大模型推理能力

Dissecting Logical Reasoning in LLMs: A Fine-Grained Evaluation and Supervision Study

Yujun Zhou, Jiayi Ye, Zipeng Ling, Yufei Han, Yue Huang, Haomin Zhuang, Zhenwen Liang, Kehan Guo, Taicheng Guo, Xiangqi Wang, Xiangliang Zhang

机构 * University of Notre Dame（诺丁汉大学） ； MBZUAI（马克斯·普朗克人工智能研究所） ； University of Pennsylvania（宾夕法尼亚大学） ； INRIA（法国国家信息与自动化研究所） 纠错

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

Comments Accepted by the Findings of EMNLP 2025

ToolLibGen: Scalable Automatic Tool Creation and Aggregation for LLM Reasoning

Murong Yue, Zhiwei Liu, Liangwei Yang, Jianguo Zhang, Zuxin Liu, Haolin Chen, Ziyu Yao, Silvio Savarese, Caiming Xiong, Shelby Heinecke, Huan Wang

机构 * George Mason University（乔治·玛森大学） ； Salesforce AI Research（Salesforce人工智能研究） 纠错

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

From Ethical Declarations to Provable Independence: An Ontology-Driven Optimal-Transport Framework for Certifiably Fair AI Systems

Sukriti Bhattacharya, Chitro Majumdar

机构 * Senior Scientist, Trustworthy AI, Luxembourg Institute of Science \& Technology, Maison de l'innovation 5, L-4362, Luxembourg Chief Investment Risk Strategist for Sovereign Institutions Founder, RsRL, Jumeirah Beach Residence (JBR), P.O.Box 29215, Dubai, United Arab Emirates 纠错

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

Comments 19 pages, 2 figures

$\textit{Agents Under Siege}$: Breaking Pragmatic Multi-Agent LLM Systems with Optimized Prompt Attacks

Rana Muhammad Shahroz Khan, Zhen Tan, Sukwon Yun, Charles Fleming, Tianlong Chen

机构 * University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校） ； Arizona State University（亚利桑那州立大学） ； Cisco（思科） 纠错

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

Prepared mind, fast response: A temporal decoupling framework for adaptive knowledge orchestration in open-domain dialogue

Jinling Gan, Churong Liang, Runnan Li

机构 * Beijing University of Posts and Telecommunications（北京邮电大学） 纠错

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

Aligning LLM+PDDL Symbolic Plans with Human Objective Specifications through Evolutionary Algorithm Guidance

Owen Burns, Dana Hughes, Katia Sycara

机构 * College of Engineering and Computer Science, University of Central Florida（中央佛罗里达大学工程与计算机科学学院） ； Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所） 纠错

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

Comments 7 pages, 5 figures

Journal ref 2025 IEEE 21st International Conference on Automation Science and Engineering (CASE), Los Angeles, CA, USA, 2025, pp. 1584-1590