大模型推理能力

REMA: A Unified Reasoning Manifold Framework for Interpreting Large Language Model

Bo Li, Guanzhi Deng, Ronghao Chen, Junrong Yue, Shuo Zhang, Qinghua Zhao, Linqi Song, Lijie Wen

机构 * Tsinghua University（清华大学） ； City University of Hong Kong（香港城市大学） ； Peking University（北京大学） ； Beijing University of Posts and Telecommunications（北京邮电大学） ； Beihang University（北航） ； Baidu Inc（百度公司） 纠错

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

Disagreements in Reasoning: How a Model's Thinking Process Dictates Persuasion in Multi-Agent Systems

Haodong Zhao, Jidong Li, Zhaomin Wu, Tianjie Ju, Zhuosheng Zhang, Bingsheng He, Gongshen Liu

机构 * School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机科学学院） ； National University of Singapore（新加坡国立大学） ； Inner Mongolia Research Institute, Shanghai Jiao Tong University（上海交通大学内蒙古研究院） 纠错

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

Comments Work in progress

Dynamic Reasoning Chains through Depth-Specialized Mixture-of-Experts in Transformer Architectures

Sampurna Roy, Ayan Sar, Anurag Kaushish, Kanav Gupta, Tanupriya Choudhury, Abhijit Kumar

机构 * School of Computer Science University of Petroleum 纠错

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

Comments Submitted in IEEE International Conference on Big Data 2025

Combining Evidence and Reasoning for Biomedical Fact-Checking

Mariano Barone, Antonio Romano, Giuseppe Riccio, Marco Postiglione, Vincenzo Moscato

机构 * University of Naples Federico II（那不勒斯费德里科二世大学） ； Northwestern University（西北大学） 纠错

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

Comments Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2025

Metacognitive Reuse: Turning Recurring LLM Reasoning Into Concise Behaviors

Aniket Didolkar, Nicolas Ballas, Sanjeev Arora, Anirudh Goyal

机构 * Meta ； Mila-Quebec AI Institute, University of Montreal（魁北克AI研究所，蒙特利尔大学） ； Princeton University（普林斯顿大学） ； Mila--Quebec AI Institute, Université de Montréal（魁北克AI研究所，蒙特利尔大学） 纠错

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

Comments 18 pages, 9 Figures, 5 Tables

Pre-Storage Reasoning for Episodic Memory: Shifting Inference Burden to Memory for Personalized Dialogue

Sangyeop Kim, Yohan Lee, Sanghwa Kim, Hyunjong Kim, Sungzoon Cho

机构 * Seoul National University（首尔国立大学） ； Coxwave ； KAIST（韩国科学技术院） 纠错

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

Comments Accepted by EMNLP 2025 (Findings)

When LLM Meets Time Series: Can LLMs Perform Multi-Step Time Series Reasoning and Inference

Wen Ye, Jinbo Liu, Defu Cao, Wei Yang, Yan Liu

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

A Simple "Try Again" Can Elicit Multi-Turn LLM Reasoning

Licheng Liu, Zihan Wang, Linjie Li, Chenwei Xu, Yiping Lu, Han Liu, Avirup Sil, Manling Li

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

Explicit v.s. Implicit Memory: Exploring Multi-hop Complex Reasoning Over Personalized Information

Zeyu Zhang, Yang Zhang, Haoran Tan, Rui Li, Xu Chen

机构 * Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学人工智能学院） ； National University of Singapore（新加坡国立大学） 纠错

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

Comments 15 pages, 13 figures, 3 tables

Designing Memory-Augmented AR Agents for Spatiotemporal Reasoning in Personalized Task Assistance

Dongwook Choi, Taeyoon Kwon, Dongil Yang, Hyojun Kim, Jinyoung Yeo

机构 * Language & AGI Lab（语言与人工智能实验室） 纠错

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

Comments 7 pages, 2 figures

Hop, Skip, and Overthink: Diagnosing Why Reasoning Models Fumble during Multi-Hop Analysis

