arXiv cs.AI Artificial Intelligence

Xinrui Li, Pawan Sasanka Ammanamanchi, Siddharth Bhat, Rianna Jamdar, Yongxi Lin, Stella Biderman: SemantEq: Faithful Bidirectional Equivalence of Formal Statements https://arxiv.org/abs/2610.32919 https://arxiv.org/pdf/2610.32919 https://arxiv.org/html/2610.32919

Shubham Gupta, Siva Reddy, Perouz Taslakian, Valentina Zantedeschi, Cem Subakan: Closing the Modality Gap via Simplex-Constrained Representations https://arxiv.org/abs/2610.32890 https://arxiv.org/pdf/2610.32890 https://arxiv.org/html/2610.32890

Nilesh Prasad Pandey, Jangseon Park, Jason Kong, Onat Gungor, Tajana Rosing: NgramRL: Accelerating RL Post-Training for Structured Generation via Rollout-Aware N-gram Speculative Decoding https://arxiv.org/abs/2610.32881 https://arxiv.org/pdf/2610.32881 https://arxiv.org/html/2610.32881

Moritz Thoma, et al.: Advancing SVD-based LLM Compression via Layer-Wise Error Model Search https://arxiv.org/abs/2610.32878 https://arxiv.org/pdf/2610.32878 https://arxiv.org/html/2610.32878

Anouar Imel, Jin Qi: Do "True" and "False" Add Up to One? Complement Consistency in LLM-Agent Opinion Simulations https://arxiv.org/abs/2610.32874 https://arxiv.org/pdf/2610.32874 https://arxiv.org/html/2610.32874

Maxim Osovsky (Adam University, Bishkek, Kyrgyzstan): From Deliberately Constructed Systemic Representations of the World of Activity to Dialogue: A Five-Level Communication Architecture for ... https://arxiv.org/abs/2610.32869 https://arxiv.org/pdf/2610.32869 https://arxiv.org/html/2610.32869

Wenxin Chen, Kyra Gan, Mingyu Lu, Zilin Jing, Fei Wang, Hoifung Poon, Tristan Naumann, Peniel Argaw: A Foundation Model for Policy In-Context Longitudinal Causal Effect Estimation https://arxiv.org/abs/2610.32863 https://arxiv.org/pdf/2610.32863 https://arxiv.org/html/2610.32863

Garima Agrawal, et al.: Reimagining Enterprise RAG for Multi-Agent Systems: A Knowledge Layer That Organizes Before It Retrieves https://arxiv.org/abs/2610.32851 https://arxiv.org/pdf/2610.32851 https://arxiv.org/html/2610.32851

Yuhua Jiang, Chang Xu, Feifei Gao, Li Zhao: HarnessMM: Recursive Self-Improvement for Harness Token Efficiency https://arxiv.org/abs/2610.32813 https://arxiv.org/pdf/2610.32813 https://arxiv.org/html/2610.32813

Navyansh Mahla, Sashank Vandrangi: ActionRAG: Evidence-Refining Graph Diffusion for Long-Term Memory in LLM Agents https://arxiv.org/abs/2610.32752 https://arxiv.org/pdf/2610.32752 https://arxiv.org/html/2610.32752

Sidi Wu, Lifeng Lin, Yizi Chen, Anna Yokokubo, Lorenz Hurni: Agentic Hazard Mapper: Emulating Expert Map-Making with AI Agents for Risk Communication https://arxiv.org/abs/2610.32738 https://arxiv.org/pdf/2610.32738 https://arxiv.org/html/2610.32738

Moon, Lee, Lee, Battsengel, Kim, Yun, Jeon, Kim, Park, Song: Retiming Robot Demonstrations with a Learned Speed Prior https://arxiv.org/abs/2610.32676 https://arxiv.org/pdf/2610.32676 https://arxiv.org/html/2610.32676

Alisson Rosa Pereira, Bruno Iochins Grisci: Do Language Models Trust Their Own Justifications? A Study on Functional Consistency https://arxiv.org/abs/2610.32665 https://arxiv.org/pdf/2610.32665 https://arxiv.org/html/2610.32665

