大模型推理能力

Simple Vision-Language Math Reasoning via Rendered Text

Matvey Skripkin, Elizaveta Goncharova, Andrey Kuznetsov

机构 * FusionBrain Lab（融合脑实验室） ； HSE University（俄罗斯高等经济学院） ； Innopolis University（因诺波利斯大学） 纠错

专题命中 数学推理 ：reasoning(title,abstract)；math reasoning(title)；chain-of-thought(abstract)；分类 cs.LG

Mitigating Overthinking in Large Reasoning Models via Manifold Steering

Yao Huang, Huanran Chen, Shouwei Ruan, Yichi Zhang, Xingxing Wei, Yinpeng Dong

机构 * Institute of Artificial Intelligence, Beihang University（北京航空航天大学人工智能研究院） ； College of AI, Tsinghua University（清华大学人工智能学院） ； Shanghai Qi Zhi Institute（上海启智研究所） ； State Key Laboratory of Virtual Reality Technology and Systems, Beihang University（北京航空航天大学虚拟现实技术与系统国家重点实验室） 纠错

专题命中 数学推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 19 pages, 7 figures

KTAE: A Model-Free Algorithm to Key-Tokens Advantage Estimation in Mathematical Reasoning

Wei Sun, Wen Yang, Pu Jian, Qianlong Du, Fuwei Cui, Shuo Ren, Jiajun Zhang

机构 * Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所） ； School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院） 纠错

专题命中 数学推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

Comments NeurIPS 2025 Poster

The Good, The Bad, and The Hybrid: A Reward Structure Showdown in Reasoning Models Training

Subramanyam Sahoo

机构 * Berkeley AI Safety Initiative (BASIS) UC Berkeley（伯克利人工智能安全计划（BASIS）加州大学伯克利分校） 纠错

专题命中 数学推理 ：reasoning(title,abstract)；分类 cs.LG

Comments Paper accepted to the 2nd Workshop on Aligning Reinforcement Learning Experimentalists and Theorists (ARLET 2025) at NeurIPS; the paper consists of 14 pages (including the appendix) and contains 3 figures

GEM: Generative Entropy-Guided Preference Modeling for Few-shot Alignment of LLMs

Yiyang Zhao, Huiyu Bai, Xuejiao Zhao

专题命中 数学推理 ：reasoning(abstract)；chain-of-thought(abstract)；CoT(abstract)；分类 cs.AI、cs.LG

Comments This paper has been accepted by AAAI 2026-AIA and designated as an oral presentation paper

Chain-of-Conceptual-Thought Elicits Daily Conversation in Large Language Models

Qingqing Gu, Dan Wang, Yue Zhao, Xiaoyu Wang, Zhonglin Jiang, Yong Chen, Hongyan Li, Luo Ji

机构 * Geely AI Lab（Geely人工智能实验室） ； Beijing Institute of Technology（北京理工大学） 纠错

专题命中 数学推理 ：reasoning(abstract)；chain-of-thought(abstract)；CoT(abstract)；分类 cs.CL

Comments PRICAI 2025

Tailored Primitive Initialization is the Secret Key to Reinforcement Learning

Yihang Yao, Guangtao Zeng, Raina Wu, Yang Zhang, Ding Zhao, Zhang-Wei Hong, Chuang Gan

机构 * Carnegie Mellon University（卡内基梅隆大学） ； Massachusetts Institute of Technology（麻省理工学院） ； MIT-IBM Watson AI Lab（MIT-IBM沃森人工智能实验室） 纠错

专题命中 数学推理 ：reasoning(abstract)；logical reasoning(abstract)；分类 cs.LG

P1: Mastering Physics Olympiads with Reinforcement Learning

Jiacheng Chen, Qianjia Cheng, Fangchen Yu, Haiyuan Wan, Yuchen Zhang, Shenghe Zheng, Junchi Yao, Qingyang Zhang, Haonan He, Yun Luo, Yufeng Zhao, Futing Wang, Li Sheng, Chengxing Xie, Yuxin Zuo, Yizhuo Li, Wenxauan Zeng, Yulun Wu, Rui Huang, Dongzhan Zhou, Kai Chen, Yu Qiao, Lei Bai, Yu Cheng, Ning Ding, Bowen Zhou, Peng Ye, Ganqu Cui

机构 * Shanghai AI Laboratory（上海人工智能实验室） 纠错

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

HAPO: Training Language Models to Reason Concisely via History-Aware Policy Optimization

Chengyu Huang, Zhengxin Zhang, Claire Cardie

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

SelecTKD: Selective Token-Weighted Knowledge Distillation for LLMs

Haiduo Huang, Jiangcheng Song, Yadong Zhang, Pengju Ren

机构 * Institute of Artificial Intelligence and Robotics（人工智能与机器人研究院） 纠错

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Evaluating Large Language Models for Workload Mapping and Scheduling in Heterogeneous HPC Systems

