大模型推理能力

SSR: Socratic Self-Refine for Large Language Model Reasoning

Haizhou Shi, Ye Liu, Bo Pang, Zeyu Leo Liu, Hao Wang, Silvio Savarese, Caiming Xiong, Yingbo Zhou, Semih Yavuz

机构 * Salesforce AI Research（Salesforce人工智能研究） ； Rutgers University（罗格斯大学） ； The University of Texas at Austin（德克萨斯大学奥斯汀分校） 纠错

专题命中 复杂问题求解 ：reasoning(title,abstract)；self-correction(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Preprint; work in progress

Beyond the Black Box: Demystifying Multi-Turn LLM Reasoning with VISTA

Yiran Zhang, Mingyang Lin, Mark Dras, Usman Naseem

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

Small Models Struggle to Learn from Strong Reasoners

Yuetai Li, Xiang Yue, Zhangchen Xu, Fengqing Jiang, Luyao Niu, Bill Yuchen Lin, Bhaskar Ramasubramanian, Radha Poovendran

机构 * University of Washington（华盛顿大学） ； Carnegie Mellon University（卡内基梅隆大学） ； Western Washington University（西雅图华盛顿大学） 纠错

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

AgentEvolver: Towards Efficient Self-Evolving Agent System

Yunpeng Zhai, Shuchang Tao, Cheng Chen, Anni Zou, Ziqian Chen, Qingxu Fu, Shinji Mai, Li Yu, Jiaji Deng, Zouying Cao, Zhaoyang Liu, Bolin Ding, Jingren Zhou

机构 * Tongyi Lab（通义实验室） ； Alibaba Group（阿里巴巴集团） 纠错

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

From Capabilities to Performance: Evaluating Key Functional Properties of LLM Architectures in Penetration Testing

Lanxiao Huang, Daksh Dave, Tyler Cody, Peter Beling, Ming Jin

机构 * Bradley Department of Electrical and Computer Engineering, Virginia Tech（弗吉尼亚理工大学电气与计算机工程系布雷拉德部门） ； National Security Institute, Virginia Tech（弗吉尼亚理工大学国家安全研究所） 纠错

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

Journal ref Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 15890 to 15916, Suzhou, China, November 2025

Evaluating Prompting Strategies with MedGemma for Medical Order Extraction

Abhinand Balachandran, Bavana Durgapraveen, Gowsikkan Sikkan Sudhagar, Vidhya Varshany J S, Sriram Rajkumar

机构 * EXL Health AI Lab at MEDIQA-OE 2025（EXL健康AI实验室） 纠错

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

Comments 2 figures 7 pages

Towards an Agentic Workflow for Internet Measurement Research

Alagappan Ramanathan, Eunju Kang, Dongsu Han, Sangeetha Abdu Jyothi

机构 * University of California, Irvine（加州大学伊维奇分校） 纠错

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

Exploring State Tracking Capabilities of Large Language Models

Kiamehr Rezaee, Jose Camacho-Collados, Mohammad Taher Pilehvar

机构 * Cardiff NLP（卡迪夫NLP） 纠错

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