrustMed-RL. Built from PubMed rare-disease cases and over 24,000 manually annotated image panels, it integrates interviews, examinations, testing, specialist consultation, and literature search through state-dependent actions. Our 8B
vision–
language policy, trained with clinically adapted GiGPO and coverage-adjusted diagnostic rewards, achieves 37.1% diagnostic accuracy on 2,500 evaluation cases, outperforming all evaluated open-weight baselines and improving over supervised fine-tuning by 12.4 percentage points.. When success additionally requires acquiring at least 50% of supporting test evidence, TrustMed-RL achieves 32.5%, exceeding GPT-4o by 6.8 percentage points. Furthermore, it surpasses all evaluated baselines on MTMedDialog and multiple larger 27–32B models on AgentClinic. In physician review of 200 diagnostically accepted test-set trajectories, 83.0% receive evidential-grounding scores of 4–5 out of 5. Physicians' assessments suggest that these diagnostic trajectories are trustworthy and aligned with human diagnostic
reasoning.
Read the full abstract ▾
All authors Wenxin Zhan, Yizheng Jiao, Haifeng Song, Shuai Xu, Chencheng Pan, Jiayi Feng, Anjie Xie
Machine Learning · Cross-listed from math.OC
Largest Rashomon sets of decision trees for robust contextual optimization
Lorenzo Bonasera and David Pisinger
Many decision trees fit the same data almost equally well, yet they can route a query point to different leaves and induce different local empirical distributions. We study decisions that meet prescribed cost, shortage or risk targets despite this predictive multiplicity. We propose the joint Rashomon and robustness optimization framework for optimal decision trees. It jointly selects an operational decision and the largest Rashomon set of trees, so that the targets hold under the local empirical distribution that every tree in this set induces at the query point. We specialize the framework to the regression setting, and we show that a tree affects the decision only through the training observations sharing the query leaf, which we call its query neighborhood. As a result, the robust problem involves only finitely many distinct constraints, which can be examined in order of increasing estimation loss. We develop a constraint generation
algorithm that combines query-path pricing with dynamic programming to identify violating neighborhoods without enumerating trees. On synthetic newsvendor instances, the
algorithm typically needs few neighborhoods and runs substantially faster than full neighborhood enumeration. On restaurant demand data, the robust orders increase the mean tolerated excess estimation loss by 17.6% and reduce the empirical conditional value-at-risk of the worst 10% of realized costs by 8.3% relative to the sample average approximation orders of the optimal tree, while the mean cost difference is not statistically significant. An interpretability analysis further shows how the retained neighborhoods explain the decision and its robustness limit.
Read the full abstract ▾
Numerical Analysis
Conditioning and Singular Value Distribution of Jacobi Weighted Histopolation Matrices
Allal Guessab, Federico Nudo and Stefano Serra-Capizzano
In this paper, we first study the singular value distribution of the unscaled
matrices arising from Jacobi weighted histopolation. For the Jacobi weight with parameters $(\alpha,\beta)$, and using the Jacobi basis with parameters $(\alpha+1,\beta+1)$, we previously proved that, for $\alpha,\beta>1/2$ and quasi-uniform meshes, the growth of these
matrices in the sense of singular value distribution is slower than any positive power of the logarithm of the
matrix size. However, the numerical behavior of the unscaled
matrices suggested a nontrivial singular value symbol, which we identify explicitly in this paper. Starting from the standard asymptotic formula for Jacobi
polynomials, we derive an asymptotic representation of the weighted
cell averages defining the entries of the histopolation
matrices. This representation allows us to analyze the associated Gram sequence by means of GLT theory. We identify its GLT symbol and, consequently, we obtain the singular value distribution of the histopolation
matrices for any $\alpha,\beta>-1$. We also characterize the set $\mathcal Z$ where the resulting symbol vanishes and compute its measure, showing that this set depends only on the mesh, while the Jacobi parameters affect the values of the symbol on its support. When this measure is positive, the singular value distribution implies the discrete asymptotic ill-posedness of the problem, while a comparison with the Toeplitz setting suggests exponential growth of the spectral condition number. When the measure of $\mathcal Z$ is zero, the problem is well-posed and the observed conditioning is algebraic in the
matrix size. Finally, numerical experiments supporting the theoretical findings are reported and discussed, while conclusions are given in the final section of the current work together with a few open problems.
