大模型推理能力

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding

Xi Chen, Aske Plaat, Niki van Stein

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

Good Learners Think Their Thinking: Generative PRM Makes Large Reasoning Model More Efficient Math Learner

Tao He, Rongchuan Mu, Lizi Liao, Yixin Cao, Ming Liu, Bing Qin

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

Comments 33 pages, 3 figures, 19 tables

CHECK-MAT: Checking Hand-Written Mathematical Answers for the Russian Unified State Exam

Ruslan Khrulev

机构 * Moscow State University（莫斯科国立大学） 纠错

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

Comments 15 pages, 3 figures, 10 tables. Code is available at: https://github.com/Karifannaa/Auto-check-EGE-math

Beyond Passive Critical Thinking: Fostering Proactive Questioning to Enhance Human-AI Collaboration

Ante Wang, Yujie Lin, Jingyao Liu, Suhang Wu, Hao Liu, Xinyan Xiao, Jinsong Su

机构 * School of Informatics, Xiamen University, China（厦门大学信息学院） ； Department of Digital Media Technology, Xiamen University, China（厦门大学数字媒体技术系） ； Baidu Inc., Beijing, China（百度公司） 纠错

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

Theorem-of-Thought: A Multi-Agent Framework for Abductive, Deductive, and Inductive Reasoning in Language Models

Samir Abdaljalil, Hasan Kurban, Khalid Qaraqe, Erchin Serpedin

机构 * Texas A&M University（德克萨斯大学） ； Hamad Bin Khalifa University（哈马德·本·卡伊夫大学） 纠错

专题命中 代码与定理证明 ：reasoning(title,abstract)；chain-of-thought(abstract)；CoT(abstract)；分类 cs.CL、cs.AI

Comments ACL 2025 KnowFM

A survey of multi-agent geosimulation methodologies: from ABM to LLM

Virginia Padilla, Jacinto Dávila

机构 * Departamento de Ciencia y Tecnología, Universidad Nacional Experimental de Guayana（科学与技术系，圭亚那国家实验大学） ； CeSiMo, Facultad de Ingeniería, Universidad de los Andes（CeSiMo，工程学院，安第斯大学） 纠错

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

Comments 20 pages, 1 table

VL-Cogito: Progressive Curriculum Reinforcement Learning for Advanced Multimodal Reasoning

Ruifeng Yuan, Chenghao Xiao, Sicong Leng, Jianyu Wang, Long Li, Weiwen Xu, Hou Pong Chan, Deli Zhao, Tingyang Xu, Zhongyu Wei, Hao Zhang, Yu Rong

机构 * DAMO Academy, Alibaba Group（达摩院，阿里巴巴集团） ； Hupan Lab（虎盘实验室） ； Fudan University（复旦大学） 纠错

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

Comments 21 pages, 5 figures, 6 tables. Work in progress

Augmented Vision-Language Models: A Systematic Review

Anthony C Davis, Burhan Sadiq, Tianmin Shu, Chien-Ming Huang

机构 * Johns Hopkins University（约翰霍普金斯大学） 纠错

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

Can LLM-Reasoning Models Replace Classical Planning? A Benchmark Study

Kai Goebel, Patrik Zips

机构 * Center for Vision, Automation & Control（视觉、自动化与控制中心） ； AIT Austrian Institute of Technology GmbH（奥地利技术研究院） 纠错

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

MPCC: A Novel Benchmark for Multimodal Planning with Complex Constraints in Multimodal Large Language Models

Yiyan Ji, Haoran Chen, Qiguang Chen, Chengyue Wu, Libo Qin, Wanxiang Che

机构 * Harbin Institute of Technology（哈尔滨工业大学） ； The University of Hong Kong（香港大学） ； Central South University（中南大学） 纠错

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

Comments Accepted to ACM Multimedia 2025

Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents

Haoran Sun, Shaoning Zeng

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

Coordinating Search-Informed Reasoning and Reasoning-Guided Search in Claim Verification

Qisheng Hu, Quanyu Long, Wenya Wang

机构 * Nanyang Technological University（南洋理工大学） 纠错

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

Comments Work in progress

Planning for Cooler Cities: A Multimodal AI Framework for Predicting and Mitigating Urban Heat Stress through Urban Landscape Transformation

