大模型推理能力

Towards Interpretable Renal Health Decline Forecasting via Multi-LMM Collaborative Reasoning Framework

Peng-Yi Wu, Pei-Cing Huang, Ting-Yu Chen, Chantung Ku, Ming-Yen Lin, Yihuang Kang

专题命中 其他推理 ：reasoning(title,abstract)；分类 cs.AI、cs.LG

UloRL:An Ultra-Long Output Reinforcement Learning Approach for Advancing Large Language Models' Reasoning Abilities

Dong Du, Shulin Liu, Tao Yang, Shaohua Chen, Yang Li

机构 * Tencent Hunyuan Team（腾讯文言团队） 纠错

专题命中 其他推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

Comments 12 pages

Corrupted by Reasoning: Reasoning Language Models Become Free-Riders in Public Goods Games

David Guzman Piedrahita, Yongjin Yang, Mrinmaya Sachan, Giorgia Ramponi, Bernhard Schölkopf, Zhijing Jin

专题命中 其他推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

Comments Published at COLM 2025

Improving LLM Reasoning for Vulnerability Detection via Group Relative Policy Optimization

Marco Simoni, Aleksandar Fontana, Giulio Rossolini, Andrea Saracino

机构 * Institute of Informatics and Telematics, National Research Council of Italy（意大利国家研究理事会信息与电信研究所） ； Department of Excellence in Robotics and AI, TeCIP, Scuola Superiore Sant'Anna（卓越机器人与人工智能系，TeCIP，圣安娜高等学院） 纠错

专题命中 其他推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

Comments Under Review

CaughtCheating: Is Your MLLM a Good Cheating Detective? Exploring the Boundary of Visual Perception and Reasoning

Ming Li, Chenguang Wang, Yijun Liang, Xiyao Wang, Yuhang Zhou, Xiyang Wu, Yuqing Zhang, Ruiyi Zhang, Tianyi Zhou

机构 * University of Maryland, College Park（马里兰大学学院 park） 纠错

专题命中 其他推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

Graph Linearization Methods for Reasoning on Graphs with Large Language Models

Christos Xypolopoulos, Guokan Shang, Xiao Fei, Giannis Nikolentzos, Hadi Abdine, Iakovos Evdaimon, Michail Chatzianastasis, Giorgos Stamou, Michalis Vazirgiannis

机构 * Ecole Polytechnique（巴黎高等理工学院） ； MBZUAI（马克斯·普朗克人工智能研究所） ； NTUA（希腊国家技术研究中心） ； University of Peloponnese（希腊皮洛斯大学） 纠错

专题命中 其他推理 ：reasoning(title,abstract)；分类 cs.CL、cs.LG

Trust Region Preference Approximation: A simple and stable reinforcement learning algorithm for LLM reasoning

Xuerui Su, Shufang Xie, Guoqing Liu, Yingce Xia, Renqian Luo, Peiran Jin, Zhiming Ma, Yue Wang, Zun Wang, Yuting Liu

专题命中 其他推理 ：reasoning(title,abstract)；分类 cs.AI、cs.LG

Comments 10pages

Causes in neuron diagrams, and testing causal reasoning in Large Language Models. A glimpse of the future of philosophy?

Louis Vervoort, Vitaly Nikolaev

专题命中 其他推理 ：reasoning(title,abstract)；分类 cs.AI、cs.LG

Comments Accepted by Journal for General Philosophy of Science

Efficient Reasoning Through Suppression of Self-Affirmation Reflections in Large Reasoning Models

Kaiyuan Liu, Chen Shen, Zhanwei Zhang, Junjie Liu, Xiaosong Yuan, Jieping ye

专题命中 其他推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

Comments Under review

Eliciting Critical Reasoning in Retrieval-Augmented Language Models via Contrastive Explanations

Leonardo Ranaldi, Marco Valentino, Andrè Freitas

机构 * Idiap Research Institute（Idiap研究机构） ； Department of Computer Science, University of Manchester（曼彻斯特大学计算机科学系） ； National Biomarker Centre (NBC), CRUK Manchester Institute（国家生物标志物中心（NBC），CRUK曼彻斯特研究所） 纠错

专题命中 其他推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

Journal ref 2025.naacl-long.557

Table-r1: Self-supervised and Reinforcement Learning for Program-based Table Reasoning in Small Language Models

Rihui Jin, Zheyu Xin, Xing Xie, Zuoyi Li, Guilin Qi, Yongrui Chen, Xinbang Dai, Tongtong Wu, Gholamreza Haffari

机构 * Southeast University（东南大学） ； Monash University（墨尔本大学） 纠错

专题命中 其他推理 ：reasoning(title,abstract)；分类 cs.CL、cs.LG

Just Enough Thinking: Efficient Reasoning with Adaptive Length Penalties Reinforcement Learning

Violet Xiang, Chase Blagden, Rafael Rafailov, Nathan Lile, Sang Truong, Chelsea Finn, Nick Haber

机构 * Stanford University（斯坦福大学） ； SynthLabs 纠错

专题命中 其他推理 ：reasoning(title,abstract)；分类 cs.AI、cs.LG

Beyond Completion: A Foundation Model for General Knowledge Graph Reasoning

Yin Hua, Zhiqiang Liu, Mingyang Chen, Zheng Fang, Chi Man Wong, Lingxiao Li, Chi Man Vong, Huajun Chen, Wen Zhang

机构 * Zhejiang University（浙江大学） ； Shopee Pte.Ltd.（Shopee公司） ； University of Macau（澳门大学） ； Zhejiang Key Laboratory of Big Data Intelligent Computing（浙江大学大数据智能计算重点实验室） 纠错