Read the full abstract ▾
Computer Vision
Beyond Plausibility: Verifiable Fine-Grained Image Editing on Structured Assets
Muyao Wang, Chen Zhu, Shiqi Yang et al. (+2 more)
Fine-grained image editing requires more than producing a visually plausible result: an editor must execute the requested attribute change precisely while leaving everything else intact. However, existing
benchmarks leave a critical gap between realism and verifiability:
benchmarks built on realistic images typically rely on human or
vision–
language model judgments, while deterministic evaluation has largely focused on synthetic shape canvases, with application-oriented extensions primarily limited to charts. This makes it difficult to determine precisely how much of a requested edit was executed, where unintended changes occurred, and whether small differences between models reflect genuine editing capability or evaluator uncertainty. To bridge this gap, we present VeriEdit-Bench, a
benchmark for fine-grained, instruction-faithful image editing across realistic structured assets with deterministic, four-axis evaluation. Its 1,740 cases are compiled from the source code of 153 Scalable Vector Graphics (SVG) graphics, charts, web interfaces, and presentation slides. Controlled source-code edits preserve the original visual context while yielding exact target images, pixel-level edit masks, and explicit edit specifications, enabling reproducible scoring along four axes: edit fidelity, preservation, localization, and magnitude. Evaluating eleven editors, we find that even the strongest model remains far from full credit; rankings for the same recoloring operation reverse between charts and SVG graphics; and outputs with similar pixel-accuracy profiles can still differ substantially in localization and change magnitude. This decomposition yields graded, verifiable feedback and exposes model-specific capability and failure profiles that holistic scores or evaluator-dependent judgments may obscure.
Read the full abstract ▾
All authors Muyao Wang, Chen Zhu, Shiqi Yang, DongHyun Hwan, Hideki Nakayama
Artificial Intelligence
AgentPersonaBench: Benchmarking Persona-Driven User Simulation
Jintao Huang, Yifan Wang, Hongyu Shen et al. (+43 more)
We introduce AgentPersonaBench (APB), a
benchmark evaluating whether persona conditioning faithfully steers downstream
agent behavior. While
language models are increasingly deployed for persona-driven user simulation, existing
benchmarks primarily evaluate conversational styling or self-reports rather than authentic behavioral fidelity. APB evaluates latent persona adherence one trait at a time,
embedding each target trait within a complete synthetic profile without explicitly naming the trait or disclosing the test. Ground-truth adherence is verified strictly from observable actions across four interaction surfaces of increasing realism: survey, chat, web (interactive web environments), and app (desktop software environments). APB comprises 2,460 tasks spanning 867 traits, verified through automated audits and expert review. Our evaluation of 20 frontier model arms demonstrates that high-fidelity user simulation is already attainable: leading models achieve up to 84.7% full-pass adherence under unprompted conditions. At the same time, APB identifies clear behavioral boundaries: adherence drops across interaction modalities (only 37.9-64.3% pass all four surfaces), multi-attribute demands degrade retention, and competing model families exhibit pronounced behavioral divergence.