Anushka Yadav, Isha Nalawade, Srujana Pillarichety, Yashwanth Babu, Reshmi Ghosh, Samyadeep Basu, Wenlong Zhao, Ali Nasaeh, Sriram Balasubramanian, Soundararajan Srinivasan

机构 * Microsoft（微软公司） ； University of Massachusetts（马萨诸塞大学） ； University of Maryland（马里兰大学） 纠错

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

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge

Yeonjun In, Wonjoong Kim, Sangwu Park, Chanyoung Park

机构 * KAIST（韩国科学技术院） 纠错

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

Comments under review

Advancing Compositional LLM Reasoning with Structured Task Relations in Interactive Multimodal Communications

Xinye Cao, Hongcan Guo, Guoshun Nan, Jiaoyang Cui, Haoting Qian, Yihan Lin, Yilin Peng, Diyang Zhang, Yanzhao Hou, Huici Wu, Xiaofeng Tao, Tony Q. S. Quek

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

Comments Accepted by IEEE JSAC. This work has been submitted to the IEEE for possible publication

Specification Self-Correction: Mitigating In-Context Reward Hacking Through Test-Time Refinement

Víctor Gallego

机构 * Komorebi AI Technologies（Komorebi人工智能技术） 纠错

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

Comments Accepted to SCALR Workshop @ COLM 2025

Reinforcement Learning in hyperbolic space for multi-step reasoning

Tao Xu, Dung-Yang Lee, Momiao Xiong

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

Comments 53 pages, 5 figures

MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents

Zijian Zhou, Ao Qu, Zhaoxuan Wu, Sunghwan Kim, Alok Prakash, Daniela Rus, Jinhua Zhao, Bryan Kian Hsiang Low, Paul Pu Liang

机构 * Singapore-MIT Alliance for Research and Technology Centre（新加坡-麻省理工联合研究技术中心） ； National University of Singapore（国立新加坡大学） ； MIT（麻省理工学院） ； Yonsei University（延世大学） 纠错

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

Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs

Yangning Li, Weizhi Zhang, Yuyao Yang, Wei-Chieh Huang, Yaozu Wu, Junyu Luo, Yuanchen Bei, Henry Peng Zou, Xiao Luo, Yusheng Zhao, Chunkit Chan, Yankai Chen, Zhongfen Deng, Yinghui Li, Hai-Tao Zheng, Dongyuan Li, Renhe Jiang, Ming Zhang, Yangqiu Song, Philip S. Yu

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

Comments submitted to ARR May

FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning

Zhehao Zhang, Weijie Xu, Fanyou Wu, Chandan K. Reddy

机构 * The Ohio State University（俄亥俄州立大学） ； Amazon（亚马逊） 纠错

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

Comments Accepted at COLM 2025

Knowledge-Aware Self-Correction in Language Models via Structured Memory Graphs

Swayamjit Saha

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

Comments 8 pages, 4 figures

KAG-Thinker: Interactive Thinking and Deep Reasoning in LLMs via Knowledge-Augmented Generation

Dalong Zhang, Jun Xu, Jun Zhou, Lei Liang, Lin Yuan, Ling Zhong, Mengshu Sun, Peilong Zhao, QiWei Wang, Xiaorui Wang, Xinkai Du, YangYang Hou, Yu Ao, ZhaoYang Wang, Zhengke Gui, ZhiYing Yi, Zhongpu Bo, Haofen Wang, Huajun Chen

机构 * Inclusion AI Ant Group（Inclusion AI蚂蚁集团） 纠错

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

APO: Enhancing Reasoning Ability of MLLMs via Asymmetric Policy Optimization

Minjie Hong, Zirun Guo, Yan Xia, Zehan Wang, Ziang Zhang, Tao Jin, Zhou Zhao

机构 * Zhejiang University（浙江大学） 纠错

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

Disentangling Reasoning and Knowledge in Medical Large Language Models

Rahul Thapa, Qingyang Wu, Kevin Wu, Harrison Zhang, Angela Zhang, Eric Wu, Haotian Ye, Suhana Bedi, Nevin Aresh, Joseph Boen, Shriya Reddy, Ben Athiwaratkun, Shuaiwen Leon Song, James Zou