Chunchun Yang, Yang Cao, Zhitang Chen: WiMoT: Replay-Free Continual Wi-Fi Sensing via Moment Transport https://arxiv.org/abs/2610.32660 https://arxiv.org/pdf/2610.32660 https://arxiv.org/html/2610.32660

Zenghui Zhou, Xiaoke Fang, Zheng Zheng: LGMT: A Tool for Testing the Logical Reasoning Reliability of LLMs https://arxiv.org/abs/2610.32627 https://arxiv.org/pdf/2610.32627 https://arxiv.org/html/2610.32627

Zaifei Yang, Weiyu Chen, Yaqing Wang, James Kwok: What Transfers Across Protein Pockets? Experience Reuse in Molecular Optimization for Agentic Structure-Based Drug Design https://arxiv.org/abs/2610.32620 https://arxiv.org/pdf/2610.32620 https://arxiv.org/html/2610.32620

Zijian Jia, Peixuan Zhang, Genying Li, Di Wu, Yujie Fu, Si Li, Boxin Shi, Shuchen Weng: LLaCO: Continuous Diffusion for Large Language Models with Competition-Aware Semantic Scheduling https://arxiv.org/abs/2610.32604 https://arxiv.org/pdf/2610.32604 https://arxiv.org/html/2610.32604

Shrihari Vasudevan, H. G. Ranjani, Raaghul Ranganathan, Satwik Sahu, Thirumaran Ekambaram: Beyond Channel Data: Configuration-Enriched Radio Foundation Models https://arxiv.org/abs/2610.32542 https://arxiv.org/pdf/2610.32542 https://arxiv.org/html/2610.32542

Kyeongseon Kim, Jiyeon Son, Tae-Hyun Oh: IGG: A Benchmark for Interactive GUI Grounding under Visibility Constraints https://arxiv.org/abs/2610.32536 https://arxiv.org/pdf/2610.32536 https://arxiv.org/html/2610.32536

Zhang, Zhang, Shi, Li, Su, Li, Wang, Mu, Zhang, Chen, Zhang, Hu: When Agents Fail: Model or Harness--Who's to Blame? https://arxiv.org/abs/2610.32483 https://arxiv.org/pdf/2610.32483 https://arxiv.org/html/2610.32483

Siyu Wu, Zeyu Liang, Linghao Wang, Qiyun Zheng, Yi Yao, Ling Lo, Hongxia Xie: CASE: Confusion-Aware Skill Evolution for Frozen Multimodal Emotion Models https://arxiv.org/abs/2610.32481 https://arxiv.org/pdf/2610.32481 https://arxiv.org/html/2610.32481

Kaiwen Wu, Chaochao Lu: CauProphet: Teaching Agents to Develop Causal Cognition like Humans https://arxiv.org/abs/2610.32477 https://arxiv.org/pdf/2610.32477 https://arxiv.org/html/2610.32477

Tianyu Yang, Yijun Tian, Lars Benedikt Kaesberg, Jan Philip Wahle, Bela Gipp, Terry Ruas, Daniel Kurzawe: Beyond Post-Hoc Rewards: Privileged Reasoning Exploration for Multimodal Embeddings https://arxiv.org/abs/2610.32474 https://arxiv.org/pdf/2610.32474 https://arxiv.org/html/2610.32474

Micha{\l} Remigiusz Janiszewski, Artur Stopa, {\L}ukasz Lenkiewicz, Wojciech Achtelik, Bartosz Gonczarek: ALLMTS: Automated LLM-based Medical Triage System https://arxiv.org/abs/2610.32469 https://arxiv.org/pdf/2610.32469 https://arxiv.org/html/2610.32469

Zhang, Li, Chen, Liu, Hu, Peng, Zi, Liu, Huang, Tang, Li: POSEIDON: Scaling Training Environments for Scientific Agents from Code Repositories https://arxiv.org/abs/2610.32448 https://arxiv.org/pdf/2610.32448 https://arxiv.org/html/2610.32448

Zongyao Zhao, Cheng-Jie Zhao, Ruihang Jiang, Bing Zheng, Zhaolin Wang, Yuanwei Liu: When to Stop Penalizing Actions? Martingale GRPO for VLA Reinforcement Learning https://arxiv.org/abs/2610.32431 https://arxiv.org/pdf/2610.32431 https://arxiv.org/html/2610.32431

