Artificial Intelligence
Complexity of Grounded Semantics and Preferred Semantics in Finitary Argumentation Frameworks
Jinfan Xu and Jieting Luo
Abstract argumentation frameworks (AFs) introduced by Dung provide a formal foundation for non-monotonic
reasoning in artificial intelligence. While decision problems for general infinite AFs typically reside at high levels of the analytical hierarchy ($\Sigma_1^1$ or $\Pi_1^1$), restricting the framework to be computably finitary reduces some of the complexity to the arithmetical hierarchy. In this paper, we present a complexity mapping of grounded and preferred semantics in computably finitary AFs across standard decision problems: credulous acceptance ($\Cred$), skeptical acceptance ($\Skep$), extension existence ($\Ex$), uniqueness ($\Uni$), and non-empty existence ($\NE$). For grounded semantics, credulous and skeptical acceptance are already known to be $\Sigma_1^0$-complete. We show that non-empty existence is also $\Sigma_1^0$-complete, whereas existence and uniqueness are trivial. These classifications are understood within the domain of valid computably finitary representations. For preferred semantics, using a computably finitely branching computation tree, $\Cred_{\pref}$ is shown to be in $\Pi_1^0$-c and $\NE_{\pref}$ is $\Sigma_2^0$-c. However, it is insufficient to reduce universal quantification and global uniqueness, leaving $\Skep_{\pref}$ in $\Pi_1^1$ and $\UniPref$ in $\Sigma_2^1$-c. Our results show the precise boundary where finitarity succeeds to bring
reasoning down to the arithmetical hierarchy and where second-order quantification forces problems back into the analytical hierarchy.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
REACT: Rolling Denoising and Dual Decoupling for Reactive Robot Control with VLA Models
Houlong Xiong, Zhenqi Qiu, Zechen Wang et al. (+8 more)
Flow-based
vision-
language-action (VLA) models generate action chunks for temporally coherent
robot motion, but chunked control creates a fundamental closed-loop trade-off: long chunks provide smooth execution, whereas frequent replanning improves reactivity at the cost of action discontinuities. We introduce REACT, a rolling-denoising framework that makes flow-based VLAs more reactive while preserving long-horizon context. Instead of regenerating entire action chunks from scratch, REACT maintains a persistent action buffer with staggered flow timesteps. At each control step, the full horizon is denoised using the latest observation, the cleanest action block is executed, partially refined future blocks are shifted forward, and fresh noise is appended to the tail. As a result, each executed action block is refined across multiple recent observations before deployment. To support real-time control, we further introduce dual decoupling, which separates sensing, VLM encoding, DiT denoising, and action execution, enabling high-frequency observation updates and action streaming under practical compute constraints. Across the RoboTwin 2.0 simulation
benchmark and real-world tasks spanning bimanual manipulation and dynamic control on multiple
robot platforms, REACT improves task success and reduces reaction latency while producing smoother trajectories than frequent-replanning and asynchronous baselines.
Read the full abstract ▾
All authors Houlong Xiong, Zhenqi Qiu, Zechen Wang, Suohang Zhang, Yiyu Ren, Wanting Xu, Hongfei Niu, Chengyang He, Ge Sun, Ran Cheng, Qian Zhu
Artificial Intelligence · Cross-listed from cs.LG
The Polytopal Neural Network
A. Emilie J. Wedenborg, Anders V. Nørskov, Teresa Dorszewski et al. (+2 more)
Understanding how deep neural networks process information remains a central challenge. Existing interpretability methods often compromise structural fidelity, rely on prespecified corpora, or explain models post-hoc. We propose Polytopal Neural Networks (PNNs), a framework that extracts distinct layer-wise aspects by enforcing a polytope-based structure that is used directly in subsequent information processing. We scale our approach using learned corpus representations and an amortized simplex inference procedure and highlight how the framework also gives a direct route to vector quantized (VQ) training. In PNNs, observations are explicitly described by their
alignment with layer-specific aspects. Empirical results show that imposing polytopal constraints on neural network representations preserves meaningful structures in the latent space with minimal degradation in performance, favorable compressed representations when compared to VQ representations in unsupervised learning, while also providing a performant new approach to VQ deep learning training. Our findings suggest that deep networks can enforce interpretable polytope-based representations, offering a principled path toward more transparent AI systems with minimal performance compromise.
Read the full abstract ▾
All authors A. Emilie J. Wedenborg, Anders V. Nørskov, Teresa Dorszewski, Kristoffer Wickstrøm, Morten Mørup
Artificial Intelligence
An Interpretable Approach to PDE Solution Discovery via Structural Experience Distillation
Yunpeng Gong, Huolong Wu, Can Yang et al. (+1 more)
PDE solution discovery aims to identify explicit symbolic expressions for unknown physical fields from observations under known physical constraints. Existing methods, however, collapse data fidelity and physical consistency into a single terminal score used as the sole feedback signal, providing little information about which subexpressions are responsible for a candidate's final performance. This opaque terminal feedback severely limits the interpretability of the search process itself, offering no insight into why a candidate succeeds or fails. Consequently, reusable structures in otherwise suboptimal candidates are often discarded, whereas incidental syntax along successful search trajectories may be repeatedly reinforced. We propose SED-MCTS, a Monte Carlo tree search approach that distills structural experience from evaluated expressions and reuses it to guide subsequent symbolic solution search. Through counterfactual subtree interventions, SED-MCTS estimates local structural contributions, routes reliable evidence to the responsible construction edges, and preserves useful components in a refined structural archive. The approach naturally extends to coupled multiphysics systems. Across a diverse suite of PDE
benchmarks, SED-MCTS achieves strong performance under a fixed evaluation budget and improves search efficiency and robustness under noisy or scarce observations.