Read the full abstract ▾
All authors Jintao Huang, Yifan Wang, Hongyu Shen, Yi Daniel Lu, Shirley Huang, Minsik Oh, Yewen Wang, Muhammad Ahmed Mohsin, Zhen Xu, Yilan Fan, Zichen Yuan, Ahsan Bilal, Zibu Wei, Sankalp Jajee, Henry Gagnier, Saksham Kapoor, Jicheng Wang, Qianfeng Wen, Yixuan He, Steven Dillmann, Jiashu He, Yucheng Lu, Linqiang Guo, Danyang Zhang, Shi Bo, Raunak Mondal, Haixiang Tang, Weihang Xiao, Allen Nie, Jing Tang, Yueying Li, Yifan Simon Liu, Jianheng Hou, Dianzhuo Wang, Qianyu Zhu, Zhixu Silvia Tao, Zhejian Peng, Zihan Wang, Ishan Gupta, Jinxuan Fan, Wanting Jiang, Shushu Liang, Chenxi Qiu, Yijun Wang, Xiaomin Li, Yuexing Hao
Cryptography and Security
COPEX: Benchmarking LLM Robustness to Adversarial Context Across Model Context Protocol (MCP) Layers
Nahom Birhan, Mehrdad Rostamzadeh, Sidhant Narula et al. (+3 more)
Large
language models increasingly mediate tool use in Model Context Protocol (MCP) systems, where
adversarial influence may enter through user instructions, tool schemas, tool outputs, or protocol messages. Existing
benchmarks often evaluate deployed
agents, conflating model susceptibility with guardrails, orchestration, and general task capability. We introduce COPEX (COntext Provider EXploitation), a controlled
benchmark that isolates the model as an MCP client by fixing the surrounding
agent stack and varying only the tool-selecting model. COPEX covers 25 attack types instantiated as 125 scenarios across four entry surfaces: model/
agent, client, server/tool, and transport. Across nine models and 3,375 trials, the mean attack success rate is 64.4%, with surface-level means ranging from 58.3% to 71.4%. Some client- and transport-level attacks succeed partly outside the model's observation or control, separating system exposure from model susceptibility. Combined input and context scanning reduces mean attack success by 49.6% on an eight-attack defense subset relative to the undefended setting. The
benchmark is available at https://github.com/inspire-center/copex.
Read the full abstract ▾
All authors Nahom Birhan, Mehrdad Rostamzadeh, Sidhant Narula, Mahmoud Nazzal, Mohammad Ghasemigol, Daniel Takabi
Artificial Intelligence
Do Tool Calls Execute as Intended? Measuring and Repairing Intent-Execution Correspondence in LLM Agents
Boyang Yang, Zhenhao Li, Ziyao Yang et al. (+4 more)
Agents built on large
language models (LLMs) build and run software through tool calls. A call reaches its program through several hops, and any hop can change the call without notice. When the changed call fails, the
agent retries a correct call, which costs users time and money.
Benchmarks and failure analyses do not see the change, because they read the call and its result but not what a hop received. We define intent-execution correspondence (IEC) as the property that the executed action matches the action the emitted call denotes under the tool contract. Our protocol observes what each hop received without executing the call, and names the first hop that changed it by the receiver's own parser. IntAct then delivers the call in a form that this hop cannot alter, or refuses the call. We build IEC-Bench from the changes observed in real-world use, with chains of dependent calls under the execution paths of 4 widely-used harnesses. In 47,828 shell calls within production sessions, Claude Code's Bash tool changes 12.0% of the calls that carry code, escape sequences, or long text. For 80.7% of the calls whose backslashes are changed, the wrong action runs without any reported error. All 10 measured harnesses change a call. Trajectory-based judgment attributes 95.1% of the production failures to the LLM, although the path caused more than half of them. On IEC-Bench, the path raises the
token cost per passed task 2.4 times (up to 12.3 times). A hop that changes a call also hides the changes after it, so 55.1% of the failures on one path appear only after its first hop is repaired. IntAct, deployed in a commercial product, recovers 79.2% of the failures with a changed call. Harnesses should therefore be designed and tested hop-by-hop to ensure a correct call executes as intended or is refused.
