大模型推理能力

Entropy-Regularized Process Reward Model

Hanning Zhang, Pengcheng Wang, Shizhe Diao, Yong Lin, Rui Pan, Hanze Dong, Dylan Zhang, Pavlo Molchanov, Tong Zhang

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； University of Toronto（多伦多大学） ； NVIDIA（英伟达） ； Princeton University（普林斯顿大学） ； Salesforce Research（Salesforce研究） 纠错

专题命中 测试时计算 ：reasoning(abstract)；分类 cs.CL、cs.LG

Comments Upate TMLR version

ConCISE: Confidence-guided Compression in Step-by-step Efficient Reasoning

Ziqing Qiao, Yongheng Deng, Jiali Zeng, Dong Wang, Lai Wei, Guanbo Wang, Fandong Meng, Jie Zhou, Ju Ren, Yaoxue Zhang

机构 * Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系） ； Pattern Recognition Center, WeChat AI, Tencent Inc.（腾讯人工智能研究院） 纠错

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

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

Language Mixing in Reasoning Language Models: Patterns, Impact, and Internal Causes

Mingyang Wang, Lukas Lange, Heike Adel, Yunpu Ma, Jannik Strötgen, Hinrich Schütze

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

Temporal Reasoning with Large Language Models Augmented by Evolving Knowledge Graphs

Junhong Lin, Song Wang, Xiaojie Guo, Julian Shun, Yada Zhu

机构 * MIT CSAIL（麻省理工学院计算机科学与人工智能实验室） ； University of Virginia（弗吉尼亚大学） ； IBM Research（IBM研究院） 纠错

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

Defining and Monitoring Complex Robot Activities via LLMs and Symbolic Reasoning

Francesco Argenziano, Elena Umili, Francesco Leotta, Daniele Nardi

机构 * Department of Computer, Automation and Management Engineering（计算机、自动化与管理工程系） 纠错

专题命中 复杂问题求解 ：reasoning(title)；planning(abstract)

Think, Verbalize, then Speak: Bridging Complex Thoughts and Comprehensible Speech

Sang Hoon Woo, Sehun Lee, Kang-wook Kim, Gunhee Kim

机构 * Seoul National University（首尔国立大学） 纠错

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

Comments EMNLP 2025 Main. Project page: https://yhytoto12.github.io/TVS-ReVerT

Beyond Spurious Signals: Debiasing Multimodal Large Language Models via Counterfactual Inference and Adaptive Expert Routing

Zichen Wu, Hsiu-Yuan Huang, Yunfang Wu

机构 * School of Computer Science, Peking University（北京大学计算机科学学院） ； MOE Key Laboratory of Computational Linguistics, Peking University（北京大学教育部计算语言学重点实验室） ； National Key Laboratory for Multimedia Information Processing, Peking University（北京大学国家多媒体信息处理重点实验室） 纠错

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

Comments Accepted by EMNLP 2025 Findings

Adaptive Self-improvement LLM Agentic System for ML Library Development

Genghan Zhang, Weixin Liang, Olivia Hsu, Kunle Olukotun

机构 * Department of Computer Science, Stanford University, USA（计算机科学系，斯坦福大学） 纠错

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

EmoQ: Speech Emotion Recognition via Speech-Aware Q-Former and Large Language Model

Yiqing Yang, Man-Wai Mak

机构 * Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University（电子与电气工程系，香港理工大学） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)

Comments 5 pages, 2 figures

SAIL-VL2 Technical Report

Weijie Yin, Yongjie Ye, Fangxun Shu, Yue Liao, Zijian Kang, Hongyuan Dong, Haiyang Yu, Dingkang Yang, Jiacong Wang, Han Wang, Wenzhuo Liu, Xiao Liang, Shuicheng Yan, Chao Feng

机构 * Douyin SAIL Team（字节跳动 SAIL 团队） ； LV-NUS Lab（NUS 实验室） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)

Comments Technical Report

RaCT: Ranking-aware Chain-of-Thought Optimization for LLMs

Haowei Liu, Xuyang Wu, Guohao Sun, Zhiqiang Tao, Yi Fang

专题命中 推理评测 ：chain-of-thought(title,abstract)；reasoning(abstract)；CoT(abstract)

