语言大模型 / LLM

VIPER: Visual Perception and Explainable Reasoning for Sequential Decision-Making

Mohamed Salim Aissi, Clemence Grislain, Mohamed Chetouani, Olivier Sigaud, Laure Soulier, Nicolas Thome

机构 * Sorbonne Université, CNRS, ISIR（索邦大学、国家科学研究中心、ISIR） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG

A Fragile Number Sense: Probing the Elemental Limits of Numerical Reasoning in LLMs

Roussel Rahman, Aashwin Ananda Mishra

机构 * Stanford University（斯坦福大学） ； SLAC National Accelerator Laboratory（SLAC国家加速器实验室） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG

TECP: Token-Entropy Conformal Prediction for LLMs

Beining Xu, Yongming Lu

机构 * Department of School of Engineering, Shenzhen MSU-BIT University, Shenzhen, China, 518000（深圳MSU-BIT大学工程学院部门） ； MSU-BIT-SMBU Joint Research Center of Applied Mathematics, Shenzhen MSU-BIT University, Shenzhen, China, 518000（应用数学联合研究中心） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

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 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments 18 pages

MoNaCo: More Natural and Complex Questions for Reasoning Across Dozens of Documents

Tomer Wolfson, Harsh Trivedi, Mor Geva, Yoav Goldberg, Dan Roth, Tushar Khot, Ashish Sabharwal, Reut Tsarfaty

机构 * University of Pennsylvania（宾夕法尼亚大学） ； Allen Institute for AI（人工智能研究院） ； Tel Aviv University（特拉维夫大学） ； Bar-Ilan University（巴伊兰大学） ； Oracle AI（Oracle人工智能） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted for publication in Transactions of the Association for Computational Linguistics (TACL), 2025. Authors pre-print

JARVIS: A Neuro-Symbolic Commonsense Reasoning Framework for Conversational Embodied Agents

Kaizhi Zheng, Kaiwen Zhou, Jing Gu, Yue Fan, Jialu Wang, Zonglin Di, Xuehai He, Xin Eric Wang

机构 * University of California（加州大学） 纠错

专题命中 推理与问题求解 ：large language model(abstract)；language model(abstract)；prompting(abstract)；分类 cs.CL、cs.AI

Comments 19th International Conference on Neurosymbolic Learning and Reasoning

Baichuan-M2: Scaling Medical Capability with Large Verifier System

M2 Team, Chengfeng Dou, Chong Liu, Fan Yang, Fei Li, Jiyuan Jia, Mingyang Chen, Qiang Ju, Shuai Wang, Shunya Dang, Tianpeng Li, Xiangrong Zeng, Yijie Zhou, Chenzheng Zhu, Da Pan, Fei Deng, Guangwei Ai, Guosheng Dong, Hongda Zhang, Jinyang Tai, Jixiang Hong, Kai Lu, Linzhuang Sun, Peidong Guo, Qian Ma, Rihui Xin, Shihui Yang, Shusen Zhang, Yichuan Mo, Zheng Liang, Zhishou Zhang, Hengfu Cui, Zuyi Zhu, Xiaochuan Wang

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG

Comments Baichuan-M2 Technical Report

Rethinking the Chain-of-Thought: The Roles of In-Context Learning and Pre-trained Priors

Hao Yang, Zhiyu Yang, Yunjie Zhang, Shanyi Zhu, Lin Yang

机构 * School of Intelligence Science and Technology, National Key Laboratory for Novel Software Technology, Nanjing University（智能科学与技术学院，新型软件技术国家重点实验室，南京大学） ； School of Computing and Information Systems, Singapore Management University（计算与信息系统学院，新加坡管理大学） ； Central South University（中南大学） ； School of Global Education and Development, International Chinese Language Education, University of Chinese Academy of Social Sciences（全球教育与发展学院，国际中文教育，中国社会科学院） 纠错

专题命中 推理与问题求解 ：large language model(abstract)；language model(abstract)；prompting(abstract)；分类 cs.CL、cs.AI

General Table Question Answering via Answer-Formula Joint Generation

Zhongyuan Wang, Richong Zhang, Zhijie Nie, Hangyu Mao

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments work in progress

Semantic Integrity Constraints: Declarative Guardrails for AI-Augmented Data Processing Systems