Aasish Kumar Sharma, Julian Kunkel

机构 * Faculty of Mathematics and Computer Science, Georg-August-Universität Göttingen（数学与计算机科学学院，哥廷根乔治-奥古斯特大学） 纠错

专题命中 数学推理 ：reasoning(abstract,comments)；分类 cs.AI

Comments 14 pages, 4 figures, 2 tables. Evaluation study on LLM-based reasoning for HPC scheduling. Published in Research in Academic Engineering Journal (RAEJ), 2025

Journal ref Robot Autom Eng J. 2025; 6(5): 555696

Scaling Generative Verifiers For Natural Language Mathematical Proof Verification And Selection

Sadegh Mahdavi, Branislav Kisacanin, Shubham Toshniwal, Wei Du, Ivan Moshkov, George Armstrong, Renjie Liao, Christos Thrampoulidis, Igor Gitman

机构 * NVIDIA ； University of British Columbia（不列颠哥伦比亚大学） ； Institute for AI R&D of Serbia（塞尔维亚人工智能研究与发展研究所） 纠错

专题命中 数学推理 ：reasoning(abstract)；分类 cs.AI

PurpCode: Reasoning for Safer Code Generation

Jiawei Liu, Nirav Diwan, Zhe Wang, Haoyu Zhai, Xiaona Zhou, Kiet A. Nguyen, Tianjiao Yu, Muntasir Wahed, Yinlin Deng, Hadjer Benkraouda, Yuxiang Wei, Lingming Zhang, Ismini Lourentzou, Gang Wang

专题命中 代码与定理证明 ：reasoning(title,abstract)；分类 cs.CL、cs.LG

Think with Self-Decoupling and Self-Verification: Automated RTL Design with Backtrack-ToT

Zhiteng Chao, Yonghao Wang, Xinyu Zhang, Jiaxin Zhou, Tenghui Hua, Husheng Han, Tianmeng Yang, Jianan Mu, Bei Yu, Rui Zhang, Jing Ye, Huawei Li

专题命中 代码与定理证明 ：reasoning(abstract)；chain-of-thought(abstract)；CoT(abstract)

Comments 6 pages, 5 figures

Learning to Refine: An Agentic RL Approach for Iterative SPARQL Query Construction

Floris Vossebeld, Shenghui Wang

机构 * Faculty of Electrical Engineering, Mathematics and Computer Science（电气工程、数学与计算机科学学院） ； University of Twente（特文特大学） ； Microsoft Netherlands（微软荷兰） 纠错

专题命中 代码与定理证明 ：reasoning(abstract)；分类 cs.AI、cs.LG

Grounded by Experience: Generative Healthcare Prediction Augmented with Hierarchical Agentic Retrieval

Chuang Zhao, Hui Tang, Hongke Zhao, Xiaofang Zhou, Xiaomeng Li

机构 * Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology（电子与计算机工程系，香港科技大学） ； College of Management and Economics, Laboratory of Computation and Analytics of Complex Management Systems (CACMS), Tianjin University（管理学院与经济学学院，复杂管理系统的计算与分析实验室，天津大学） ； Department of Computer Science and Engineering, The Hong Kong University of Science and Technology（计算机科学与工程系，香港科技大学） 纠错

专题命中 代码与定理证明 ：reasoning(abstract)；分类 cs.AI

ARCHE: A Novel Task to Evaluate LLMs on Latent Reasoning Chain Extraction

Pengze Li, Jiaqi Liu, Junchi Yu, Lihao Liu, Mingyu Ding, Wanli Ouyang, Shixiang Tang, Xi Chen

专题命中 逻辑推理 ：reasoning(title,abstract)；chain-of-thought(abstract)；分类 cs.AI

Comments Accepted to AAAI 2026

Concept-RuleNet: Grounded Multi-Agent Neurosymbolic Reasoning in Vision Language Models

Sanchit Sinha, Guangzhi Xiong, Zhenghao He, Aidong Zhang

专题命中 逻辑推理 ：reasoning(title,abstract)；verifier(abstract)；分类 cs.AI

Comments AAAI 2026 (oral)

RAC3: Retrieval-Augmented Corner Case Comprehension for Autonomous Driving with Vision-Language Models

Yujin Wang, Quanfeng Liu, Jiaqi Fan, Jinlong Hong, Hongqing Chu, Mengjian Tian, Bingzhao Gao, Hong Chen

专题命中 逻辑推理 ：reasoning(abstract)；chain-of-thought(abstract)；CoT(abstract)；logical reasoning(abstract)

