大模型推理能力

GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models

Iman Mirzadeh, Keivan Alizadeh, Hooman Shahrokhi, Oncel Tuzel, Samy Bengio, Mehrdad Farajtabar

机构 * Apple（苹果公司） ； Washington State University（华盛顿州立大学） 纠错

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

Comments ICLR camera ready + additional discussion in the appendix

SLIM: Subtrajectory-Level Elimination for More Effective Reasoning

Xifeng Yao, Chengyuan Ma, Dongyu Lang, Yinhao Ni, Zhiwei Xu, Huarui Xie, Zihao Chen, Guang Shen, Dandan Tu, Yi Bai, Changzheng Zhang

机构 * Huawei Technologies Co., Ltd.（华为技术有限公司） 纠错

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

Comments EMNLP 2025 Findings

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control

Quanfeng Lu, Zhantao Ma, Shuai Zhong, Jin Wang, Dahai Yu, Michael K. Ng, Ping Luo

机构 * The University of Hong Kong（香港大学） ； Hong Kong Baptist University（香港 Baptist 大学） ； TCL Corporate Research (Hong Kong) Co., Ltd（TCL 香港研究院） 纠错

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

Comments 28 pages, 12 figures

An Investigation on Group Query Hallucination Attacks

Kehao Miao, Xiaolong Jin

机构 * University of Science and Technology of China（中国科学技术大学） ； Purdue University（帕克大学） 纠错

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

Thinking Before You Speak: A Proactive Test-time Scaling Approach

Cong Liu, Wenchang Chai, Hejun Wu, Yan Pan, Pengxu Wei, Liang Lin

机构 * Sun Yat-sen University（中山大学） ； Hong Kong Polytechnic University（香港理工大学） 纠错

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

Journal ref EMNLP 2025

Logical Reasoning with Outcome Reward Models for Test-Time Scaling

Ramya Keerthy Thatikonda, Wray Buntine, Ehsan Shareghi

机构 * Department of Data Science & AI, Monash University（数据科学与人工智能系，莫纳什大学） ； College of Engineering and Computer Science, VinUniversity（工程与计算机科学学院，文大学） 纠错

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

Comments EMNLP 2025

Rethinking Reasoning in LLMs: Neuro-Symbolic Local RetoMaton Beyond ICL and CoT

Rushitha Santhoshi Mamidala, Anshuman Chhabra, Ankur Mali

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

An Iterative Approach for Heterogeneous Multi-Agent Route Planning with Resource Transportation Uncertainty and Temporal Logic Goals

Gustavo A. Cardona, Kaier Liang, Cristian-Ioan Vasile

机构 * Mechanical Engineering and Mechanics Department（机械工程与力学系） 纠错

专题命中 逻辑推理 ：planning(title,abstract)

Large Language Models (LLMs) for Electronic Design Automation (EDA)

Kangwei Xu, Denis Schwachhofer, Jason Blocklove, Ilia Polian, Peter Domanski, Dirk Pflüger, Siddharth Garg, Ramesh Karri, Ozgur Sinanoglu, Johann Knechtel, Zhuorui Zhao, Ulf Schlichtmann, Bing Li

机构 * Technical University of Munich（慕尼黑技术大学） ； University of Stuttgart（斯图加特大学） ； New York University（纽约大学） ； University of Siegen（锡根大学） 纠错

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

Comments Accepted by IEEE International System-on-Chip Conference

AirRAG: Autonomous Strategic Planning and Reasoning Steer Retrieval Augmented Generation

Wenfeng Feng, Chuzhan Hao, Yuewei Zhang, Guochao Jiang, Jingyi Song, Hao Wang

机构 * Alibaba Cloud Computing（阿里巴巴云 computing） 纠错

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

Comments 20 pages, EMNLP25 Accepted

CataractSurg-80K: Knowledge-Driven Benchmarking for Structured Reasoning in Ophthalmic Surgery Planning

Yang Meng, Zewen Pan, Yandi Lu, Ruobing Huang, Yanfeng Liao, Jiarui Yang

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

Comments 18 pages, 9 figures

Discrete-Guided Diffusion for Scalable and Safe Multi-Robot Motion Planning

Jinhao Liang, Sven Koenig, Ferdinando Fioretto

机构 * University of Virginia（弗吉尼亚大学） ； University of California, Irvine（加州大学伊藤分校） 纠错

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

Encouraging Good Processes Without the Need for Good Answers: Reinforcement Learning for LLM Agent Planning

Zhiwei Li, Yong Hu, Wenqing Wang

机构 * WeChat, Tencent Inc., China（微信，腾讯公司，中国） ； School of Software & Microelectronics, Peking University, Beijing（软件与微电子学院，北京大学，北京） 纠错

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

PyVision: Agentic Vision with Dynamic Tooling

Shitian Zhao, Haoquan Zhang, Shaoheng Lin, Ming Li, Qilong Wu, Kaipeng Zhang, Chen Wei

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

Comments 26 Pages, 10 Figures, Technical report, Fix Typo

Capabilities of GPT-5 across critical domains: Is it the next breakthrough?