Read the full abstract ▾
All authors Yunpeng Gong, Huolong Wu, Can Yang, Min Jiang
Artificial Intelligence · Cross-listed from cs.LG
Agentic-TTT: Training test-time policy for test-time training
Jiahao Lu and Mohan Kankanhalli
Test-time training (TTT) adapts an LLM's parameters using signals derived from test inputs, and can make striking improvements in pre-specified settings such as IMO competitions or designated open problems. By turning deployment experience into parameter updates, TTT provides a direct mechanism for model-level self-improvement. Yet TTT is not universally beneficial: each TTT
algorithm works in different settings, and applying an ill-suited method could waste test-time compute or even damage model performance. Therefore, such parameter-level self-improvement requires agency: the model must decide when TTT is warranted, which
algorithm to invoke, and whether an existing skill can be reused. To fill this gap, we introduce Agentic-TTT, which learns a test-time policy to govern those decisions. Agentic-TTT turns TTT procedures into callable tools, treats accumulated skills as an evolving deployment environment, and trains its policy using the observed utility gains from its decisions. On our
benchmark, Agentic-TTT nearly doubles the utility over the backbone model, learns to trade off utility against compute, and generalizes to domains unseen during training. Together, these results point toward autonomous self-improvement: models that can decide how to learn from their own deployment experience.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SE
Neural Network Verification for Deep Joint Source-Channel Coding
Thanh Le, Hai Duong, Takeshi Matsumura et al. (+1 more)
Deep joint source-channel coding (DeepJSCC) transmits data end-to-end over wireless channels using a neural encoder-decoder, but reconstruction quality can degrade sharply under
adversarial perturbations and channel disturbances; no method formally bounds this degradation for DeepJSCC. We present the first bound-propagation framework for verifying DeepJSCC's decoder, bounding worst-case reconstruction error over a given wireless channel's noise region. Current deep neural network (DNN) verifiers do not support three DeepJSCC decoder components: parametric rectified linear activations (PReLU), transposed convolutions, and Rayleigh fading. We extend state-of-the-art techniques for optimization of linear relaxation in DNN verification for PReLU, replace the transposed convolution with its restricted upsample-then-convolution form, and formulate Rayleigh fading as a structural perturbation prepended directly into the decoder, thereby reducing the dimensionality of the verification problem. We also instantiate Lipschitz-regularized global robustness training, denoted GloRo, improving global robustness and enabling tight certification of DeepJSCC models for the first time. On DeepJSCC model for image transmission, this global robustness training procedure combined with structural encoding lowers the median certified bound by up to 41% and certifies about ten times more safe cases (192 against 19) than GloRo with interval encoding at a 10-degree error in channel estimation. Over-the-air validation with an orthogonal frequency-division multiplexing (OFDM) implementation on software-defined
radio devices confirm the certificate holds on real hardware, with a worst observed error on
radio link at 0.082 against a certified bound of 0.128.
Read the full abstract ▾
All authors Thanh Le, Hai Duong, Takeshi Matsumura, ThanhVu Nguyen
Artificial Intelligence · Cross-listed from cs.CV
DataVista: Diagnosing Multimodal LLMs on Data Video Understanding
Yupeng Xie, Zhenyang Wang, Jiayi Zhu et al. (+4 more)
Data
video is a media form that integrates data visualization with
video narrative, widely adopted in news reporting and business analysis. Compared with general
video understanding, data
video understanding places greater emphasis on accurately reading data from animated charts, integrating evidence across charts and time, and understanding how narrative organization and visual design communicate information. Yet existing
benchmarks target either general
videos or static charts, and data
video understanding has not been systematically evaluated. We present DataVista, the first
benchmark for data
video understanding, containing 961 real-world data
videos and 6,775 evaluation questions organized under a three-level progressive capability framework (data perception, temporal
reasoning, narrative understanding) with 10 fine-grained question types across five topic domains. Systematic evaluation of 19 mainstream MLLMs shows that the best-performing model, Gemini-3.1-Pro, achieves 70.0% overall accuracy, still far below human expert performance, with models performing worst on Causal
Reasoning and Narrative Structure. Increasing frame counts and adding subtitles mainly benefit data perception and temporal
reasoning, with limited gains in narrative understanding. Further analysis of model responses identifies typical failure modes in chart reading, evidence judgment, and instruction understanding. The
benchmark is available at https://github.com/HKUSTDial/DataVista.
Read the full abstract ▾
All authors Yupeng Xie, Zhenyang Wang, Jiayi Zhu, Yinghao Tang, Zhouan Shen, Yiyu Chen, Yuyu Luo
Artificial Intelligence
MetaOPD: Meta-Learned Token Weighting for On-Policy Distillation
Zipeng Wang, Xinpeng Dong, Yuefan Wang et al. (+6 more)
On-policy
distillation (OPD) trains a student on its own generated responses using
token-level teacher supervision. However, uniform weighting overlooks differences in
token learning value, while existing weighting methods rely on predefined mappings from prediction signals to
token weights. These mappings are not learned from the effectiveness of the resulting student updates, limiting their ability to adapt to evolving learning needs. In this paper, we propose MetaOPD, a bilevel optimization framework that jointly learns the student model and a lightweight
token-weighting network. The inner objective updates the student through weighted OPD, while the outer objective optimizes the weighting network using validation loss on reference solutions after a virtual student update. Differentiating through this update connects weighting decisions to their effects on post-update performance, allowing the mapping from prediction signals to
token weights to evolve alongside the student. Experiments on six mathematical
reasoning and three out-of-domain
datasets, covering two student scales and seven baselines, demonstrate the effectiveness of MetaOPD, with Avg@8/Pass@8 gains over OPD of 1.99/5.97 percentage points for the 0.6B student and 2.25/6.41 points for the 1.7B student.