Cache-of-Thought: Master-Apprentice Framework for Cost-Effective Vision Language Model Reasoning

Mingyuan Wu, Jize Jiang, Haozhen Zheng, Meitang Li, Zhaoheng Li, Beitong Tian, Bo Chen, Yongjoo Park, Minjia Zhang, Chengxiang Zhai, Klara Nahrstedt

机构 * University of Illinois Urbana Champaign（伊利诺伊大学厄巴纳-香槟分校） ； University of Michigan Ann Arbor（密歇根大学安娜堡分校） 纠错

专题命中 推理评测 ：reasoning(title,abstract)；CoT(abstract)；分类 cs.LG

Comments EMNLP 2025 Main Conference. Mingyuan, Jize, and Haozhen contributed equally, while Minjia, Chengxiang, and Klara advised equally

GUI-ReWalk: Massive Data Generation for GUI Agent via Stochastic Exploration and Intent-Aware Reasoning

Musen Lin, Minghao Liu, Taoran Lu, Lichen Yuan, Yiwei Liu, Haonan Xu, Yu Miao, Yuhao Chao, Zhaojian Li

机构 * ByteDance（字节跳动） ； UCAS（北京大学） 纠错

专题命中 推理评测 ：reasoning(title,abstract)；分类 cs.LG

LLM Agents at the Roundtable: A Multi-Perspective and Dialectical Reasoning Framework for Essay Scoring

Jinhee Jang, Ayoung Moon, Minkyoung Jung, YoungBin Kim, Seung Jin Lee

机构 * NC AI ； Chung-Ang University 纠错

专题命中 推理评测 ：reasoning(title,abstract)；分类 cs.CL

HydraRAG: Structured Cross-Source Enhanced Large Language Model Reasoning

Xingyu Tan, Xiaoyang Wang, Qing Liu, Xiwei Xu, Xin Yuan, Liming Zhu, Wenjie Zhang

机构 * University of New South Wales（新南威尔士大学） ； Data61, CSIRO（Data61，CSIRO） 纠错

专题命中 推理评测 ：reasoning(title,abstract)；分类 cs.CL

Comments Accepted by EMNLP2025 (Main Conference)

Watson: A Cognitive Observability Framework for the Reasoning of LLM-Powered Agents

Benjamin Rombaut, Sogol Masoumzadeh, Kirill Vasilevski, Dayi Lin, Ahmed E. Hassan

机构 * Centre for Software Excellence, Huawei Canada（华为加拿大卓越软件中心） ； Queen's University, Kingston, Canada（皇后大学） 纠错

专题命中 推理评测 ：reasoning(title,abstract)；分类 cs.AI

Diagnostics of cognitive failures in multi-agent expert systems using dynamic evaluation protocols and subsequent mutation of the processing context

Andrejs Sorstkins, Josh Bailey, Dr Alistair Baron

机构 * School of Computing and Communications（计算与通讯学院） ； Lancaster University（兰卡斯特大学） 纠错

专题命中 推理评测 ：reasoning(abstract)；planning(abstract)；分类 cs.AI

Comments Dissertation and research project created in collaboration with JobFair LTD

EHR-MCP: Real-world Evaluation of Clinical Information Retrieval by Large Language Models via Model Context Protocol

Kanato Masayoshi, Masahiro Hashimoto, Ryoichi Yokoyama, Naoki Toda, Yoshifumi Uwamino, Shogo Fukuda, Ho Namkoong, Masahiro Jinzaki

机构 * Department of Radiology, Keio University Hospital, Tokyo, Japan（Keio大学医院放射科） ； Division of Infectious Diseases and Infection Control, Keio University Hospital, Tokyo, Japan（Keio大学医院感染病学与感染控制科） 纠错

专题命中 推理评测 ：reasoning(abstract)；分类 cs.CL、cs.AI

Empathy-R1: A Chain-of-Empathy and Reinforcement Learning Framework for Long-Form Mental Health Support

