大模型推理能力

SignalLLM: A General-Purpose LLM Agent Framework for Automated Signal Processing

Junlong Ke, Qiying Hu, Shenghai Yuan, Yuecong Xu, Jianfei Yang

机构 * Department of Electronic Engineering, Tsinghua University（清华大学电子工程系） ； School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore（南洋理工大学电子与电气工程学院） ； MARS Lab, Nanyang Technological University, Singapore（南洋理工大学MARS实验室） 纠错

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

Comments 11 pages

Spontaneous Giving and Calculated Greed in Language Models

Yuxuan Li, Hirokazu Shirado

机构 * School of Computer Science Carnegie Mellon University（计算机科学学院卡内基梅隆大学） 纠错

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

Comments Accepted to EMNLP 2025 main conference and selected as an Oral Presentation

Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving

Xiangru Tang, Tianrui Qin, Tianhao Peng, Ziyang Zhou, Daniel Shao, Tingting Du, Xinming Wei, Peng Xia, Fang Wu, He Zhu, Ge Zhang, Jiaheng Liu, Xingyao Wang, Sirui Hong, Chenglin Wu, Hao Cheng, Chi Wang, Wangchunshu Zhou

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

Benchmarking GPT-5 for biomedical natural language processing

Yu Hou, Zaifu Zhan, Min Zeng, Yifan Wu, Shuang Zhou, Rui Zhang

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

Select-Then-Decompose: From Empirical Analysis to Adaptive Selection Strategy for Task Decomposition in Large Language Models

Shuodi Liu, Yingzhuo Liu, Zi Wang, Yusheng Wang, Huijia Wu, Liuyu Xiang, Zhaofeng He

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

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

Comments Accepted to the Main Conference of EMNLP 2025 (Oral)

LANPO: Bootstrapping Language and Numerical Feedback for Reinforcement Learning in LLMs

Ang Li, Yifei Wang, Zhihang Yuan, Stefanie Jegelka, Yisen Wang

机构 * MIT（麻省理工学院） 纠错

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

Evaluating Prompting Strategies and Large Language Models in Systematic Literature Review Screening: Relevance and Task-Stage Classification

Binglan Han, Anuradha Mathrani, Teo Susnjak

机构 * School of Mathematical and Computational Sciences（数学与计算科学学院） 纠错

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

IPBench: Benchmarking the Knowledge of Large Language Models in Intellectual Property

Qiyao Wang, Guhong Chen, Hongbo Wang, Huaren Liu, Minghui Zhu, Zhifei Qin, Linwei Li, Yilin Yue, Shiqiang Wang, Jiayan Li, Yihang Wu, Ziqiang Liu, Longze Chen, Run Luo, Liyang Fan, Jiaming Li, Lei Zhang, Kan Xu, Chengming Li, Hamid Alinejad-Rokny, Shiwen Ni, Yuan Lin, Min Yang

机构 * Shenzhen Key Laboratory for High Performance Data Mining, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, China（深圳高性能数据挖掘重点实验室，深圳先进技术研究院，中国科学院，中国） ； University of Chinese Academy of Sciences, China（中国科学院大学，中国） ； Dalian University of Technology, China（大连理工大学，中国） ； School of Biomedical Engineering, UNSW Sydney, Australia（生物医学工程学院，新南威尔士大学悉尼分校，澳大利亚） ； Shenzhen MSU-BIT University, China（深圳MSU-BIT大学，中国） ； Shenzhen University of Advanced Technology, China（深圳大学先进技术学院，中国） 纠错

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

Comments 71 pages, 75 figures, 53 tables

Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving

Pengxiang Li, Yinan Zheng, Yue Wang, Huimin Wang, Hang Zhao, Jingjing Liu, Xianyuan Zhan, Kun Zhan, Xianpeng Lang

机构 * LiAuto ； Tsinghua University（清华大学） 纠错

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

The Sum Leaks More Than Its Parts: Compositional Privacy Risks and Mitigations in Multi-Agent Collaboration