Read the full abstract ▾
All authors Zipeng Wang, Xinpeng Dong, Yuefan Wang, Pingchen Lu, Xian Wei, Kun Kuang, Fei Wu, Zhongxiang Dai, Min Zhang
Artificial Intelligence
MindFlow: Mind Supernet Powered Thinking Flows for Research Idea Innovation
Mengdi Liu, Wenjue Chen, Wenyue Chen et al. (+10 more)
Research idea innovation is a fundamental engine of scientific progress, yet it remains difficult to generate and evaluate in a scalable and controllable way. This challenge lies in its inherently open-ended and multi-objective nature, where ideas should balance novelty, plausibility and feasibility. While recent LLM-based approaches have made progress through carefully designed
prompts or
agent pipelines, they are constrained by predefined, static ideation workflows. To address this limitation, we propose MindFlow, a framework that explicitly formulates ideation as a graph-structured Flow in Mind, which is composed of modular thinking operators and modeled by a probabilistic mind supernet. Given a research topic, a controller dynamically samples thinking flows to generate candidate ideas. This open-ended problem is optimized using a tournament-based relative ranking, enabling the controller to progressively favor higher-quality thinking flows. We further introduce an evaluation protocol that jointly assesses problem finding and problem solving, going beyond title- or abstractonly judgments. Across diverse topics, MindFlow shows its superiority as an explicit, controllable and optimizable research idea innovator.
Read the full abstract ▾
All authors Mengdi Liu, Wenjue Chen, Wenyue Chen, Cheng Yang, Fanqi Kong, Zhangyang Gao, Xiaoxue Cheng, Yiheng Li, Yujian Yuan, Keliang Li, Hong Chang, Shiguang Shan, Chenglin Wu
Artificial Intelligence · Cross-listed from cs.SE
Can LLMs Fix It Without Code? Toward Automated Verification of No-Code Bug Fixes
Utku Boran Torun, Veli Karakaya and Eray Tüzün
A no-code fix resolves an invalid bug report by directing the user to change a setting, update to a version where the problem is already fixed, or adjust their workflow. Manually verifying whether a proposed no-code fix resolves the reported bug takes considerable developer time. This study proposes an automated, execution-based pipeline for evaluating the capability of large
language models (LLMs) to generate no-code fixes in a real browser environment. We evaluate 322 no-code fixes generated by the 12 configurations released with the
benchmark of a previous study, covering bug reports categorized as Faulty Configuration, Wrong Version, or External System & Dependency. An executor
agent applies each fix by following its natural-
language instructions, and an issue-specific checker determines whether the reported bug persists. We repeat the pipeline with three executors: two Computer-Use
Agents, OpenCUA-72B and Claude Sonnet 5, and one
multimodal agentic LLM, Meta's Muse Glimmer. Only 17.6% of the candidate issues could be set up and passed both sanity gates. Across the 322 fixes, 14.6% to 49.7% resolved the bug depending on the executor, and the strongest configuration, Claude Opus 4.6 in the Vanilla pipeline, resolved up to 74.1% of its fixes under Claude Sonnet 5. Changing only the executor shifted a configuration's resolution rate by 38.8% on average, and the three executors reached the same verdict on only 46.9% of the fixes. Compared with human execution, the executors matched the human consensus for 66.1% to 88.1% of the sampled fixes. Even under the best executor, fewer than half of the LLM-generated no-code fixes resolve the reported bug, so such fixes need verification before they reach users. Execution-based verification can provide this, but the measured capability depends strongly on the executor, which evaluations must report and control.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Stochastic Grouping Conformal Prediction for Effective Subgroup Reliability
Meihui Zhong, Wenxin Tai, Ting Zhong et al. (+1 more)
Conformal prediction offers a distribution-free coverage guarantee, making it especially attractive for clinical applications. Standard conformal prediction, however, provides such guarantees only at the population level, and its prediction sets can exhibit coverage disparities across clinically important subgroups. A natural remedy is to calibrate within predefined groups. However, this can require access to sensitive subgroup attributes and is prone to a worst-group bottleneck: protecting the most difficult subgroup can inflate prediction sets for all, increasing cognitive burden on decision makers. To this end, we propose
Stochastic Grouping Conformal Prediction (SGCP), a conformal framework for subgroup-reliable uncertainty quantification. It learns a
stochastic grouping map that allows each sample to draw calibration information from others with similar calibration behavior, yielding a local score law that boosts reliability across subpopulations. We prove that SGCP retains the standard coverage guarantee. Experiments on synthetic and real-world
benchmarks show that it consistently reduces subgroup coverage gaps while achieving smaller or comparable prediction set sizes relative to existing baselines.
