大模型推理能力

Do Math Reasoning LLMs Help Predict the Impact of Public Transit Events?

Bowen Fang, Ruijian Zha, Xuan Di

机构 * Department of Civil Engineering and Engineering Mechanics, Columbia University（哥伦比亚大学土木工程与工程力学系） ； Engineering Mechanics, Columbia University（哥伦比亚大学工程力学系） ； Department of Computer Science, Columbia University（哥伦比亚大学计算机科学系） ； Data Science Institute, Columbia University（哥伦比亚大学数据科学研究院） 纠错

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

Recitation over Reasoning: How Cutting-Edge Language Models Can Fail on Elementary School-Level Reasoning Problems?

Kai Yan, Yufei Xu, Zhengyin Du, Xuesong Yao, Zheyu Wang, Xiaowen Guo, Jiecao Chen

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

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

Comments 24 pages, 3 figures, 13 tables. The paper is accepted at AACL-IJCNLP 2025 (main track), and the latest version adds modifications in camera-ready

Towards Robust Mathematical Reasoning

Thang Luong, Dawsen Hwang, Hoang H. Nguyen, Golnaz Ghiasi, Yuri Chervonyi, Insuk Seo, Junsu Kim, Garrett Bingham, Jonathan Lee, Swaroop Mishra, Alex Zhai, Clara Huiyi Hu, Henryk Michalewski, Jimin Kim, Jeonghyun Ahn, Junhwi Bae, Xingyou Song, Trieu H. Trinh, Quoc V. Le, Junehyuk Jung

机构 * Georgia Institute of Technology（佐治亚理工学院） ； Seoul National University（首尔国立大学） ； Microsoft（微软） ； Massachusetts Institute of Technology（麻省理工学院） ； Brown University（布朗大学） 纠错

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

Comments EMNLP 2025 (main conference), https://aclanthology.org/2025.emnlp-main.1794/

PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts

Yiming Wang, Pei Zhang, Jialong Tang, Haoran Wei, Baosong Yang, Rui Wang, Chenshu Sun, Feitong Sun, Jiran Zhang, Junxuan Wu, Qiqian Cang, Yichang Zhang, Fei Huang, Junyang Lin, Fei Huang, Jingren Zhou

机构 * Qwen Team, Alibaba Group（阿里集团Qwen团队） ； Shanghai Jiao Tong University（上海交通大学） 纠错

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

Comments Accepted by NeurIPS 2025

Analyzing the Power of Chain of Thought through Memorization Capabilities

Lijia Yu, Xiao-Shan Gao, Lijun Zhang

机构 * Institute of AI for Industries（人工智能产业研究院） ； State Key Laboratory of Mathematical Sciences（数学科学国家重点实验室） ； Academy of Mathematics and Systems Science（数学与系统科学学院） ； University of Chinese Academy of Sciences（中国科学院大学） ； Key Laboratory of System Software of Chinese Academy of Sciences（中国科学院系统软件重点实验室） 纠错

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

KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems

Hancheng Ye, Zhengqi Gao, Mingyuan Ma, Qinsi Wang, Yuzhe Fu, Ming-Yu Chung, Yueqian Lin, Zhijian Liu, Jianyi Zhang, Danyang Zhuo, Yiran Chen

机构 * Duke University（杜克大学） ； MIT（麻省理工学院） ； NVIDIA（英伟达） 纠错

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

Comments Accepted for publication in NeurIPS2025. Code is available at \url{https://github.com/FastMAS/KVCOMM}

Automated Discovery of Conservation Laws via Hybrid Neural ODE-Transformers

Vivan Doshi

机构 * Independent Researcher（独立研究者） 纠错

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

Comments 5th Math-AI Workshop - Neural Information Processing Systems (NeurIPS 2025)

AReaL-Hex: Accommodating Asynchronous RL Training over Heterogeneous GPUs

Ran Yan, Youhe Jiang, Tianyuan Wu, Jiaxuan Gao, Zhiyu Mei, Wei Fu, Haohui Mai, Wei Wang, Yi Wu, Binhang Yuan

机构 * HKUST（香港科技大学） ； Tsinghua University（清华大学） ； Ant Group（蚂蚁集团） 纠错

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

Interpreting the Latent Structure of Operator Precedence in Language Models

Dharunish Yugeswardeenoo, Harshil Nukala, Ved Shah, Cole Blondin, Sean O Brien, Vasu Sharma, Kevin Zhu

机构 * Algoverse AI Research（Algoverse AI研究） 纠错

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

Comments 11 pages, 6 figures. An earlier version of this work was accepted to CoLM 2024. This is an extended version of our CoLM 2024 paper. Includes additional ablations; added Ved Shah as author for those contributions