Alexander W. Lee, Justin Chan, Michael Fu, Nicolas Kim, Akshay Mehta, Deepti Raghavan, Ugur Cetintemel

机构 * Brown University（布朗大学） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Journal ref PVLDB, 18(11): 4073 - 4080, 2025

Multilingual != Multicultural: Evaluating Gaps Between Multilingual Capabilities and Cultural Alignment in LLMs

Jonathan Rystrøm, Hannah Rose Kirk, Scott Hale

机构 * Oxford Internet Institute（牛津互联网研究所） ； University of Oxford（牛津大学） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted at OMMM@RANLP2025

Rethinking Reasoning in LLMs: Neuro-Symbolic Local RetoMaton Beyond ICL and CoT

Rushitha Santhoshi Mamidala, Anshuman Chhabra, Ankur Mali

专题命中 推理与问题求解 ：large language model(abstract)；language model(abstract)；prompting(abstract)；分类 cs.CL、cs.AI

Understanding Tool-Integrated Reasoning

Heng Lin, Zhongwen Xu

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG

XFinBench: Benchmarking LLMs in Complex Financial Problem Solving and Reasoning

Zhihan Zhang, Yixin Cao, Lizi Liao

机构 * School of Computing and Information Systems, Singapore Management University（计算与信息系统学院，新加坡管理大学） ； Institute of Trustworthy Embodied AI, Fudan University（可信具身人工智能研究院，复旦大学） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.LG

Dissecting Tool-Integrated Reasoning: An Empirical Study and Analysis

Yufeng Zhao, Junnan Liu, Hongwei Liu, Dongsheng Zhu, Yuan Shen, Songyang Zhang, Kai Chen

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments Preprint, working in progress

Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning

Yekun Zhu, Guang Chen, Chengjun Mao

专题命中 推理与问题求解 ：large language model(abstract)；language model(abstract)；preference optimization(abstract)；分类 cs.AI、cs.LG

Diagnosing Memorization in Chain-of-Thought Reasoning, One Token at a Time

Huihan Li, You Chen, Siyuan Wang, Yixin He, Ninareh Mehrabi, Rahul Gupta, Xiang Ren

机构 * University of Southern California（南加州大学） ； University of California, San Diego（加州大学圣地亚哥分校） ； Meta ； Amazon AGI（亚马逊人工智能研究院） 纠错

专题命中 推理与问题求解 ：large language model(abstract)；language model(abstract)；pretraining(abstract)；分类 cs.CL、cs.AI

Pragmatic Inference Chain (PIC) Improving LLMs' Reasoning of Authentic Implicit Toxic Language

Xi Chen, Shuo Wang

机构 * Nanyang Technological University（南洋理工大学） ； University of Macau（澳门大学） 纠错

专题命中 推理与问题求解 ：large language model(abstract)；language model(abstract)；prompting(abstract)；分类 cs.CL、cs.AI

Comments 14 pages, 4 figures, 2 tables

CRISPR-GPT for Agentic Automation of Gene-editing Experiments

Yuanhao Qu, Kaixuan Huang, Ming Yin, Kanghong Zhan, Dyllan Liu, Di Yin, Henry C. Cousins, William A. Johnson, Xiaotong Wang, Mihir Shah, Russ B. Altman, Denny Zhou, Mengdi Wang, Le Cong

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted to Nature Biomedical Engineering

Advancing AI-Scientist Understanding: Multi-Agent LLMs with Interpretable Physics Reasoning

Yinggan Xu, Hana Kimlee, Yijia Xiao, Di Luo

机构 * NSF Center for Quantum Network（NSF量子网络中心） ； University of California, Los Angeles（加州大学洛杉矶分校） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments ICML 2025 Workshop on MAS

LARC: Towards Human-level Constrained Retrosynthesis Planning through an Agentic Framework

Frazier N. Baker, Daniel Adu-Ampratwum, Reza Averly, Botao Yu, Huan Sun, Xia Ning

机构 * Department of Computer Science and Engineering, 2 Division of Medicinal Chemistry & Pharmacognosy, 3 Department of Biomedical Informatics, 4 Translational Data Analytics Institute（1 计算机科学与工程系，2 药物化学与药理学系，3 生物医学信息学系，4 转化数据分析研究所） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments 24 pages, 5 figures

Less is More: Learning Graph Tasks with Just LLMs

Sola Shirai, Kavitha Srinivas, Julian Dolby, Michael Katz, Horst Samulowitz, Shirin Sohrabi

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG

Are Your LLMs Capable of Stable Reasoning?