Shengao Yi, Xiaojiang Li, Wei Tu, Tianhong Zhao

机构 * Department of City and Regional Planning, University of Pennsylvania（城市与区域规划系，宾夕法尼亚大学） ； Guangdong Key Laboratory for Urban Informatics, Guangdong-Hong Kong-Macao Joint Laboratory for Smart Cities（广东城市信息关键实验室、粤港澳大湾区智慧城市联合实验室） ； Shenzhen Key Laboratory of Spatial Information Smart Sensing（深圳空间信息智能感知关键实验室） ； Department of Urban Informatics, School of Architecture and Urban Planning, Shenzhen University（城市信息系，深圳大学） ； College of Big Data and Internet, Shenzhen Technology University（大数据与互联网学院，深圳科技大学） 纠错

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

A Unified Perception-Language-Action Framework for Adaptive Autonomous Driving

Yi Zhang, Erik Leo Haß, Kuo-Yi Chao, Nenad Petrovic, Yinglei Song, Chengdong Wu, Alois Knoll

机构 * Chair of Robotics, Artificial Intelligence and Embedded Systems Technical University of Munich (TUM)（机器人、人工智能与嵌入系统教授席 Technical University of Munich） 纠错

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

Where Paths Collide: A Comprehensive Survey of Classic and Learning-Based Multi-Agent Pathfinding

Shiyue Wang, Haozheng Xu, Yuhan Zhang, Jingran Lin, Changhong Lu, Xiangfeng Wang, Wenhao Li

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

Comments 112 pages, 21 figures, 20 tables. The project website is: https://wangsh1yue.github.io/Where-Paths-Collide

SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution

Han Li, Yuling Shi, Shaoxin Lin, Xiaodong Gu, Heng Lian, Xin Wang, Yantao Jia, Tao Huang, Qianxiang Wang

机构 * Shanghai Jiao Tong University（上海交通大学） ； Huawei（华为） ； Xidian University（西安电子科技大学） 纠错

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

Comments Our code and data are available at https://github.com/YerbaPage/SWE-Debate

DrugMCTS: a drug repurposing framework combining multi-agent, RAG and Monte Carlo Tree Search

Zerui Yang, Yuwei Wan, Siyu Yan, Yudai Matsuda, Tong Xie, Bram Hoex, Linqi Song

机构 * City University of Hong Kong, Hong Kong, PR China（香港城市大学） ； City University of Hong Kong Shenzhen Research Institute, Shenzhen, PR China（香港城市大学深圳研究院） ； The Hong Kong University of Science and Technology (Guangzhou), Guangzhou PR China（香港科学与技术大学（广州）） ； GreenDynamics, Sydney, NSW, Australia（GreenDynamics公司） ； University of New South Wales, Kensington, NSW, Australia（新南威尔士大学） 纠错

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

Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling

Trae Research Team, Pengfei Gao, Zhao Tian, Xiangxin Meng, Xinchen Wang, Ruida Hu, Yuanan Xiao, Yizhou Liu, Zhao Zhang, Junjie Chen, Cuiyun Gao, Yun Lin, Yingfei Xiong, Chao Peng, Xia Liu

机构 * Trae Research（Trae研究） 纠错

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

Comments Pengfei Gao and Zhao Tian contributed equally to this technical report

SmartCourse: A Contextual AI-Powered Course Advising System for Undergraduates

Yixuan Mi, Yiduo Yu, Yiyi Zhao

机构 * Department of Computer Science, Wenzhou-Kean University, Wenzhou, China（计算机科学系，温州市凯恩大学，中国温州） ； Department of Computer Science, Kean University, Union, NJ, United States（计算机科学系，凯恩大学，美国新泽西州联合市） 纠错

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

Comments 7 pages, 6 figures, 1 table. *Corresponding author: Yixuan Mi. Code: https://github.com/EthanYixuanMi/Smartcourse-Contextual-Advising

LLMs and the Human Condition

Peter Wallis

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

Comments Edits and rearranged to provide significantly tighter writing - no change to the content. Now targeting a one day workshop on multi agent systems and LLMs

When no one shows up (at first): Navigating the uncertainties of participatory workshops in interdisciplinary research

Monique Munarini

专题命中 规划推理 ：planning(abstract)