\texttt{ReMind}: Understanding Deductive Code Reasoning in LLMs

Jun Gao, Yun Peng, Xiaoxue Ren

机构 * Zhejiang University（浙江大学） ； The Chinese University of Hong Kong（香港中文大学） 纠错

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

Position: Vibe Coding Needs Vibe Reasoning: Improving Vibe Coding with Formal Verification

Jacqueline Mitchell, Yasser Shaaban

机构 * University of Southern California（南加州大学） 纠错

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

Comments 7 pages, 3 figures, In Proceedings of the 1st ACM SIGPLAN International Workshop on Language Models and Programming Languages (LMPL'25), October 12-18, 2025, Singapore, Singapore. ACM, New York, NY, USA

Inferring multiple helper Dafny assertions with LLMs

Álvaro Silva, Alexandra Mendes, Ruben Martins

机构 * INESC TEC, Faculty of Engineering, University of Porto（葡萄牙波尔图大学工程学院INESC TEC） ； Computer Science Department of Carnegie Mellon University（卡内基梅隆大学计算机科学系） 纠错

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

The Curse of CoT: On the Limitations of Chain-of-Thought in In-Context Learning

Tianshi Zheng, Yixiang Chen, Chengxi Li, Chunyang Li, Qing Zong, Haochen Shi, Baixuan Xu, Yangqiu Song, Ginny Y. Wong, Simon See

机构 * The Hong Kong University of Science and Technology（香港科技大学） ； NVIDIA（英伟达） 纠错

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

Comments Accepted by TMLR

MiRAGE: Misconception Detection with Retrieval-Guided Multi-Stage Reasoning and Ensemble Fusion

Cuong Van Duc, Thai Tran Quoc, Minh Nguyen Dinh Tuan, Tam Vu Duc, Son Nguyen Van, Hanh Nguyen Thi

机构 * Hanoi University of Science and Technology（河内科学技术大学） ； School of Computing, Phenikaa University（现象学大学计算机学院） ； Faculty of Interdisciplinary Digital Technology, Phenikaa University（现象学大学跨学科数字技术学院） 纠错

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

Active Thinking Model: A Goal-Directed Self-Improving Framework for Real-World Adaptive Intelligence

Hong Su

机构 * School of Computer Science, Chengdu University of Information Technology（信息工程大学计算机学院） 纠错

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

Knolling Bot: Teaching Robots the Human Notion of Tidiness

Yuhang Hu, Judah Goldfeder, Zhizhuo Zhang, Xinyue Zhu, Ruibo Liu, Philippe Wyder, Jiong Lin, Hod Lipson

机构 * Columbia University（哥伦比亚大学） 纠错

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

Comments Accepted at the 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Creative AI Track

PROPEX-RAG: Enhanced GraphRAG using Prompt-Driven Prompt Execution

Tejas Sarnaik, Manan Shah, Ravi Hegde

机构 * Indian Institute of Technology, Gandhinagar, Gujarat, India（印度理工学院冈丁加尔分校，古吉拉特邦，印度） 纠错

专题命中 逻辑推理 ：reasoning(abstract)

Comments Accepted in PReMI 2025

PPMI: Privacy-Preserving LLM Interaction with Socratic Chain-of-Thought Reasoning and Homomorphically Encrypted Vector Databases

Yubeen Bae, Minchan Kim, Jaejin Lee, Sangbum Kim, Jaehyung Kim, Yejin Choi, Niloofar Mireshghallah

机构 * Seoul National University（首尔国立大学） ； Stanford University（斯坦福大学） ； NVIDIA（英伟达） ； University of Washington（华盛顿大学） 纠错

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

Comments 29 pages

LLM Strategic Reasoning: Agentic Study through Behavioral Game Theory

Jingru Jia, Zehua Yuan, Junhao Pan, Paul E. McNamara, Deming Chen

机构 * University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

专题命中 规划推理 ：reasoning(title,abstract)；chain-of-thought(abstract)；CoT(abstract)；分类 cs.AI、cs.LG

Comments Accepted by NeurIPS 2025

Don't Just Search, Understand: Semantic Path Planning Agent for Spherical Tensegrity Robots in Unknown Environments

Junwen Zhang, Changyue Liu, Pengqi Fu, Xiang Guo, Ye Shi, Xudong Liang, Zhijian Wang, Hanzhi Ma

专题命中 规划推理 ：planning(title,abstract)；reasoning(abstract)