Read the full abstract ▾
All authors Meihui Zhong, Wenxin Tai, Ting Zhong, Fan Zhou
Artificial Intelligence · Cross-listed from q-bio.NC
Neural Decoding as Cognitive Inference
Yi Guo, Changhong Jing, Yong Hu et al. (+4 more)
The
brain maintains stable cognition despite continuously changing neural activity. How to extract stable cognitive states from variable neural observations remains a central problem in neural decoding. Existing neural decoding methods map neural observations to predefined external labels based on the stimulus-response principle, often capturing recording-specific spurious correlations. Inspired by how the
brain infers the world, and specifically by
Bayesian brain theory, we recast neural decoding as cognitive inference constrained by
brain-intrinsic priors, yielding high-level meta-neural semantic representations. In decoding experiments spanning five neural recording modalities and three cognitive domains (motor, perception and internal mentation), our cognitive inference method reorganized the geometry of neural observation representations, yielding meta-neural semantic representations that exhibited consistent
geometric relationships across cognitive tasks and enabled the recovery of stable cognitive states from variable neural observations. Our work provides an account of how the
brain maintains relatively stable cognition despite continual changes in the external environment. Cognitive stability is sustained through cognitive inference from changing neural activity, without requiring fixed neural activity patterns.
Read the full abstract ▾
All authors Yi Guo, Changhong Jing, Yong Hu, Yan Liu, Michael K. P. Ng, Shanshan Wang, Shuqiang Wang
Artificial Intelligence · Cross-listed from cs.MM
From Surface to Depth: Towards Cognitive Appraisal Reasoning in Multimodal Emotion Understanding
Jia Li, Yichao He, Yangchen Yu et al. (+6 more)
Recent
multimodal large
language models (MLLMs) increasingly incorporate explainable
reasoning for emotion understanding. However,
reasoning based mainly on observable affective cues can reduce emotion understanding to superficial cue-label associations, giving rise to the Clever Hans effect. Such shortcuts become unreliable when affective cues are implicit, conflicting across modalities, linguistically misleading, or obscured by redundant details. In contrast, human emotions are shaped by how individuals interpret and evaluate surrounding events beyond observable cues. Inspired by appraisal theories of emotion, we formulate
multimodal emotion understanding as a progression from perception to cognitive appraisal, and introduce a
dataset, a model, and a
benchmark to support this novel paradigm. CogEmo-40K is a large-scale instruction-tuning
dataset constructed through a perception-to-appraisal pipeline to elicit evidence-grounded
reasoning across six cognitive appraisal dimensions underlying emotion. CogEmo-MoE is a compact sparse MLLM that introduces interleaved MoE blocks for appraisal-specific adaptation, enabling effective appraisal
reasoning at a substantially smaller scale than typical emotion MLLMs. CogEmo-Bench introduces an Appraisal Evidence Quality Score (AEQS) to assess cognitive-affective understanding across six complementary appraisal dimensions, addressing the limitation of conventional emotion metrics that evaluate what emotion is predicted but not why it arises. Extensive experiments show that our paradigm not only leads CogEmo-Bench, but also exhibits strong cross-domain generalization. Our findings suggest that perception-to-appraisal
reasoning can move beyond surface-level cue-label associations toward more reliable
multimodal emotion understanding and closer cognitive
alignment between MLLMs and humans.
Read the full abstract ▾
All authors Jia Li, Yichao He, Yangchen Yu, Qiankun Li, Xinyi Li, Baiyi Ye, Zhenzhen Hu, Richang Hong, Erik Cambria
Artificial Intelligence · Cross-listed from cs.CV
Beyond Visual Enhancement: Adaptive Multi-Context Steering to Mitigate LVLM Hallucinations
Shuran Ma, JiaLe Li, Yuxin Dong et al. (+9 more)
Hallucination remains a significant challenge in Large
Vision-
Language Models (LVLMs). Existing training-free methods generally mitigate
hallucinations through contrastive decoding or visual enhancement, often increasing the relative influence of visual evidence during generation. This raises a fundamental question: Can LVLMs dynamically regulate the contributions of different context sources to suppress
hallucinations? In this work, we investigate and quantify how LVLMs coordinate multiple context sources during decoding and examine how this intrinsic behavior can guide
hallucination mitigation. We find that LVLMs exhibit an intrinsic
vision-attending tendency that can guide adaptive visual steering, while textual contexts can also contribute to
hallucination mitigation. Motivated by these findings, we propose AIMS (Adaptive Information Multi-source Steering), a lightweight training-free framework that adaptively coordinates visual, prefilled textual, and generated contexts during decoding. Specifically, AIMS constructs compact prototypes for the three context domains and estimates their affinities with the current query to determine head-wise steering weights. The resulting multi-source steering direction is applied to the query representation, enabling adaptive context integration without additional model training or auxiliary forward passes. Extensive experiments across multiple LVLMs and decoding strategies demonstrate that AIMS effectively mitigates object
hallucination while maintaining competitive general-purpose
multimodal capabilities.
Read the full abstract ▾
All authors Shuran Ma, JiaLe Li, Yuxin Dong, Shan Zheng, Qingyun Jiang, Xiang Chen, Qi Zhu, Deyi Ji, Yifan Yang, Jianfeng Pan, Yu Tian, Xue Yang
Artificial Intelligence · Cross-listed from cs.CL
Forms of LLM-Integrated Applications from LLM-Chats to Autonomous AI Agent System
Irene Weber
Large
language models (LLMs) are increasingly embedded as components in software systems, marketed under labels such as chatbot, copilot,
retrieval-augmented generation, workflow, coding
agent and AI
agent. Whether these labels denote genuine architectural forms or serve as branding has not been assessed systematically. In the sources surveyed, labels do carry architectural content, most clearly in vendor usage: copilot denotes a router-worker architecture operating a host application under step-by-step user confirmation, while the more recent shift to the label
agent coincides with AI-planned multi-step execution of which the user sees only the outcome. The coding
agents of four major providers share one architecture, a reason-and-act loop delegating to subagents. This survey describes seven recurring forms—LLM chats, custom
agents,
retrieval-augmented generation (RAG), AI-enhanced workflows, copilots, coding
agents, and, in part, agentic RAG—in a common vocabulary of
agents and tools. Each is characterized along four structural dimensions (agentic RAG only partially): the architectural pattern, the control of execution and the point of user intervention, the number of
agent calls per task, and tool use. An illustrative corpus of 22 systems from research publications and vendor documentation grounds the descriptions and shows where they reach their limit.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SE
Evaluating Exact Output and Checkpoint-State Prediction in Real Programs
Xiaohong Chen, David Bucur, Chenglong Ma et al. (+4 more)
We present a
benchmark for predicting final output and checkpoint state from source and input alone. It extends CRUXEval-style output prediction with paired shorter- and longer-trace inputs and checkpoints inside and after a loop. The
benchmark contains 400 cases from 371 Python and C++ programs, evaluated under seven settings from four model families without tools or code execution. Of 11,200 planned predictions, 11,151 produced gradable responses.