Vaidehi Patil, Elias Stengel-Eskin, Mohit Bansal

机构 * UNC Chapel Hill（北卡罗来纳大学教堂山分校） ； 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(abstract)；chain-of-thought(abstract)；分类 cs.CL、cs.AI

Comments Code: https://github.com/Vaidehi99/MultiAgentPrivacy

METAL: A Multi-Agent Framework for Chart Generation with Test-Time Scaling

Bingxuan Li, Yiwei Wang, Jiuxiang Gu, Kai-Wei Chang, Nanyun Peng

机构 * University of California, Los Angeles（加州大学洛杉矶分校） ； University of California, Merced（加州大学默塞德分校） ； Adobe Research（Adobe研究） 纠错

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

Comments ACL2025 Main

KERAG: Knowledge-Enhanced Retrieval-Augmented Generation for Advanced Question Answering

Yushi Sun, Kai Sun, Yifan Ethan Xu, Xiao Yang, Xin Luna Dong, Nan Tang, Lei Chen

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

Comments Accepted by EMNLP Findings 2025

COCORELI: Cooperative, Compositional Reconstitution \& Execution of Language Instructions

Swarnadeep Bhar, Omar Naim, Eleni Metheniti, Bastien Navarri, Loïc Cabannes, Morteza Ezzabady, Nicholas Asher

机构 * IRIT ； ENS Paris-Saclay（巴黎-萨克雷大学） ； CNRS（国家科学研究中心） 纠错

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

Comments 18 pages

MoSE: Skill-by-Skill Mixture-of-Experts Learning for Embodied Autonomous Machines

Lu Xu, Jiaqian Yu, Xiongfeng Peng, Yiwei Chen, Weiming Li, Jaewook Yoo, Sunghyun Chunag, Dongwook Lee, Daehyun Ji, Chao Zhang

机构 * Advanced Research Lab, Samsung Research China-Beijing（三星研究院中国北京先进研究实验室） ； Manufacturing/Material Handling AI Lab (DS AI Center)（制造/物料处理AI实验室（DS AI中心）） 纠错

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

The benefits of query-based KGQA systems for complex and temporal questions in LLM era

Artem Alekseev, Mikhail Chaichuk, Miron Butko, Alexander Panchenko, Elena Tutubalina, Oleg Somov

机构 * Skoltech（斯克里普契克技术大学） ； AIRI ； HSE University（俄罗斯高等经济大学） ； SaluteDevices ； Kazan Federal University（卡扎ン联邦大学） ； Moscow Institute of Physics（莫斯科物理技术学院） 纠错

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

Comments 15 pages, 3 figures, 7 tables

Journal ref Lecture Notes in Computer Science, vol 15836. Springer, Cham., 2025

ReVISE: Learning to Refine at Test-Time via Intrinsic Self-Verification

Hyunseok Lee, Seunghyuk Oh, Jaehyung Kim, Jinwoo Shin, Jihoon Tack

机构 * Yonsei University（延世大学） 纠错

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

Comments Published as conference proceeding for ICML 2025. First two authors contributed equally

Large Linguistic Models: Investigating LLMs' metalinguistic abilities

Gašper Beguš, Maksymilian Dąbkowski, Ryan Rhodes

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

Journal ref IEEE Transactions on Artificial Intelligence 2025

OMEGA: Can LLMs Reason Outside the Box in Math? Evaluating Exploratory, Compositional, and Transformative Generalization

Yiyou Sun, Shawn Hu, Georgia Zhou, Ken Zheng, Hannaneh Hajishirzi, Nouha Dziri, Dawn Song

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

Re-Initialization Token Learning for Tool-Augmented Large Language Models

Chenghao Li, Liu Liu, Baosheng Yu, Jiayan Qiu, Yibing Zhan

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

Automatic Generation of Inference Making Questions for Reading Comprehension Assessments