Comments Accepted by IEEE Transactions on Multimedia

SciAgent: A Unified Multi-Agent System for Generalistic Scientific Reasoning

Xuchen Li, Ruitao Wu, Xuanbo Liu, Xukai Wang, Jinbo Hu, Zhixin Bai, Bohan Zeng, Hao Liang, Leheng Chen, Mingrui Chen, Haitian Zhong, Xuanlin Yang, Xu-Yao Zhang, Liu Liu, Jia Li, Kaiqi Huang, Jiahao Xu, Haitao Mi, Wentao Zhang, Bin Dong

专题命中 逻辑推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

Comments 1. To ensure result rigor, the model outputs require further evaluation by human experts. 2. The results may affect our conclusions and methods, thus necessitating a more detailed review. 3. We anticipate subsequent revisions may be substantial, potentially involving major adjustments to the methodology. Given the uncertainty surrounding the revision process, we decide to request a withdrawal

High-level reasoning while low-level actuation in Cyber-Physical Systems: How efficient is it?

Burak Karaduman, Baris Tekin Tezel, Moharram Challenger

专题命中 逻辑推理 ：reasoning(title,abstract)

DR-Encoder: Encode Low-rank Gradients with Random Prior for Large Language Models Differentially Privately

Huiwen Wu, Deyi Zhang, Xiaohan Li, Xiaogang Xu, Jiafei Wu, Zhe Liu

机构 * Zhejiang Laboratory（浙江实验室） 纠错

专题命中 逻辑推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

Fault2Flow: An AlphaEvolve-Optimized Human-in-the-Loop Multi-Agent System for Fault-to-Workflow Automation

Yafang Wang, Yangjie Tian, Xiaoyu Shen, Gaoyang Zhang, Jiaze Sun, He Zhang, Ruohua Xu, Feng Zhao

机构 * ISILC, Victoria University（维多利亚大学ISILC） ； Kexin Melbourne AI Research Center（墨尔本凯欣人工智能研究中心） ； Eastern Institute of Technology（东部技术研究所） 纠错

专题命中 逻辑推理 ：reasoning(abstract)；分类 cs.AI

LLM-Assisted Formalization Enables Deterministic Detection of Statutory Inconsistency in the Internal Revenue Code

Borchuluun Yadamsuren, Steven Keith Platt, Miguel Diaz

专题命中 逻辑推理 ：reasoning(abstract)；分类 cs.AI

Comments 29 pages, 3 appendices with Prolog code and full codebase available at: https://github.com/borchuluun/section121-inconsistency-detection

CausalGuard: A Smart System for Detecting and Preventing False Information in Large Language Models

Piyushkumar Patel

机构 * Microsoft（微软） 纠错

专题命中 逻辑推理 ：reasoning(abstract)；分类 cs.AI

Two Agents, One Prompt, and Your Weight

Elchanan Mossel, Amnon Schreiber

专题命中 逻辑推理 ：reasoning(abstract)

Comments Typos corrected

MAPLE: Multi-Agent Adaptive Planning with Long-Term Memory for Table Reasoning

Ye Bai, Minghan Wang, Thuy-Trang Vu

机构 * Department of Data Science & AI, Monash University（数据科学与人工智能系，墨尔本大学） 纠错

专题命中 规划推理 ：reasoning(title,abstract)；planning(title,abstract)；chain-of-thought(abstract)；分类 cs.CL

Comments 27 pages, 11 figures, ALTA 2025

Cognitive Maps in Language Models: A Mechanistic Analysis of Spatial Planning

Caroline Baumgartner, Eleanor Spens, Neil Burgess, Petru Manescu

机构 * University College London（伦敦大学学院） ； University of Oxford（牛津大学） 纠错

专题命中 规划推理 ：planning(title,abstract)；reasoning(abstract)；分类 cs.AI

HumanoidGen: Data Generation for Bimanual Dexterous Manipulation via LLM Reasoning

Zhi Jing, Siyuan Yang, Jicong Ao, Ting Xiao, Yu-Gang Jiang, Chenjia Bai

机构 * Fudan University（复旦大学） ； Institute of Artificial Intelligence (TeleAI), China Telecom（人工智能研究所（TeleAI），中国电信） ； University of Science and Technology of China（中国科学技术大学） ； East China University of Science and Technology（东华大学） 纠错

专题命中 规划推理 ：reasoning(title,abstract)；planning(abstract)；分类 cs.AI

Comments Project Page: https://openhumanoidgen.github.io

Online Learning of HTN Methods for integrated LLM-HTN Planning

Yuesheng Xu, Hector Munoz-Avila

机构 * Computer Science \& Engineering, Lehigh University ； Bethlehem, PA 18015-3084 USA 纠错

专题命中 规划推理 ：planning(title,abstract)；分类 cs.AI

Comments The Twelfth Annual Conference on Advances in Cognitive Systems (ACS-2025)

Journal ref The Twelfth Annual Conference on Advances in Cognitive Systems (ACS-2025)