Reasoning-enabled settings outperform their off counterparts by 33.1 to 55.2 percentage points on completed responses. The strongest setting scores 93.0% on shorter-trace final output, 77.0% on longer-trace final output, and 65.5% and 63.5% on the two state tasks; these scores also hold when missing responses count as wrong. Across 2,397 matched Python comparisons with identical source, changing to the longer-trace input yields 528 correct-to-wrong changes and 147 reversals. Source-clustered analyses preserve this accuracy gap, while adjusted Python models give no evidence of a positive incremental association between cumulative state load and error. Changed inputs and checkpoint tasks alter several factors together, so the gaps do not isolate trace length or an internal state-tracking mechanism. The
benchmark exposes errors hidden by short-output scores alone.
Read the full abstract ▾
All authors Xiaohong Chen, David Bucur, Chenglong Ma, Yi Zhang, Lingming Zhang, Sriram Vishwanath, Grigore Rosu
Artificial Intelligence
How Is Automated Research Evaluated? A Survey of Benchmarks and Evaluation Practices
Liulei Zhang, Dejing Zhou, Chuyue Huang et al. (+5 more)
Automated research systems support literature synthesis, ideation, experiments, writing, and peer review, but their evaluation is dispersed across tasks,
benchmarks, and studies that are difficult to compare directly. We review this literature from the perspective of evaluation design and evidence, covering six targets: literature synthesis, research ideation, executable workflows, scholarly writing and communication, automatic peer review, and end-to-end research. We compare task construction, evidence sources, evaluators, and scoring procedures to explain the capabilities assessed by different designs. Our synthesis highlights three recurring lessons: output checks, process checks, and human studies provide complementary information; evaluator calibration is specific to the property being assessed; and resource budgets and attempt selection are integral to interpreting performance comparisons. We identify diagnostic evaluation designs and documented gaps in supporting evidence, and translate these comparisons into reporting and audit recommendations for specific evaluation settings. The survey helps readers navigate existing evaluations, select appropriate
benchmarks, and design subsequent studies.
Read the full abstract ▾
All authors Liulei Zhang, Dejing Zhou, Chuyue Huang, Guanhua Chen, Yutong Yao, Lidia S. Chao, Chi Man Vong, Derek F. Wong
Artificial Intelligence
LEVER: Adaptive Cost-Aware Proof Search Over AND/OR Graphs
Nihal Jain, Shuangjie Yao, Begum Cicekdag et al. (+2 more)
Mathematicians value proofs for more than correctness: among correct proofs, simplicity, purity and the computational cost of finding them vary widely. Yet LLM-powered
theorem provers largely search for any correct proof, and improve its quality only after it is found. We propose LEVER, a proof search
algorithm that makes the objective over correct proofs programmable and optimizes it during search. LEVER scores partial proofs over an AND/OR proof graph, combining realized objective values with predictions for open subgoals, so the objective guides search before a proof is complete. The same mechanism optimizes computational cost, proof length, topical impurity, and even their weighted combinations, while the Lean kernel enforces correctness. On PutnamBench in Lean 4, under matched budgets, LEVER costs 34% less than a strong single-conversation
agent while raising the solve rate from 80% to 96%. On reducing topical impurity, i.e., how far a proof strays from its
theorem's subject, it improves over post-hoc refactoring (42% reduction against 33%) at two-thirds of the cost and more reliably; on proof length, the metric refactoring is built for, it approaches refactoring. Varying the objective's weights traces a quality-cost trade-off curve, so the user can choose how much a better proof is worth. Overall, LEVER is a performant, cost-efficient and tunable proof search
algorithm for navigating the space of correct proofs.
Read the full abstract ▾
All authors Nihal Jain, Shuangjie Yao, Begum Cicekdag, Zhuo Zhang, Suman Jana
Artificial Intelligence · Cross-listed from cs.SE
Trajectory-Guided Fault Localization for Agent Skill Evolution
Yu Ge, Linna Xie, Zhong Li et al. (+2 more)
Agent skills provide reusable guidance for code
agents, but incomplete or unsuitable guidance can impair task execution. To reduce the manual effort of skill refinement, recent approaches use LLMs to generate revisions from execution feedback. However, grounding these revisions in explicit behavioral evidence remains challenging. To address this gap, we propose SkillMorph, a skill-
evolution approach based on trajectory-guided fault localization in
agent skills. Its core idea is to link execution evidence to specific skill contents before generating revisions. Specifically, SkillMorph compares failure and success evidence in abstracted trajectories across repeated runs and tasks, incorporating changes between
evolution loops to identify suspicious actions. It then uses these suspicious actions to localize edit sites in the skills and generate corresponding revisions. Experiments on SWE-Skills-Bench and CannBot show that the skills evolved by SkillMorph consistently achieve higher trial-level accuracy and execution consistency than the original skills and those from four existing skill-
evolution methods. We have also applied SkillMorph to automated kernel generation with an AI operator-development team, which has accepted 6 skill-revision pull requests.