Wanjing Anya Ma, Michael Flor, Zuowei Wang

机构 * Stanford University（斯坦福大学） ； ETS Research Institute（教育考试服务中心研究所） 纠错

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

Comments Accepted to the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025), co-located with the ACL 2025

A Survey on (M)LLM-Based GUI Agents

Fei Tang, Haolei Xu, Hang Zhang, Siqi Chen, Xingyu Wu, Yongliang Shen, Wenqi Zhang, Guiyang Hou, Zeqi Tan, Yuchen Yan, Kaitao Song, Jian Shao, Weiming Lu, Jun Xiao, Yueting Zhuang

机构 * Zhejiang University（浙江大学） ； Microsoft Research Asia（微软亚洲研究院） 纠错

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

Task Memory Engine: Spatial Memory for Robust Multi-Step LLM Agents

Ye Ye

机构 * New York University（纽约大学） 纠错

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

Comments Under review. 9 pages main content, 15 pages appendix, 5 figures

Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards

Xiaoyuan Liu, Tian Liang, Zhiwei He, Jiahao Xu, Wenxuan Wang, Pinjia He, Zhaopeng Tu, Haitao Mi, Dong Yu

机构 * Tencent（腾讯） ； CUHK（香港中文大学） 纠错

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

Comments code available at https://github.com/xyliu-cs/RISE

Sparks: Multi-Agent Artificial Intelligence Model Discovers Protein Design Principles

Alireza Ghafarollahi, Markus J. Buehler

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

Meta-Thinking in LLMs via Multi-Agent Reinforcement Learning: A Survey

Ahsan Bilal, Muhammad Ahmed Mohsin, Muhammad Umer, Muhammad Awais Khan Bangash, Muhammad Ali Jamshed

机构 * University of Oklahoma（俄克拉荷马大学） ； Stanford University（斯坦福大学） ； School of Electrical and Computer Engineering, Oklahoma State University（电气与计算机工程学院，俄克拉荷马州立大学） ； University of Glasgow（格拉斯哥大学） 纠错

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

Comments Submitted to IEEE Transactions on Artificial Intelligence

Knowledge-Driven Feature Selection and Engineering for Genotype Data with Large Language Models

Joseph Lee, Shu Yang, Jae Young Baik, Xiaoxi Liu, Zhen Tan, Dawei Li, Zixuan Wen, Bojian Hou, Duy Duong-Tran, Tianlong Chen, Li Shen

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

Comments accepted by AMIA-IS'25: AMIA Informatics Summit [Marco Ramoni Distinguished Paper Award for Translational Bioinformatics]

Rethinking Reflection in Pre-Training

Essential AI, :, Darsh J Shah, Peter Rushton, Somanshu Singla, Mohit Parmar, Kurt Smith, Yash Vanjani, Ashish Vaswani, Adarsh Chaluvaraju, Andrew Hojel, Andrew Ma, Anil Thomas, Anthony Polloreno, Ashish Tanwer, Burhan Drak Sibai, Divya S Mansingka, Divya Shivaprasad, Ishaan Shah, Karl Stratos, Khoi Nguyen, Michael Callahan, Michael Pust, Mrinal Iyer, Philip Monk, Platon Mazarakis, Ritvik Kapila, Saurabh Srivastava, Tim Romanski

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

StableToolBench-MirrorAPI: Modeling Tool Environments as Mirrors of 7,000+ Real-World APIs

Zhicheng Guo, Sijie Cheng, Yuchen Niu, Hao Wang, Sicheng Zhou, Wenbing Huang, Yang Liu

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

Output Length Effect on DeepSeek-R1's Safety in Forced Thinking

Xuying Li, Zhuo Li, Yuji Kosuga, Victor Bian

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

Transformers Learn to Implement Multi-step Gradient Descent with Chain of Thought

Jianhao Huang, Zixuan Wang, Jason D. Lee

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

Comments ICLR 2025 Spotlight