Comments 8 pages, 5 figures

Elicit and Enhance: Advancing Multimodal Reasoning in Medical Scenarios

Zhongzhen Huang, Linjie Mu, Yakun Zhu, Xiangyu Zhao, Shaoting Zhang, Xiaofan Zhang

机构 * Shanghai Jiao Tong University（上海交通大学） 纠错

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

TPS-Bench: Evaluating AI Agents' Tool Planning \& Scheduling Abilities in Compounding Tasks

Hanwen Xu, Xuyao Huang, Yuzhe Liu, Kai Yu, Zhijie Deng

机构 * Shanghai Jiaotong University（上海交通大学） 纠错

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

Learning to Seek Evidence: A Verifiable Reasoning Agent with Causal Faithfulness Analysis

Yuhang Huang, Zekai Lin, Fan Zhong, Lei Liu

机构 * Institute of Biomedical Science, Fudan University（复旦大学生物医学研究院） ； Fudan University（复旦大学） ； Intelligent Medicine Institute, Fudan University（复旦大学智能医学研究院） ； Shanghai Institute of Infectious Disease and Biosecurity, Fudan University（复旦大学传染病与生物安全研究所） ； Shanghai Institute of Stem Cell Research and Clinical Translation, Fudan University（复旦大学干细胞研究与临床转化研究所） 纠错

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

Comments 12 pages, 3 figures. Under review at the Conference on Computer Vision and Pattern Recognition (CVPR) 2026

Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous Thought

Hanlin Zhu, Shibo Hao, Zhiting Hu, Jiantao Jiao, Stuart Russell, Yuandong Tian

机构 * UC Berkeley（伯克利大学） ； UCSD（加州大学圣达菲分校） ； Meta AI 纠错

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

Comments 26 pages, 7 figures, NeurIPS 2025

Towards Transparent Reasoning: What Drives Faithfulness in Large Language Models?

Teague McMillan, Gabriele Dominici, Martin Gjoreski, Marc Langheinrich

机构 * ETH Zurich（苏黎世联邦理工学院） ； Università della Svizzera italiana（瑞士意大利大学） 纠错

专题命中 规划推理 ：reasoning(title)；分类 cs.CL

Comments 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: NeurIPS 2025 Workshop on Evaluating the Evolving LLM Lifecycle: Benchmarks, Emergent Abilities, and Scaling

A Self-Evolving AI Agent System for Climate Science

Zijie Guo, Jiong Wang, Fenghua Ling, Wangxu Wei, Xiaoyu Yue, Zhe Jiang, Wanghan Xu, Jing-Jia Luo, Lijing Cheng, Yoo-Geun Ham, Fengfei Song, Pierre Gentine, Toshio Yamagata, Ben Fei, Wenlong Zhang, Xinyu Gu, Chao Li, Yaqiang Wang, Tao Chen, Wanli Ouyang, Bowen Zhou, Lei Bai

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

Aligning LLM agents with human learning and adjustment behavior: a dual agent approach

Tianming Liu, Jirong Yang, Yafeng Yin, Manzi Li, Linghao Wang, Zheng Zhu

机构 * Department of Civil and Environmental Engineering, University of Michigan, Ann Arbor, United States（美国密歇根大学土木与环境工程系） ； Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, United States（美国密歇根大学电气工程与计算机科学系） ； College of Civil Engineering and Architecture, Zhejiang University, Hangzhou, China（浙江大学建筑工程学院） 纠错

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

Comments 32 pages, 6 figures, 7 tables

InnovatorBench: Evaluating Agents' Ability to Conduct Innovative LLM Research

Yunze Wu, Dayuan Fu, Weiye Si, Zhen Huang, Mohan Jiang, Keyu Li, Shijie Xia, Jie Sun, Tianze Xu, Xiangkun Hu, Pengrui Lu, Xiaojie Cai, Lyumanshan Ye, Wenhong Zhu, Yang Xiao, Pengfei Liu

机构 * SJTU（上海交通大学） ； SII（新加坡理工学院） ； GAIR（谷歌人工智能研究） 纠错

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

Knowledge Elicitation with Large Language Models for Interpretable Cancer Stage Identification from Pathology Reports

Yeawon Lee, Christopher C. Yang, Chia-Hsuan Chang, Grace Lu-Yao

专题命中 规划推理 ：chain-of-thought(abstract)；planning(abstract)；分类 cs.AI

Lares: LLM-driven Code Slice Semantic Search for Patch Presence Testing

Siyuan Li, Yaowen Zheng, Hong Li, Jingdong Guo, Chaopeng Dong, Chunpeng Yan, Weijie Wang, Yimo Ren, Limin Sun, Hongsong Zhu

专题命中 规划推理 ：reasoning(abstract)；logical reasoning(abstract)