Read the full abstract ▾
All authors Yu Ge, Linna Xie, Zhong Li, Yu Pei, Tian Zhang
Artificial Intelligence · Cross-listed from cs.LG
GRPODropout: Less is More for Online Reinforcement Learning Rollouts
Hexuan Deng, Zihao Yan, Xuebo Liu et al. (+8 more)
Reinforcement learning (RL) methods such as GRPO substantially improve large
language model
reasoning but often suffer from policy
entropy collapse: the loss of sampling diversity weakens exploration and limits further improvement. Existing methods address this issue either through
algorithm-level interventions, such as reward modification and
entropy/KL regularization, or through
token-level reweighting. We investigate a complementary perspective:
entropy collapse can also be mitigated by changing which generated rollouts contribute to policy updates. Under the same sampling budget, not all rollouts contribute positively to an update, and selectively excluding some can improve learning. To address this, we propose GRPODropout: before the standard update, we use a simple strategy that selectively removes a small number of high-probability positive-advantage rollouts and recenters the retained advantages. To motivate this design, we develop a rollout-level theoretical analysis that guides method design and threshold selection. The method changes only rollout usage, and adds negligible computational overhead. Experiments show higher accuracy than original GRPO and higher actor
entropy while using fewer rollout samples for updates, illustrating "less is more." This work provides insight into RL rollout usage: removing some rollouts can improve performance. Code is available at https://github.com/hexuandeng/GRPODropout/.
Read the full abstract ▾
All authors Hexuan Deng, Zihao Yan, Xuebo Liu, Shuo Nie, Yue Wang, Chen Wang, Zhaohua Zhang, Tianwen Jiang, Qiuyong Xiao, Jihong Zhang, Min Zhang
Artificial Intelligence
Probability-Signature Dynamics: Unpacking Modular Addition Learning Within Two-Layer Networks
Yunji Wang, Junjie Yao, Linyu Liu et al. (+2 more)
Neural networks trained on modular addition tasks often develop
Fourier-structured representations that support exact generalization. While prior work has identified these
Fourier circuits, the mechanism by which gradient-based training selects them from the data distribution remains unclear. We address this question using probability signatures, which express leading gradient interactions through conditional statistics of the training distribution. For modular addition, these signatures are cyclic shift operators and are diagonalized by the discrete
Fourier transform, yielding approximately decoupled
Fourier-mode dynamics. This explains the emergence of
Fourier sparsity, frequency matching, and phase
alignment. The same framework resolves a puzzle under label noise: corrupted examples can show faster early loss decrease than clean examples, despite lacking a coherent generalization rule. We show that noise increases conditional label collisions, strengthening early shared-coordinate reinforcement. Finally, this method can be applied to other operators. Taking XOR as an example, we observed the predicted frequency in experiments.
Read the full abstract ▾
All authors Yunji Wang, Junjie Yao, Linyu Liu, Pinyan Lu, Zhi-Qin John Xu
Artificial Intelligence · Cross-listed from cs.CV
From Suppression to Repair: Mitigating Object Hallucination in Large Vision-Language Models via Localized Distribution Alignment
Chen Zhao, Xingping Dong, Jiachun Shi et al. (+5 more)
Object
hallucination remains a major obstacle for large
vision-
language models (LVLMs) to generate reliable content. An intuitive mitigation strategy is to suppress
hallucination-related components in hidden representations. However, these components may also contain useful information, and suppressing them can weaken the model's
multimodal capabilities. In this paper, we propose ResOT, a training-free method that repairs representations at inference time through localized distribution
alignment. Specifically, ResOT projects dominant hallucinated directions away from the faithful subspace, forming a low-dimensional residual subspace for intervention. Within this subspace, ResOT uses Gaussian optimal transport (OT) to align the hallucinated distribution with the faithful one. The resulting map defines repair targets with minimal changes to the original representations. At inference, ResOT adaptively controls how far each
token state moves toward its OT target. Experiments on three representative LVLMs show that ResOT substantially reduces object
hallucination while improving image caption quality and
multimodal performance across multiple
benchmarks. Code will be released.
Read the full abstract ▾
All authors Chen Zhao, Xingping Dong, Jiachun Shi, Liang Peng, Chong Wang, Zhen Lei, Ran He, Bo Du
Artificial Intelligence · Cross-listed from cs.CV
From Pixels to Structure: Lightweight Vision-Language Models for Document OCR and Structured JSON Extraction
Uddipan Basu Bir, Vincent Christlein, Andreas Maier et al. (+1 more)
While massive, closed-source
Vision-
Language Models (VLMs) set strong
benchmarks for document understanding, their dependence on commercial APIs limits adoption in institutional archives due to data autonomy concerns, recurring costs, and the environmental footprint of hyperscale computing. This is especially acute in heritage digitization, where documents include historical handwriting, domain-specific terminology (e.g., jewelry, prehistory, architecture), and non-standard layouts requiring high-dimensional structured extraction. We present a comparative study of eight open-source lightweight VLMs (up to 7B parameters) for Optical Character Recognition (OCR)-to-structure across three university heritage collections. Given a document image, models must extract text and generate schema-compliant JSON, enabling automatic validation and downstream use. We evaluate models under a constraint-aware protocol across zero-shot, few-shot, and fine-tuning settings, measuring extraction fidelity and structured-output quality using Character Error Rate (CER), Approximate Normalized Levenshtein Similarity (ANLS*), and mean Average Precision F1 (mAP-F1). Against a fine-tuning baseline, we further test the independent impact of (i) hyperparameter optimization, (ii) classical image preprocessing (illumination flattening, denoising, and CLAHE), and (iii) multi-stage training. Finally, we analyze the trade-off between
dataset-specific fine-tuning and a single multi-
dataset checkpoint, where joint training enables one model to operate across collections but can shift performance between
datasets. Overall, we show that carefully adapted VLMs with up to 7B parameters can provide a sustainable, private, high-performing alternative to manual transcription or commercial black-box systems, and we offer actionable guidance for heritage institutions seeking institution-controlled OCR-to-JSON extraction.