Read the full abstract ▾
All authors Boyang Yang, Zhenhao Li, Ziyao Yang, Kanghui Jia, Xin Yin, Mingmou Liu, Haoye Tian
Robotics
Frame-Level Temporal Alignment for Human-to-Robot Visual Adaptation
Xizhe Zhang, Jingfeng Zhang, Zirun Zhou et al. (+1 more)
Transferring visual representations pretrained on human
videos to
robot manipulation requires learning reliable correspondences between human and
robot demonstrations. However, paired demonstrations can differ in execution rate and in the proportion of non-key frames that do not directly reflect task progress. Frames at the same relative timestamp may therefore represent different task stages, which can cause correspondence learning to fail. To address these issues, we propose Frame-Level Temporal
Alignment (FLTA), a framework that uses two temporal priors to adapt visual encoders pretrained on human
videos for
robot manipulation. It learns shared task-progress representations without frame-level correspondence annotations, allowing frames at different relative temporal positions to match. A global progress prior combines normalized temporal positions with visual similarity to construct a soft correspondence target. A local temporal order prior penalizes backward transitions while allowing stays and varying forward rates to accommodate execution-rate differences. With ResNet-50 and ViT encoders, our method achieves relative improvements of 46.93% and 65.96%, respectively, over the best baselines in average simulation success rates and achieves higher task success rates on real-world manipulation tasks. These results also suggest that effective human-
robot adaptation depends less on the number of parameters updated than on which parameters are selected. Our project page is available at https://rtx5090ultra.github.io/FLTA-Project-Page/.
Read the full abstract ▾
All authors Xizhe Zhang, Jingfeng Zhang, Zirun Zhou, Hong Jia
Artificial Intelligence
Functionally Equivalent or Not? Graph-Grounded Differential Surrogate Execution for Code Equivalence
Amit Kachroo, Like Hui, Haitao Mao et al. (+2 more)
Determining whether two programs are functionally equivalent is central to code modernization, patch validation, refactoring, and code-generation evaluation. Yet the usual signals are incomplete: tests cover only finite inputs, textual similarity confuses implementation with behavior, and unconstrained LLM judgments are difficult to audit. Direct execution is often impossible when a program depends on an obsolete, licensed, unavailable, or unsafe environment. We introduce FEAgent, a selective equivalence assessor
agent that combines typed program-graph evidence with differential surrogate execution. FEAgent first aligns public interfaces and behaviorally relevant graph anchors, then issues bounded queries over call-flow, control-flow, data-flow, type, import, and effect relations. Next, a branch-aware generator
agent proposes discriminating inputs, and two blinded LLM surrogates independently predict source and target observables. Every claim and predicted divergence is recorded in an evidence ledger. A deterministic reconciler then returns EQUIVALENT, INEQUIVALENT, or UNCLEAR rather than forcing a verdict when paths are uncovered or evidence conflicts. We evaluate FEAgent on function-level equivalence and repository-level bug patches, where the existing oracle is a
benchmark label or a passing test suite. Every disagreement with that oracle is adjudicated by direct execution, revealing errors in
benchmark labels and behavioral divergences missed by unit-test-only scoring. On EquiBench, execution confirms FEAgent's disagreements with published labels on 216 of 1,200 evaluated pairs (18.0%); on SWE-bench Verified, 94 of 331 test-passing
agent patches (28.4%) diverge from the reference patch. FEAgent thus serves as an audit layer between testing and formal verification, keeping its evidence reviewable and its uncertainty explicit without claiming a proof of equivalence.
Read the full abstract ▾
All authors Amit Kachroo, Like Hui, Haitao Mao, Yuhao Zhang, Nguyen Vo
Computation and Language
Boundaries Agree, Labels Do Not: Intra-Annotator Dynamics as a Kind of Training Data
Marharyta Shvets
Data quality now matters as much as compute for training
language models. Much training data comes from human annotation of text, and interpretive annotation has no ground truth that could settle what is "accurate". Two lines of work respond to this. One combines annotators into a "ground truth" and measures how well they agree with each other; the other treats their disagreement as a signal. Both compare different people at one point in time. We measure something else: how well one reader reproduces their own reading of the same text over time. One expert human reader and three LLM families segmented three Sumerian myths and labelled the causal function of each segment with one of seven states. Across runs months apart, the human cut the text in much the same places but named the segments differently, in every myth. The models show no such consistent pattern: their gap between the two layers is positive in some myths and negative in others, and its size varies. The human's label changes are not random: the runs go through much the same functions but start them one step apart, while model runs start them at the same places. We argue that this pattern is a usable measure of data quality and a contamination check: a "human" annotation whose labels are as stable as its boundaries, and whose functions start in sync, looks like a model's.