机构 * Stanford University（斯坦福大学） ； Together AI ； University of California, San Francisco（加州大学旧金山分校） 纠错

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

Med-U1: Incentivizing Unified Medical Reasoning in LLMs via Large-scale Reinforcement Learning

Xiaotian Zhang, Yuan Wang, Zhaopeng Feng, Ruizhe Chen, Zhijie Zhou, Yan Zhang, Hongxia Xu, Jian Wu, Zuozhu Liu

机构 * Zhejiang University（浙江大学） ； Bytedance Inc（字节跳动公司） ； Zhejiang Key Laboratory of Medical Imaging Artificial Intelligence（浙江省医学影像人工智能重点实验室） 纠错

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

Rethinking External Slow-Thinking: From Snowball Errors to Probability of Correct Reasoning

Zeyu Gan, Yun Liao, Yong Liu

机构 * Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China（中国人民大学人工智能学院） ； Beijing Key Laboratory of Research on Large Models（北京大型模型研究关键实验室） ； Engineering Research Center of Next-Generation Intelligent Search（下一代智能搜索工程研究中心） ； College of Artificial Intelligence, Tianjin University of Science（天津科技大学人工智能学院） 纠错

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

Comments Published as a conference paper in ICML 2025

Entropy-based Exploration Conduction for Multi-step Reasoning

Jinghan Zhang, Xiting Wang, Fengran Mo, Yeyang Zhou, Wanfu Gao, Kunpeng Liu

机构 * Portland State University（波特兰州立大学） ； University of Montreal（蒙特利尔大学） ； Uber ； Jilin University（吉林大学） 纠错

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

Comments Accepted by ACL 2025

A Survey of Task-Oriented Knowledge Graph Reasoning: Status, Applications, and Prospects

Guanglin Niu, Bo Li, Yangguang Lin

机构 * School of Artificial Intelligence, Beihang University（北航人工智能学院） ； School of Information Science and Technology, Beijing Forestry University（北京林业大学信息科学与技术学院） 纠错

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

Comments 45 pages, 17 figures, 12 tables

Reliable Reasoning Path: Distilling Effective Guidance for LLM Reasoning with Knowledge Graphs

Yilin Xiao, Chuang Zhou, Qinggang Zhang, Bo Li, Qing Li, Xiao Huang

机构 * The Hong Kong Polytechnic University（香港理工大学） 纠错

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

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning

Kongcheng Zhang, Qi Yao, Shunyu Liu, Yingjie Wang, Baisheng Lai, Jieping Ye, Mingli Song, Dacheng Tao

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

Com$^2$: A Causal-Guided Benchmark for Exploring Complex Commonsense Reasoning in Large Language Models

Kai Xiong, Xiao Ding, Yixin Cao, Yuxiong Yan, Li Du, Yufei Zhang, Jinglong Gao, Jiaqian Liu, Bing Qin, Ting Liu

机构 * Research Center for Social Computing and Interactive Robotics（社会计算与交互机器人研究中心） ； Harbin Institute of Technology（哈尔滨工业大学） ； Institute of Trustworthy Embodied AI（可信具身人工智能研究院） ； Fudan University（复旦大学） ； Beijing Academy of Artificial Intelligence（北京人工智能研究院） ； Nanjing University（南京大学） 纠错

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

Comments Accepted by ACL 2025 Main Conference

Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning

Chen Qian, Dongrui Liu, Haochen Wen, Zhen Bai, Yong Liu, Jing Shao

机构 * Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学北京校区人工智能学院） ； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； University College London, University of London（伦敦大学大学学院） ； Dalian University of Technology（大连理工大学） 纠错

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

Comments Preprint. Under review