Read the full abstract ▾
All authors Uddipan Basu Bir, Vincent Christlein, Andreas Maier, Mathias Zinnen
Artificial Intelligence
Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks
Haoyu Zhao, Zhengxu Yu, Zhiyuan He et al. (+5 more)
Learning to act in unfamiliar environments requires
agents to infer how the world works and revise that understanding as new evidence arrives. Yet limited observations can support multiple world models that explain past interactions but predict different outcomes in unseen states. We introduce Memento 3, building on the Memento series to enable frozen LLM
agents to continually learn explicit world models through external
memory. The
agent maintains a natural-
language rulebook as persistent semantic
memory, recording revisable hypotheses about environment dynamics while leaving unknown aspects underspecified. It compiles this rulebook into executable code for prediction and planning. Through a continual loop of observation, reflection, rule revision, compilation, and verification, the
agent uses prediction errors to refine both the rulebook and its code. Updated code is accepted only when the LLM judges it faithful to the rulebook and
cell-exact replay reproduces the observed transitions. We investigate this process as a model-based route to recursive self-improvement (RSI): the
agent autonomously explores the environment, revises its world model, and uses verified updates to guide subsequent interaction and learning, while the underlying LLM remains fixed. A population extension maintains multiple world models in parallel, sharing interaction evidence and using their predictions to guide exploration. On ARC-AGI-3, the single-model
agent clears every level of all 25 public games, achieves a mean Relative Human Action Efficiency (RHAE) of 100.0, and uses 44% of the human action count. In an Atari Pong case study, a learned feedback controller wins 21:0 in each of three evaluated episodes with different openings, without further LLM calls.
Read the full abstract ▾
All authors Haoyu Zhao, Zhengxu Yu, Zhiyuan He, Meng Fang, Rasul Tutunov, Haitham Bou-Ammar, Weilin Luo, Jun Wang
Artificial Intelligence · Cross-listed from cs.MM
AuraLuxMuse: Adaptive Fusion Modeling for Aesthetic Stage Lighting Design with Music and Expert Guidance
Junyu Deng, Jiale Cao, Mengtian Li et al. (+5 more)
We present AuraLuxMuse, a novel system for automated aesthetic stage lighting design that integrates expert knowledge, representation learning, and preference-adaptive modeling. Lighting design in live performance settings requires the seamless translation of musical features into dynamic lighting behaviors. However, traditional workflows remain time-consuming, labor-intensive, and difficult to transfer. AuraLuxMuse encodes music and professional cue sequences into a shared
retrieval space, estimates cue-event density, and retargets selected fixture commands to the destination stage. It assists pre-production authoring by returning editable cues rather than replacing the designer with an unconstrained generator. At the heart of AuraLuxMuse are two key modules: Lighting-Aligned Music Pretraining (LAMP), which performs contrastive learning between audio and lighting cues for
alignment, and Preference-Adaptive Mixture of Experts (PAMoE), which conditions preference-aware cue
retrieval and adaptation on designers' intent through a gated ensemble of style-specific expert networks. To support training and evaluation, we introduce Musilux, the first
dataset of paired musical audio and professional lighting cue sequences under diverse performance scenarios. We evaluate AuraLuxMuse across both virtual simulation environments and professional-grade laboratories. Experimental results, including objective and subjective evaluation, demonstrate that AuraLuxMuse retrieves and adapts stage-lighting cues that are visually cohesive, semantically meaningful, and artistically expressive, showing its potential for AI-assisted aesthetic stage design.
Read the full abstract ▾
All authors Junyu Deng, Jiale Cao, Mengtian Li, Zhongxia Ji, Ruhua Chen, Yiyi He, Guangnan Ye, Zuo Hu
Artificial Intelligence
RouterInterp: Understanding Superposed Specialisation in Mixture of Experts Routing
Ilya Lasy, Nora Yinuo Cai and Kola Ayonrinde
Sparse Mixture of Experts (MoE) models scale more efficiently than dense models by routing
tokens to modular expert networks that are only active for processing a fraction of
tokens. A leading hypothesis for the performance of MoE models is that each expert specialises in a single, coherent domain. However, interpretability efforts that assume this hypothesis have generally been unsuccessful. We propose and present evidence for an alternative account that we call the Superposed Specialisation Hypothesis (SSH): experts specialise in a disjoint union of fine-grained features rather than one broad domain. Leveraging the SSH, we introduce RouterInterp, a method for interpreting expert routing that identifies Sparse Autoencoder features most predictive of routing decisions and produces unified natural
language explanations. On gpt-oss-20b, RouterInterp explains expert routing with ${\sim}65\%$ higher detection accuracy than prior
token statistics based methods. This work provides a scalable method for generating more accurate explanations of expert routing and increases our understanding of a previously uninterpretable component of foundation models.