Read the full abstract ▾
Machine Learning
A multi-stage probabilistic framework to estimate gas-fired generator performance during extreme winter weather
Sajjad Uddin Mahmud and Anamika Dubey
Extreme winter weather has repeatedly disrupted gas-fired power generation in the United States, yet the plant-level data needed to systematically quantify outage risk remain proprietary. Using publicly available weather and electricity demand data together with anonymized generator contingency records from the North American Electric Reliability Corporation (NERC), we develop a three-stage
Bayesian probabilistic framework for estimating winter-driven generator performance. Applied to New York State (2013–2022), the framework sequentially estimates: the hourly probability of a generator contingency event, the expected net available capacity conditioned on an event occurring, and the event duration. Colder conditions and higher electricity demand are associated with higher failure probability, lower retained capacity, and longer event duration. Under the most severe observed stress conditions, estimated mean hourly event probability reaches 24% , while expected mean net available capacity falls to 13% of nameplate rating. Full outage events have a median duration of 12.7 hours, while partial derating event duration increases from 2.4 to 7.1 hours with capacity loss severity. The proposed framework establishes a transferable baseline that utilities with access to plant-level records can directly extend to obtain more precise reliability estimates for operational planning and resource adequacy assessment.
Read the full abstract ▾
Robotics
Human Behavior-Informed Crash Scenario Generation with Real-World Crash Priors for Autonomous Vehicle Safety Evaluation
Mingxing Peng, Xusen Guo, Long Chen et al. (+3 more)
Reliable safety evaluation of autonomous vehicles (AVs) is essential to improving road safety, yet it depends critically on realistic simulation of rare crashes. Existing crash scenario generation methods can increase collision occurrence, but often fail to realistically reproduce how crashes evolve before impact or the distribution of crash types observed in the real world. Here, we present CrashSim, a human behavior-informed crash scenario generation framework that uses real-world crash priors to guide generative multi-
agent traffic simulation for more reliable AV safety evaluation. These priors capture how real-world crashes evolve before impact and how different crash types are distributed, allowing limited crash data to guide realistic and scalable scenario generation across naturalistic driving contexts. We evaluate CrashSim against competing methods, showing that it more closely reproduces real-world pre-impact behavior, collision dynamics, collision geometry and crash-type distributions. We further use CrashSim to construct nuCrash
dataset, containing over 4,000 crash and near-crash scenarios. Closed-loop evaluation of five AV planners shows that nuCrash more effectively exposes differences in planner safety capabilities than nuScenes. An LLM-assisted evaluation
agent further analyzes planner failures to provide capability-level diagnoses and targeted improvement guidance. Together, CrashSim enables realistic and scalable crash generation for more informative AV safety evaluation.
Read the full abstract ▾
All authors Mingxing Peng, Xusen Guo, Long Chen, Xintao Yan, Siyu Teng, Jun Ma
Machine Learning
A Bird's-Eye View of Iterative Reward Design
Logan Mondal Bhamidipaty, Lauren Robson, Linda Petrini et al. (+2 more)
Designing effective reward functions in RL typically requires substantial expertise and trial and error. Recent work automates this process with LLM-based systems that generate and iteratively improve reward code using policy feedback. However, these methods are often hard to compare because they differ in implementation details, feedback assumptions, and evaluation environments. To address this, we introduce a
Benchmark for Iterative Reward Design (BIRD) that expresses existing methods in a unified configuration and evaluation space. This lets us compare
algorithms directly, ablate individual design choices, and prototype new components under matched feedback conditions and policy-training budgets. Across MuJoCo, Meta-World, Assistax, and HumanoidBench, we identify a small set of simple design choices that consistently improve performance. Combining these choices yields significantly better performance than the evaluated methods from prior work. Our results highlight the strength of simple baselines and motivate further study of when additional algorithmic complexity improves iterative reward design. Code is available at https://github.com/safety-research/bird.
Read the full abstract ▾
All authors Logan Mondal Bhamidipaty, Lauren Robson, Linda Petrini, Shengrui Lyu, Kamal Ndousse