大模型推理能力

Multi-Path Collaborative Reasoning via Reinforcement Learning

基于强化学习的多路径协作推理

Jindi Lv, Yuhao Zhou, Zheng Zhu, Xiaofeng Wang, Guan Huang, Jiancheng Lv

机构 * Sichuan University（四川大学） ； GigaAI ； Tsinghua University（清华大学） 纠错

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

AI总结 本文提出M3PO框架，通过多路径协作机制提升大语言模型的推理能力，实现更可靠和高效的多步推理。

SETS: Leveraging Self-Verification and Self-Correction for Improved Test-Time Scaling

SETS：利用自我验证和自我校正以提高测试时间扩展

Jiefeng Chen, Jie Ren, Xinyun Chen, Chengrun Yang, Ruoxi Sun, Jinsung Yoon, Sercan Ö Arık

机构 * Google Cloud AI Research（谷歌云人工智能研究） 纠错

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

AI总结 SETS通过结合并行与顺序技术，利用LLMs的自我改进能力，在无需模型训练的情况下提升测试时间扩展性能。

Comments Published in Transactions on Machine Learning Research (11/2025)

Lessons from Studying Two-Hop Latent Reasoning

从双跳潜在推理研究中获得的启示

Mikita Balesni, Tomek Korbak, Owain Evans

机构 * Apollo Research（Apollo研究机构） ； UK AI Security Institute（英国人工智能安全研究所） ； UC Berkeley（加州大学伯克利分校） ； TruthfulAI 纠错

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

AI总结 研究通过双跳问答任务揭示LLM潜在推理能力，发现模型在合成事实组合上表现不足，但能处理混合事实场景，强调避免误判推理能力的必要性。

TokenSqueeze: Performance-Preserving Compression for Reasoning LLMs

Yuxiang Zhang, Zhengxu Yu, Weihang Pan, Zhongming Jin, Qiang Fu, Deng Cai, Binbin Lin, Jieping Ye

机构 * State Key Lab of CAD&CG, Zhejiang University（浙江大学CAD&CG国家重点实验室） ； School of Software Technology, Zhejiang University（浙江大学软件学院） ； Alibaba Cloud（阿里云） ； Zhiyuan Research Institute（智源研究院） 纠错

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

Comments Accepted to NeurIPS 2025

SEAL: Steerable Reasoning Calibration of Large Language Models for Free

Runjin Chen, Zhenyu Zhang, Junyuan Hong, Souvik Kundu, Zhangyang Wang

机构 * The University of Texas at Austin（德克萨斯大学奥斯汀分校） ； Intel（英特尔） 纠错

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

Sherlock: Self-Correcting Reasoning in Vision-Language Models

Yi Ding, Ruqi Zhang

机构 * Department of Computer Science, Purdue University, USA（计算机科学系，普渡大学） 纠错

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

Comments Published at NeurIPS 2025, 27 pages

Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills

Changsheng Wang, Chongyu Fan, Yihua Zhang, Jinghan Jia, Dennis Wei, Parikshit Ram, Nathalie Baracaldo, Sijia Liu

机构 * Michigan State University（密歇根州立大学） ； IBM Research（IBM研究院） 纠错

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

Comments Accepted by EMNLP 2025

ConciseHint: Boosting Efficient Reasoning via Continuous Concise Hints during Generation

Siao Tang, Xinyin Ma, Gongfan Fang, Xinchao Wang

机构 * 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)；chain-of-thought(abstract)；CoT(abstract)；分类 cs.CL、cs.AI

Comments Compare with more baselines, add more in-depth analysis, and re-evaluate the GPQA-D benchmark. Codes are available at https://github.com/tsa18/ConciseHint

R-Capsule: Compressing High-Level Plans for Efficient Large Language Model Reasoning

Hongyu Shan, Mingyang Song, Chang Dai, Di Liang, Han Chen

机构 * Tianjin University（天津大学） ； Tencent Hunyuan（腾讯文元） ； Peking University（北京大学） ； Fudan University（复旦大学） ； National Engineering Research Center of Educational Big Data and the Faculty of Artificial Intelligence in Education, Central China Normal University（教育大数据国家工程研究中心和教育人工智能学院，中央财经大学） 纠错

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

Dynamic Early Exit in Reasoning Models

Chenxu Yang, Qingyi Si, Yongjie Duan, Zheliang Zhu, Chenyu Zhu, Qiaowei Li, Minghui Chen, Zheng Lin, Weiping Wang

机构 * Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所） ； School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络安全学院） ； Huawei Technologies Co., Ltd.（华为技术有限公司） 纠错

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

Comments 41 pages, 18 figures

From Roots to Rewards: Dynamic Tree Reasoning with Reinforcement Learning

Ahmed Bahloul, Simon Malberg

机构 * School of Computation, Information and Technology（计算、信息与技术学院） 纠错

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

Comments RARA Workshop @ ICDM 2025

SightSound-R1: Cross-Modal Reasoning Distillation from Vision to Audio Language Models

Qiaolin Wang, Xilin Jiang, Linyang He, Junkai Wu, Nima Mesgarani

机构 * Columbia University（哥伦比亚大学） ； University of Washington（华盛顿大学） 纠错

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

LLM-Guided Semantic Relational Reasoning for Multimodal Intent Recognition

Qianrui Zhou, Hua Xu, Yifan Wang, Xinzhi Dong, Hanlei Zhang

机构 * Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系） ； School of Information Science and Engineering, Hebei University of Science and Technology（河北科技大学信息科学与工程学院） 纠错