Detao Zeng, Guilin Ou, Nuo Chen, Yunhao Feng, Hongliang Wang, Qinli Yang, Junming Shao, Zhong Zhang: Async-RBench: Benchmarking Asynchronous Task Execution in LLM Agents https://arxiv.org/abs/2610.32429 https://arxiv.org/pdf/2610.32429 https://arxiv.org/html/2610.32429

Shen Liu, Ze Zhou, Zhenguo Xu, Shaopu Wang, Yike Gao, Chunlei Wang: LeafSkill: Efficient Leaf-Level Action Grounding for Recursive LLM Agents https://arxiv.org/abs/2610.32412 https://arxiv.org/pdf/2610.32412 https://arxiv.org/html/2610.32412

Ming Ze Tang, David Cutting, Boyd Carson, Vasiliki Carson: DealsFlow: An Evidence-Gated Agentic Harness for Venture Capital Deal Triage https://arxiv.org/abs/2610.32380 https://arxiv.org/pdf/2610.32380 https://arxiv.org/html/2610.32380

Shi, Li, Yu, Fu, Ding, Chen, Chen, Zhao, Liu: Adaptive Control of Scientific Instruments with Nonstationary Responses through Multimodal Agents https://arxiv.org/abs/2610.32370 https://arxiv.org/pdf/2610.32370 https://arxiv.org/html/2610.32370

Ioannis Kyprakis, Stefanos Gkikas, Chariklia Chatzaki, Zongyi Jiang, Randy Gomez, Raul Fernandez Rojas: FOCUS: A Lightweight Mamba-2 Model for EEG-Based Cognitive Workload Classification https://arxiv.org/abs/2610.32361 https://arxiv.org/pdf/2610.32361 https://arxiv.org/html/2610.32361

He, Zhu, Li, Tang, Jiang, Ma, Zhuo, Li: TGR-EvoDAG: A DAG-based Multi-Agent Code Evolution Framework for Generative Recommendation on Tencent https://arxiv.org/abs/2610.32326 https://arxiv.org/pdf/2610.32326 https://arxiv.org/html/2610.32326

Han, Liu, Chen, Zhang, Song, Yang, Shang, Ding, Guo, Zhang: From Visual Affinity to Learning Credit in Multimodal Reinforcement Learning https://arxiv.org/abs/2610.32324 https://arxiv.org/pdf/2610.32324 https://arxiv.org/html/2610.32324

Yanze Wang, Pengfei Yao, Tianyi Sun, Hongda Chen, Yunyun Han, Jun Sun, Chuanrui Hu, Yafeng Deng: Beyond Gain: Measuring Skill Internalization for Agent Skill Retirement https://arxiv.org/abs/2610.32322 https://arxiv.org/pdf/2610.32322 https://arxiv.org/html/2610.32322

Wang, Wang, Wang, Feng, Zhang, Ouyang, Wu, Wang, Zheng, Huang, Zhou: Solvent: Long-Horizon Reasoning for Multi-Step Retrosynthesis https://arxiv.org/abs/2610.32308 https://arxiv.org/pdf/2610.32308 https://arxiv.org/html/2610.32308

Shan Peng, Shuaiqi Cheng, Miao Peng, Chenyi Zi, Jia Li: DMAIC-Bench: From Self-Reflection to Self-Restraint for Agents in Multi-Stage Analytical Tasks https://arxiv.org/abs/2610.32305 https://arxiv.org/pdf/2610.32305 https://arxiv.org/html/2610.32305

Tianyi Xu, Huazheng Wang: Lifelong Context Adaptation through Bidirectional Memory-Skill Learning https://arxiv.org/abs/2610.32295 https://arxiv.org/pdf/2610.32295 https://arxiv.org/html/2610.32295

Zhiyong Cao, et al.: Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attribution https://arxiv.org/abs/2610.32285 https://arxiv.org/pdf/2610.32285 https://arxiv.org/html/2610.32285