Comments Presented at HHAI25:The 4th International Conference Series on Hybrid Human-Artificial Intelligence, workshop Mind the AI-GAP 2025:Co-Designing Socio-Technical Systems. (June 9-13, 2025 in Pisa, Italy)

Climate in a Bottle: Towards a Generative Foundation Model for the Kilometer-Scale Global Atmosphere

Noah D. Brenowitz, Tao Ge, Akshay Subramaniam, Peter Manshausen, Aayush Gupta, David M. Hall, Morteza Mardani, Arash Vahdat, Karthik Kashinath, Michael S. Pritchard

专题命中 规划推理 ：planning(abstract)

3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding

Ting Huang, Zeyu Zhang, Hao Tang

专题命中 视觉空间推理 ：reasoning(title,abstract)；CoT(abstract)

SeqAffordSplat: Scene-level Sequential Affordance Reasoning on 3D Gaussian Splatting

Di Li, Jie Feng, Jiahao Chen, Weisheng Dong, Guanbin Li, Yuhui Zheng, Mingtao Feng, Guangming Shi

专题命中 视觉空间推理 ：reasoning(title,abstract)

Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents

Shaofei Cai, Zhancun Mu, Haiwen Xia, Bowei Zhang, Anji Liu, Yitao Liang

专题命中 视觉空间推理 ：reasoning(abstract)；分类 cs.AI

Towards Affordable Tumor Segmentation and Visualization for 3D Breast MRI Using SAM2

Solha Kang, Eugene Kim, Joris Vankerschaver, Utku Ozbulak

机构 * Center for Biosystems and Biotech Data Science, Ghent University Global Campus, Incheon, Republic of Korea（生物系统与生物技术数据科学中心，格罗宁根大学全球校园，韩国Incheon） ； Department of Mathematics, Computer Science and Statistics, Ghent University, Ghent, Belgium（数学、计算机科学与统计学系，格罗宁根大学，比利时Ghent） ； IDLab, Department of Electronics and Information Systems, Ghent University, Ghent, Belgium（IDLab，电子与信息系统系，格罗宁根大学，比利时Ghent） 纠错

专题命中 视觉空间推理 ：planning(abstract)；分类 cs.AI

Comments Accepted for publication in the 28th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2nd Deep Breast Workshop on AI and Imaging for Diagnostic and Treatment Challenges in Breast Care (DeepBreath), 2025

Dual-Stream Global-Local Feature Collaborative Representation Network for Scene Classification of Mining Area

Shuqi Fan, Haoyi Wang, Xianju Li

专题命中 视觉空间推理 ：planning(abstract)

Comments Accepted to IJCNN 2025

Towards Omnimodal Expressions and Reasoning in Referring Audio-Visual Segmentation

Kaining Ying, Henghui Ding, Guangquan Jie, Yu-Gang Jiang

机构 * Fudan University, China（复旦大学） 纠错

专题命中 复杂问题求解 ：reasoning(title,abstract)

Comments ICCV 2025, Project Page: https://henghuiding.com/OmniAVS/

Controllable Traffic Simulation through LLM-Guided Hierarchical Reasoning and Refinement

Zhiyuan Liu, Leheng Li, Yuning Wang, Haotian Lin, Hao Cheng, Zhizhe Liu, Lei He, Jianqiang Wang

机构 * School of Vehicle and Mobility, Tsinghua University（清华大学车辆与移动学院） ； Artificial Intelligence Thrust, The Hong Kong University of Science and Technology (Guangzhou)（香港理工大学（广州）人工智能研究部） ； School of Computer Science, Carnegie Mellon University（卡内基梅隆大学计算机科学学院） ； Department of Computer Sciences, University of Wisconsin-Madison（威斯康星大学麦迪逊分校计算机科学系） 纠错

专题命中 复杂问题求解 ：reasoning(title)

Comments Accepted by IROS 2025

EducationQ: Evaluating LLMs' Teaching Capabilities Through Multi-Agent Dialogue Framework

Yao Shi, Rongkeng Liang, Yong Xu

机构 * South China University of Technology（华南理工大学） ； Education Innovation Research Institute of Guangdong（广东教育创新研究院） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments Paper URL: https://aclanthology.org/2025.acl-long.1576 ;Presentation Video: https://www.youtube.com/watch?v=j63ooKE50I0

Journal ref Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (2025) 32799-32828