Xianrong Yao, Dong She, Chenxu Zhang, Yimeng Zhang, Yueru Sun, Noman Ahmed, Yang Gao, Zhanpeng Jin

机构 * School of Future Technology（未来技术学院） 纠错

专题命中 推理评测 ：reasoning(abstract)；分类 cs.CL、cs.AI

DischargeSim: A Simulation Benchmark for Educational Doctor-Patient Communication at Discharge

Zonghai Yao, Michael Sun, Won Seok Jang, Sunjae Kwon, Soie Kwon, Hong Yu

专题命中 推理评测 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments Equal contribution for the first two authors. To appear in the proceedings of the Main Conference on Empirical Methods in Natural Language Processing (EMNLP) 2025

A Layered Multi-Expert Framework for Long-Context Mental Health Assessments

Jinwen Tang, Qiming Guo, Wenbo Sun, Yi Shang

机构 * Texas A\&M University-Corpus Christi（德克萨斯A&M大学-科珀斯克里斯蒂） ； Delft University of Technology（代尔夫特理工大学） 纠错

专题命中 推理评测 ：reasoning(abstract)；分类 cs.CL、cs.AI

Journal ref Proc. 2025 IEEE Conference on Artificial Intelligence (CAI), Santa Clara, CA, USA, 2025, pp. 435-440

It Depends: Resolving Referential Ambiguity in Minimal Contexts with Commonsense Knowledge

Lukas Ellinger, Georg Groh

机构 * School for Computation, Information and Technology（计算、信息与技术学院） ； Technical University of Munich（慕尼黑技术大学） 纠错

专题命中 推理评测 ：reasoning(abstract)；分类 cs.CL

Comments Accepted by UncertaiNLP workshop @ EMNLP 2025

Pruning the Paradox: How CLIP's Most Informative Heads Enhance Performance While Amplifying Bias

Avinash Madasu, Vasudev Lal, Phillip Howard

机构 * Intel Labs（英特尔实验室） ； Oracle（Oracle公司） ； Thoughtworks（Thoughtworks公司） 纠错

专题命中 推理评测 ：reasoning(abstract)；分类 cs.AI

AcT2I: Evaluating and Improving Action Depiction in Text-to-Image Models

Vatsal Malaviya, Agneet Chatterjee, Maitreya Patel, Yezhou Yang, Chitta Baral

机构 * Arizona State University（亚利桑那州立大学） 纠错

专题命中 推理评测 ：reasoning(abstract)

Comments Project Page : https://vatsal-malaviya.github.io/AcT2I/

Fleming-R1: Toward Expert-Level Medical Reasoning via Reinforcement Learning

Chi Liu, Derek Li, Yan Shu, Robin Chen, Derek Duan, Teng Fang, Bryan Dai

机构 * Ubiquant 纠错

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

Stress Testing Deliberative Alignment for Anti-Scheming Training

Bronson Schoen, Evgenia Nitishinskaya, Mikita Balesni, Axel Højmark, Felix Hofstätter, Jérémy Scheurer, Alexander Meinke, Jason Wolfe, Teun van der Weij, Alex Lloyd, Nicholas Goldowsky-Dill, Angela Fan, Andrei Matveiakin, Rusheb Shah, Marcus Williams, Amelia Glaese, Boaz Barak, Wojciech Zaremba, Marius Hobbhahn