Georgios P. Georgiou

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

Socially Interactive Agents for Preserving and Transferring Tacit Knowledge in Organizations

Martin Benderoth, Patrick Gebhard, Christian Keller, C. Benjamin Nakhosteen, Stefan Schaffer, Tanja Schneeberger

专题命中 规划推理 ：chain-of-thought(abstract)；CoT(abstract)

Comments 4 pages, 2 figures

Self-Organizing Agent Network for LLM-based Workflow Automation

Yiming Xiong, Jian Wang, Bing Li, Yuhan Zhu, Yuqi Zhao

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

CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning

Zeyi Sun, Yuhang Cao, Jianze Liang, Qiushi Sun, Ziyu Liu, Zhixiong Zhang, Yuhang Zang, Xiaoyi Dong, Kai Chen, Dahua Lin, Jiaqi Wang

机构 * Shanghai Jiao Tong University（上海交通大学） ； Shanghai AI Laboratory（上海人工智能实验室） ； The Chinese University of Hong Kong（香港中文大学） ； The University of Hong Kong（香港大学） 纠错

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

Comments code available at this url: https://github.com/OpenIXCLab/CODA

Learning Game-Playing Agents with Generative Code Optimization

Zhiyi Kuang, Ryan Rong, YuCheng Yuan, Allen Nie

机构 * stanford（斯坦福大学） 纠错

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

Comments ICML 2025 Workshop on Programmatic Representations for Agent Learning, Vancouver, Canada

Convert Language Model into a Value-based Strategic Planner

Xiaoyu Wang, Yue Zhao, Qingqing Gu, Zhonglin Jiang, Xiaokai Chen, Yong Chen, 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 规划推理 ：planning(abstract)；分类 cs.CL、cs.AI

Comments 13 pages, 6 figures, ACL 2025 Industry Track

Governance-as-a-Service: A Multi-Agent Framework for AI System Compliance and Policy Enforcement

Suyash Gaurav, Jukka Heikkonen, Jatin Chaudhary

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

A Theory of Intelligences

Michael E. Hochberg

机构 * ISEM, Université de Montpellier, CNRS, IRD, EPHE（蒙彼利埃大学智能科学系、法国国家科学研究中心、国际研究与发展机构、法国国家高等科学研究院） 纠错

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

Comments 37 pages, 1 Table, 6 figures

Interactive Graph Visualization and TeamingRecommendation in an Interdisciplinary Project'sTalent Knowledge Graph

Jiawei Xu, Juichien Chen, Yilin Ye, Zhandos Sembay, Swathi Thaker, Pamela Payne-Foster, Jake Chen, Ying Ding

专题命中 规划推理 ：reasoning(abstract)

Comments Short paper presented at the ASIS&T 2025 Annual Meeting

A Comprehensive Review on Traffic Datasets and Simulators for Autonomous Vehicles

Supriya Sarker, Brent Maples, Iftekharul Islam, Muyang Fan, Christos Papadopoulos, Weizi Li

专题命中 规划推理 ：planning(abstract)

Comments This manuscript has been withdrawn due to the need for substantial updates and revisions

SELF: Surrogate-light Feature Selection with Large Language Models in Deep Recommender Systems

Pengyue Jia, Zhaocheng Du, Yichao Wang, Xiangyu Zhao, Xiaopeng Li, Yuhao Wang, Qidong Liu, Huifeng Guo, Ruiming Tang

专题命中 规划推理 ：reasoning(abstract)

Comments Accepted to CIKM'25

11Plus-Bench: Demystifying Multimodal LLM Spatial Reasoning with Cognitive-Inspired Analysis

Chengzu Li, Wenshan Wu, Huanyu Zhang, Qingtao Li, Zeyu Gao, Yan Xia, José Hernández-Orallo, Ivan Vulić, Furu Wei

机构 * Microsoft Research（微软研究院） ； Language Technology Lab, University of Cambridge（语言技术实验室，剑桥大学） ； Institute of Automation, Chinese Academy of Sciences（自动化研究所，中国科学院） ； Department of Oncology, University of Cambridge（癌症部门，剑桥大学） ； Leverhulme Centre for the Future of Intelligence, University of Cambridge（未来智能中心，剑桥大学） ； VRAIN, Universitat Politècnica de València（VRAIN，巴塞罗那理工大学） 纠错

专题命中 视觉空间推理 ：reasoning(title,abstract)；分类 cs.CL、cs.LG

Comments 9 pages, 4 figures (22 pages, 7 figures, 7 tables including references and appendices)

FlyMeThrough: Human-AI Collaborative 3D Indoor Mapping with Commodity Drones

Xia Su, Ruiqi Chen, Jingwei Ma, Chu Li, Jon E. Froehlich

专题命中 视觉空间推理 ：planning(abstract)

Comments Accepted at UIST 2025, 14 pages, 8 figures, 2 tables

Assessing the Geolocation Capabilities, Limitations and Societal Risks of Generative Vision-Language Models

Oliver Grainge, Sania Waheed, Jack Stilgoe, Michael Milford, Shoaib Ehsan

专题命中 视觉空间推理 ：reasoning(abstract)

Comments Accepted to AAAI Fall Symposium 2025 on AI Trustworthiness and Risk Assessment for Challenging Contexts (ATRACC)

A Statistical Framework of Watermarks for Large Language Models: Pivot, Detection Efficiency and Optimal Rules

Xiang Li, Feng Ruan, Huiyuan Wang, Qi Long, Weijie J. Su

机构 * University of Pennsylvania（宾夕法尼亚大学） ； Northwestern University（西北大学） 纠错

专题命中 测试时计算 ：reasoning(abstract)；verifier(abstract)；分类 cs.CL、cs.LG

Comments Accepted by Annals of Statistics

Journal ref Ann. Statist. 53(1): 322-351 (February 2025)

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization

Xinyu Li, Tianjin Huang, Ronghui Mu, Xiaowei Huang, Gaojie Jin

专题命中 复杂问题求解 ：reasoning(abstract)；chain-of-thought(abstract)；CoT(abstract)；分类 cs.AI、cs.LG