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

Comments Accepted by EMNLP 2025 (Main Track, Long Paper)

Datarus-R1: An Adaptive Multi-Step Reasoning LLM for Automated Data Analysis

Ayoub Ben Chaliah, Hela Dellagi

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

Aware First, Think Less: Dynamic Boundary Self-Awareness Drives Extreme Reasoning Efficiency in Large Language Models

Qiguang Chen, Dengyun Peng, Jinhao Liu, HuiKang Su, Jiannan Guan, Libo Qin, Wanxiang Che

机构 * LARG, Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology（大型语言模型研究组，社会计算与交互机器人研究中心，哈尔滨工业大学） ； School of Computer Science and Engineering, Central South University（计算机科学与工程学院，中南大学） 纠错

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

Comments Preprint

Reasoning Capabilities of Large Language Models on Dynamic Tasks

Annie Wong, Thomas Bäck, Aske Plaat, Niki van Stein, Anna V. Kononova

机构 * Leiden Institute of Advanced Computer Science（莱顿先进计算机科学研究所） ； Leiden University（莱顿大学） 纠错

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

Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey

Jason Zhu, Hongyu Li

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

Seewo's Submission to MLC-SLM: Lessons learned from Speech Reasoning Language Models

Bo Li, Chengben Xu, Wufeng Zhang

机构 * Seewo（赛沃） 纠错

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

Can Separators Improve Chain-of-Thought Prompting?

Yoonjeong Park, Hyunjin Kim, Chanyeol Choi, Junseong Kim, Jy-yong Sohn

机构 * Yonsei University（延世大学） ； Linq 纠错

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

Comments IEEE FLLM 2024

Towards Better Chain-of-Thought: A Reflection on Effectiveness and Faithfulness

Jiachun Li, Pengfei Cao, Yubo Chen, Jiexin Xu, Huaijun Li, Xiaojian Jiang, Kang Liu, Jun Zhao

机构 * School of Artificial Intelligence, University of Chinese Academy of Sciences（人工智能学院，中国科学院大学） ； The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences（复杂系统认知与决策智能重点实验室，中国科学院自动化研究所） ； China Merchants Bank（中国民生银行） 纠错

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

Comments 18 pages, 21 figures, accepted by ACL 2025 Findings

Reasoning Can Hurt the Inductive Abilities of Large Language Models

Haibo Jin, Peiyan Zhang, Man Luo, Haohan Wang

机构 * School of Information Sciences University of Illinois at Urbana-Champaign（信息科学学院伊利诺伊大学厄巴纳-香槟分校） ； Computer Science and Engineering HKUST（计算机科学与工程香港科技大学） ； Research Scientist, Intel Labs（英特尔实验室研究员） ； School of Information Sciences University of Illinois Urbana-Champaign（信息科学学院伊利诺伊大学厄巴纳-香槟分校） 纠错

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

Comments 26 pages

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models

Zekai Zhao, Qi Liu, Kun Zhou, Zihan Liu, Yifei Shao, Zhiting Hu, Biwei Huang

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

Causal Graphs Meet Thoughts: Enhancing Complex Reasoning in Graph-Augmented LLMs

Hang Luo, Jian Zhang, Chujun Li

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

Comments 18 pages, 3 figures, 3 tables

Larger Language Models Don't Care How You Think: Why Chain-of-Thought Prompting Fails in Subjective Tasks

Georgios Chochlakis, Niyantha Maruthu Pandiyan, Kristina Lerman, Shrikanth Narayanan

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

Comments 5 pages, 2 figures, 1 table. arXiv admin note: text overlap with arXiv:2403.17125

Journal ref ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2025

A Survey on Feedback-based Multi-step Reasoning for Large Language Models on Mathematics

Ting-Ruen Wei, Haowei Liu, Xuyang Wu, Yi Fang

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

Layered Chain-of-Thought Prompting for Multi-Agent LLM Systems: A Comprehensive Approach to Explainable Large Language Models

Manish Sanwal

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

CoT-Driven Framework for Short Text Classification: Enhancing and Transferring Capabilities from Large to Smaller Model

Hui Wu, Yuanben Zhang, Zhonghe Han, Yingyan Hou, Lei Wang, Siye Liu, Qihang Gong, Yunping Ge

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

Comments Knowledge-Based Systems

Chain-of-Thought Predictive Control

Zhiwei Jia, Vineet Thumuluri, Fangchen Liu, Linghao Chen, Zhiao Huang, Hao Su

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

Comments ICML 2024; project page at https://sites.google.com/view/cotpc

Extending Token Computation for LLM Reasoning

Bingli Liao, Danilo Vasconcellos Vargas

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

Empowering Multi-step Reasoning across Languages via Tree-of-Thoughts

Leonardo Ranaldi, Giulia Pucci, Federico Ranaldi, Elena Sofia Ruzzetti, Fabio Massimo Zanzotto

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

Comments Findings of the Association for Computational Linguistics: NAACL 2024

Journal ref 2024.findings-naacl.78