专题命中 其他推理 ：reasoning(abstract)；chain-of-thought(abstract)；CoT(abstract)；分类 cs.AI

LongCat-Flash Technical Report

Meituan LongCat Team, Bayan, Bei Li, Bingye Lei, Bo Wang, Bolin Rong, Chao Wang, Chao Zhang, Chen Gao, Chen Zhang, Cheng Sun, Chengcheng Han, Chenguang Xi, Chi Zhang, Chong Peng, Chuan Qin, Chuyu Zhang, Cong Chen, Congkui Wang, Dan Ma, Daoru Pan, Defei Bu, Dengchang Zhao, Deyang Kong, Dishan Liu, Feiye Huo, Fengcun Li, Fubao Zhang, Gan Dong, Gang Liu, Gang Xu, Ge Li, Guoqiang Tan, Guoyuan Lin, Haihang Jing, Haomin Fu, Haonan Yan, Haoxing Wen, Haozhe Zhao, Hong Liu, Hongmei Shi, Hongyan Hao, Hongyin Tang, Huantian Lv, Hui Su, Jiacheng Li, Jiahao Liu, Jiahuan Li, Jiajun Yang, Jiaming Wang, Jian Yang, Jianchao Tan, Jiaqi Sun, Jiaqi Zhang, Jiawei Fu, Jiawei Yang, Jiaxi Hu, Jiayu Qin, Jingang Wang, Jiyuan He, Jun Kuang, Junhui Mei, Kai Liang, Ke He, Kefeng Zhang, Keheng Wang, Keqing He, Liang Gao, Liang Shi, Lianhui Ma, Lin Qiu, Lingbin Kong, Lingtong Si, Linkun Lyu, Linsen Guo, Liqi Yang, Lizhi Yan, Mai Xia, Man Gao, Manyuan Zhang, Meng Zhou, Mengxia Shen, Mingxiang Tuo, Mingyang Zhu, Peiguang Li, Peng Pei, Peng Zhao, Pengcheng Jia, Pingwei Sun, Qi Gu, Qianyun Li, Qingyuan Li, Qiong Huang, Qiyuan Duan, Ran Meng, Rongxiang Weng, Ruichen Shao, Rumei Li, Shizhe Wu, Shuai Liang, Shuo Wang, Suogui Dang, Tao Fang, Tao Li, Tefeng Chen, Tianhao Bai, Tianhao Zhou, Tingwen Xie, Wei He, Wei Huang, Wei Liu, Wei Shi, Wei Wang, Wei Wu, Weikang Zhao, Wen Zan, Wenjie Shi, Xi Nan, Xi Su, Xiang Li, Xiang Mei, Xiangyang Ji, Xiangyu Xi, Xiangzhou Huang, Xianpeng Li, Xiao Fu, Xiao Liu, Xiao Wei, Xiaodong Cai, Xiaolong Chen, Xiaoqing Liu, Xiaotong Li, Xiaowei Shi, Xiaoyu Li, Xili Wang, Xin Chen, Xing Hu, Xingyu Miao, Xinyan He, Xuemiao Zhang, Xueyuan Hao, Xuezhi Cao, Xunliang Cai, Xurui Yang, Yan Feng, Yang Bai, Yang Chen, Yang Yang, Yaqi Huo, Yerui Sun, Yifan Lu, Yifan Zhang, Yipeng Zang, Yitao Zhai, Yiyang Li, Yongjing Yin, Yongkang Lv, Yongwei Zhou, Yu Yang, Yuchen Xie, Yueqing Sun, Yuewen Zheng, Yuhuai Wei, Yulei Qian, Yunfan Liang, Yunfang Tai, Yunke Zhao, Zeyang Yu, Zhao Zhang, Zhaohua Yang, Zhenchao Zhang, Zhikang Xia, Zhiye Zou, Zhizhao Zeng, Zhongda Su, Zhuofan Chen, Zijian Zhang, Ziwen Wang, Zixu Jiang, Zizhe Zhao, Zongyu Wang, Zunhai Su

机构 * Meituan LongCat Team（美团LongCat团队） 纠错

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

Reward Hacking Mitigation using Verifiable Composite Rewards

Mirza Farhan Bin Tarek, Rahmatollah Beheshti

机构 * University of Delaware（特拉华大学） 纠错

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

Comments Accepted at the 16th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM-BCB 2025)

SEMMA: A Semantic Aware Knowledge Graph Foundation Model

Arvindh Arun, Sumit Kumar, Mojtaba Nayyeri, Bo Xiong, Ponnurangam Kumaraguru, Antonio Vergari, Steffen Staab

机构 * Institute for AI, University of Stuttgart（斯图加特大学人工智能研究所） ； IIIT Hyderabad（海得拉巴国家理工学院） ； Stanford University（斯坦福大学） ； University of Edinburgh（爱丁堡大学） ； University of Southampton（南安普顿大学） 纠错

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

Comments EMNLP 2025