Read the full abstract ▾
Artificial Intelligence
Safe Actions Alone Do Not Ensure Safe Agents: Identifying Unfulfilled Obligations with Guard Models
Youwei Feng, Yitong Zhang, Yuetong Liu et al. (+1 more)
Guard models are increasingly used to safeguard LLM-based
agents, primarily by identifying actions that
agents are forbidden to perform. However, identifying forbidden actions alone is insufficient to ensure
agent safety. In this paper, we argue that
agent safety also depends on identifying required yet unperformed safety-critical actions, which we call obligations. Our preliminary study on a popular
benchmark for evaluating safety shows that 56.92% of GLM-5.3 trajectories contain unfulfilled obligations, compared with only 30.00% containing forbidden actions. This finding reveals unfulfilled obligations as a major and previously overlooked source of safety risk. However, to our knowledge, no existing
benchmark evaluates whether guard models can identify these obligations. To close this gap, we introduce ObligationBench, the first
benchmark for evaluating the capability of obligation identification, comprising 240 expert-validated trajectories covering issue resolution, feature development, and terminal operations. Our evaluation of 14 representative models reveals substantial limitations: the highest recall and exact-match rate are only 48.97% and 10.00%, respectively. To address these limitations, we develop ObligationGuard using 40,000 synthetic training examples. ObligationGuard achieves 57.52% recall and an exact-match rate of 21.67%, surpassing all evaluated models on both metrics. We call on the community to incorporate obligation identification into the design and evaluation of future guard models to improve
agent safety.
Read the full abstract ▾
All authors Youwei Feng, Yitong Zhang, Yuetong Liu, Jia Li
Artificial Intelligence · Cross-listed from eess.SY
Narrow and Deep: An Ontology Tower as the Knowledge of an LLM Agent for an Industrial Equipment System
Younghwan Joo and Sung-il Kim
Large
language model (LLM)
agents are beginning to operate industrial energy equipment, and what they get right depends on what they are told about the plant. Established building ontologies name many kinds of points across many sites, whereas an industrial equipment system needs few entities with much knowledge about each. This study proposes the ontology tower, a narrow-and-deep ontology of a single equipment system whose knowledge deepens in two ways: through quantities derived from the measured points by physical relations, and through lessons from the operating journal incorporated as knowledge nodes. On a real low-humidity air-handling test plant operated daily through a programmable logic controller,
agents received a text projected from its tower in a preregistered evaluation of nine tasks replayed from the plant's records, using four open-weight models from 9 to about 750 billion parameters. This knowledge raised the rate at which the
agents avoided the most plausible misjudgment of each task by about 20 percentage points, and the overall task score of the 9-billion-parameter model as much as that of the largest. Operating lessons were used when incorporated into the tower or placed in the
prompt as records, but seldom when left in the journal behind a search tool. In live runs through an invariant safety layer, the
agents brought the controlled variable into its target band in 12 of 14 runs. An ontology narrow in entities but deep in what is known about them can thus supply the knowledge that an
agent for an industrial equipment system needs.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Same Outcome, Different Evidence: Intent Recovery in LLM Safety Evaluation
Haitong Jiang, Chunlin Liu, Sihan Tang et al. (+3 more)
Safety evaluations of large
language models commonly summarize harmful-output behavior with attack success rate (ASR). Yet the same non-harmful outcome can arise for very different reasons. A model may recover a harmful task and refuse it, fail to recover the task, or respond to something else entirely. Distinguishing these cases becomes especially important under intent-obscuring
prompts, where a low ASR does not reveal whether the evaluated task was actually engaged. To make this distinction explicit, we pair ASR with operative understanding rate (UR), which measures whether a response both identifies the evaluated task and treats it as the task to be answered. Across interfaces, this paired view reveals substantial variation hidden by ASR: similar ASR values can correspond to sharply different recovery rates. Controlled English reconstructions show that recovery consistently improves as compressed
prompts become more explicit, whereas ASR does not follow the same pattern. A complementary contrast comes from FormalLogic, where high recovery can still coincide with frequent harmful assistance. Together, these results show that non-harmful outcomes are not equally informative about model safety, motivating the joint reporting of intent recovery and ASR in LLM safety evaluation. Code and experiment inputs are available at https://github.com/kevinjiang0121-cyber/IRIS.
Read the full abstract ▾
All authors Haitong Jiang, Chunlin Liu, Sihan Tang, Chan Wu, Xiaoqing Su, Yuhong Feng
Artificial Intelligence
What Output-Only Review Cannot Verify: Study Contracts for Research Agents
Eitan Waks and Ben Glocker
Some defects in an AI-generated study can be identified from its artifacts; others require knowledge of what was approved before execution. We propose study contracts that bind declared experimental choices, run obligations and claim scope to recorded execution evidence, and distinguish this contract-relative verification from scientific truth. A diagnostic using eight self-authored clean/mutated pairs illustrates the information boundary. A deterministic checker applying a registered, fault-specific rule to approved and executed objects detected all eight registered mutations. Across eighteen recorded judge aliases given individual metadata-filtered packages without pair context or the registry-selected fault label, 104 of 144 mutated evaluation cases received defect flags; the remaining cases comprised 32 abstentions and eight terminal failures, with no explicit clean decisions on mutated cases. Some packages retained approval and execution fields, including digests. The
prompt instructed judges to abstain when evidence was insufficient. These results characterize a deliberately information-asymmetric development setting; they do not isolate the effect of authoritative information from differences in task specification and rule selection, and they are not comparative verifier quality or
agent reward hacking. We identify full-information comparisons, legitimate-adaptation controls and closed-loop
agent evaluations as necessary tests of whether contract checks improve useful compliant completion under optimization.
Read the full abstract ▾