专题命中 其他推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

Comments ACL 2025 Findings

Optimizing Case-Based Reasoning System for Functional Test Script Generation with Large Language Models

Siyuan Guo, Huiwu Liu, Xiaolong Chen, Yuming Xie, Liang Zhang, Tao Han, Hechang Chen, Yi Chang, Jun Wang

机构 * School of Artificial Intelligence, International Center of Future Science（人工智能学院，未来科学国际中心） ； Huawei Technologies Ltd.（华为技术有限公司） ； School of Artificial Intelligence（人工智能学院） ； AI Centre University College London（伦敦大学学院人工智能中心） 纠错

专题命中 其他推理 ：reasoning(title,abstract)；分类 cs.CL、cs.LG

Comments Accepted by KDD 2025 (ADS Track)

Deciphering Trajectory-Aided LLM Reasoning: An Optimization Perspective

Junnan Liu, Hongwei Liu, Linchen Xiao, Shudong Liu, Taolin Zhang, Zihan Ma, Songyang Zhang, Kai Chen

机构 * Shanghai AI Laboratory（上海人工智能实验室） 纠错

专题命中 其他推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models

Haoyuan Sun, Jiaqi Wu, Bo Xia, Yifu Luo, Yifei Zhao, Kai Qin, Xufei Lv, Tiantian Zhang, Yongzhe Chang, Xueqian Wang

机构 * Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院，清华大学） 纠错

专题命中 其他推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

Self-Training Large Language Models with Confident Reasoning

Hyosoon Jang, Yunhui Jang, Sungjae Lee, Jungseul Ok, Sungsoo Ahn

机构 * POSTECH（POSTECH大学） ； KAIST（韩国科学技术院） 纠错

专题命中 其他推理 ：reasoning(title,abstract)；分类 cs.CL、cs.LG

Social preferences with unstable interactive reasoning: Large language models in economic trust games

Ou Jiamin, Eikmans Emile, Buskens Vincent, Pankowska Paulina, Shan Yuli

专题命中 其他推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

Comments 19 pages, 2 figures, 2 tables

When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning

Xiaoyun Zhang, Jingqing Ruan, Xing Ma, Yawen Zhu, Haodong Zhao, Hao Li, Jiansong Chen, Ke Zeng, Xunliang Cai

机构 * Meituan（美团） 纠错

专题命中 其他推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

Structural Reasoning Improves Molecular Understanding of LLM

Yunhui Jang, Jaehyung Kim, Sungsoo Ahn

专题命中 其他推理 ：reasoning(title,abstract)；分类 cs.AI、cs.LG

An Analysis for Reasoning Bias of Language Models with Small Initialization

Junjie Yao, Zhongwang Zhang, Zhi-Qin John Xu

专题命中 其他推理 ：reasoning(title,abstract)；分类 cs.CL、cs.LG

Comments 31 pages, 16 figures

Debating for Better Reasoning: An Unsupervised Multimodal Approach

Ashutosh Adhikari, Mirella Lapata

专题命中 其他推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

FlashThink: An Early Exit Method For Efficient Reasoning

Guochao Jiang, Guofeng Quan, Zepeng Ding, Ziqin Luo, Dixuan Wang, Zheng Hu

专题命中 其他推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoning

Shaokun Zhang, Yi Dong, Jieyu Zhang, Jan Kautz, Bryan Catanzaro, Andrew Tao, Qingyun Wu, Zhiding Yu, Guilin Liu

专题命中 其他推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

Comments 17 pages, 6 tables, 12 figures. - update new results - add more details

Enigme: Generative Text Puzzles for Evaluating Reasoning in Language Models

John Hawkins

机构 * Centre for Artificial Intelligence and Innovation（人工智能与创新中心） ； Pingla Institute（Pingla研究院） 纠错

专题命中 其他推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

Comments To be published in the proceedings of The 2025 11th International Conference on Engineering, Applied Sciences, and Technology (ICEAST)

Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs

Jinyan Su, Jennifer Healey, Preslav Nakov, Claire Cardie

机构 * Cornell University（康奈尔大学） ； Adobe Research（Adobe研究） ； MBZUAI 纠错

专题命中 其他推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

Retrieval, Reasoning, Re-ranking: A Context-Enriched Framework for Knowledge Graph Completion

Muzhi Li, Cehao Yang, Chengjin Xu, Xuhui Jiang, Yiyan Qi, Jian Guo, Ho-fung Leung, Irwin King

机构 * IDEA Research, International Digital Economy Academy（IDEA研究室，国际数字经济学院） ； Department of Computer Science & Engineering, The Chinese University of Hong Kong（计算机科学与工程系，香港中文大学） ； Artificial Intelligence Thrust, Hong Kong University of Science and Technology (Guangzhou)（人工智能方向，香港科技大学（广州）） 纠错

专题命中 其他推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

Comments Accepted by NAACL2025 main

Adapting Language-Specific LLMs to a Reasoning Model in One Day via Model Merging -- An Open Recipe

Kunat Pipatanakul, Pittawat Taveekitworachai, Potsawee Manakul, Kasima Tharnpipitchai

专题命中 其他推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

Comments 9 pages

Weak-to-Strong Generalization beyond Accuracy: a Pilot Study in Safety, Toxicity, and Legal Reasoning

Ruimeng Ye, Yang Xiao, Bo Hui

专题命中 其他推理 ：reasoning(title,abstract)；分类 cs.CL、cs.LG

Cognitive Activation and Chaotic Dynamics in Large Language Models: A Quasi-Lyapunov Analysis of Reasoning Mechanisms

Xiaojian Li, Yongkang Leng, Ruiqing Ding, Hangjie Mo, Shanlin Yang

专题命中 其他推理 ：reasoning(title,abstract)；分类 cs.AI、cs.LG