Hongkang Chu, Yifan Shen, Tianjiao Yu, Zhuoqing Zhong, Jianguo Cao, Meihuan Huang, Xu Cao: MedCaseAgent: From Multimodal Clinical Evidence to Rare Disease Case Reports https://arxiv.org/abs/2610.32258 https://arxiv.org/pdf/2610.32258 https://arxiv.org/html/2610.32258

Wang, Wang, Ye, Li, Chen, Shi, Wang, Zhang, Wang, Wu, Qi, Cai, Gu, Zheng: RSIHub: A Composable Framework for Agent-Evolution Methods https://arxiv.org/abs/2610.32253 https://arxiv.org/pdf/2610.32253 https://arxiv.org/html/2610.32253

Wenbin Mao, Pei Zou: Minimum Description Length Unsupervisedly Separates Law-Grade from Statistical-Grade Knowledge in a Self-Improving Science Agent - and Reveals 86% of Its Own Discoveries ... https://arxiv.org/abs/2610.32245 https://arxiv.org/pdf/2610.32245 https://arxiv.org/html/2610.32245

Tong Li, Qingyang Xu: Spatial Heuristic Strategy based Diffusion Reinforcement Learning for Online 3D Bin Packing https://arxiv.org/abs/2610.32241 https://arxiv.org/pdf/2610.32241 https://arxiv.org/html/2610.32241

Hrishikesh Singh, Aarti Sharma, Millie Pant: Financial Context-Rich Strategy for Actor-Critic based Agents: A Deep Reinforcement Learning Approach for Stock Trading https://arxiv.org/abs/2610.32237 https://arxiv.org/pdf/2610.32237 https://arxiv.org/html/2610.32237

Han Wang, Zhitao Wang, Natalia Frumkin, Xuanwu Yin, Alireza Khodamoradi, Dong Li, Emad Barsoum: Training an MoE LLM in MXFP4: How We Closed the Gap to BF16 https://arxiv.org/abs/2610.32229 https://arxiv.org/pdf/2610.32229 https://arxiv.org/html/2610.32229

Xinhao Song, Haoxuan Peng, Su Su, Hongliang Wu, Sirui Song, Gongshen Liu, Linfeng Zhang, Dongrui Liu: Correct Answers, Closed Gates: SolveBind for GUI Agents at the Verification Barrier https://arxiv.org/abs/2610.32223 https://arxiv.org/pdf/2610.32223 https://arxiv.org/html/2610.32223

Jiaxing Sun, et al.: RxnExBench: Benchmarking Vision-Language Models for Structured Chemical Reaction Extraction from Scientific Literature https://arxiv.org/abs/2610.32221 https://arxiv.org/pdf/2610.32221 https://arxiv.org/html/2610.32221

Wang, Luo, Song, Shan, Zhao, Liu, Xing, Huo, Lin, Gu, Mu, Wang, Li, Zhu, Xiao: PEAR: Adaptive Advantage Reshaping for Perception and Exploration in Large Vision-Language Models https://arxiv.org/abs/2610.32216 https://arxiv.org/pdf/2610.32216 https://arxiv.org/html/2610.32216

Hyojun Kim, Hyeseon An, Yo-Sub Han: Watermarking Diffusion Language Models with Learned Foresight and Balanced Bands https://arxiv.org/abs/2610.32205 https://arxiv.org/pdf/2610.32205 https://arxiv.org/html/2610.32205

Victor Shea-Jay Huang, Rongqing Li, Zhangyue Yin, Kelong Mao, Yaqi Zhao, Xinyuan Wang, Yao Yin, Lirui Luo, Renrui Zhang, Hongsheng Li: SWE-Shift: Evaluating Coding Agents in Evolving Workspaces https://arxiv.org/abs/2610.32196 https://arxiv.org/pdf/2610.32196 https://arxiv.org/html/2610.32196

Adeyemi Adeseye, Aisvarya Adeseye, Hannu Tenhunen, Jouni Isoaho: Evidence-Grounded SLM Behavioral Prediction Architecture for Future Assistance Use https://arxiv.org/abs/2610.32193 https://arxiv.org/pdf/2610.32193 https://arxiv.org/html/2610.32193