Junnan Liu, Hongwei Liu, Linchen Xiao, Ziyi Wang, Kuikun Liu, Songyang Gao, Wenwei Zhang, Songyang Zhang, Kai Chen

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments ACL 2025 Camera, Benchmark: https://huggingface.co/datasets/opencompass/LiveMathBench, Code: https://github.com/open-compass/GPassK

Polymath: A Self-Optimizing Agent with Dynamic Hierarchical Workflow

Chia-Tung Ho, Jing Gong, Xufeng Yao, Yunsheng Bai, Abhishek B Akkur, Haoxing Ren

专题命中 推理与问题求解 ：large language model(abstract)；language model(abstract)；foundation model(abstract)；分类 cs.AI、cs.LG

Comments 18 pages, 12 figures, under review for AAAI2026

CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward

Shudong Liu, Hongwei Liu, Junnan Liu, Linchen Xiao, Songyang Gao, Chengqi Lyu, Yuzhe Gu, Wenwei Zhang, Derek F. Wong, Songyang Zhang, Kai Chen

机构 * Shanghai AI Laboratory（上海人工智能实验室） ； NLP 2 CT Lab, University of Macau（澳门大学自然语言处理与计算机视觉实验室） ； University of Macau（澳门大学） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments Technical Report; 31 Pages

Bridging LLMs and Symbolic Reasoning in Educational QA Systems: Insights from the XAI Challenge at IJCNN 2025

Long S. T. Nguyen, Khang H. N. Vo, Thu H. A. Nguyen, Tuan C. Bui, Duc Q. Nguyen, Thanh-Tung Tran, Anh D. Nguyen, Minh L. Nguyen, Fabien Baldacci, Thang H. Bui, Emanuel Di Nardo, Angelo Ciaramella, Son H. Le, Ihsan Ullah, Lorenzo Di Rocco, Tho T. Quan

机构 * URA Research Group, Ho Chi Minh City University of Technology (HCMUT), Vietnam ； Ho Chi Minh City International University (HCMIU), Vietnam ； University of South-Eastern Norway, Norway ； Japan Advanced Institute of Science ； Univ. Bordeaux, CNRS, Bordeaux INP, LaBRI, UMR 5800, F-33400 Talence, France ； University of Naples Parthenope, Italy ； VNU Information Technology Institute, Vietnam National University, Vietnam ； Visual Intelligence Lab, School of Computer Science \& Insight Center for Data Analyitcs, University of Galway, Ireland ； Sapienza University of Rome, Italy 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments The XAI Challenge @ TRNS-AI Workshop, IJCNN 2025: Explainable AI for Educational Question Answering. Website: https://sites.google.com/view/trns-ai/challenge/

Emergent Response Planning in LLMs

Zhichen Dong, Zhanhui Zhou, Zhixuan Liu, Chao Yang, Chaochao Lu

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

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.LG

Comments Published at ICML 2025. Code available at: https://github.com/niconi19/Emergent-Response-Planning-in-LLMs

Journal ref Proceedings of the 42nd International Conference on Machine Learning (ICML 2025)

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding

Xi Chen, Aske Plaat, Niki van Stein

专题命中 推理与问题求解 ：large language model(abstract)；language model(abstract)；prompting(abstract)；分类 cs.CL、cs.AI

Where to show Demos in Your Prompt: A Positional Bias of In-Context Learning

Kwesi Cobbina, Tianyi Zhou

机构 * University of Maryland, College Park（马里兰大学 College Park分校） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Solving Formal Math Problems by Decomposition and Iterative Reflection

Yichi Zhou, Jianqiu Zhao, Yongxin Zhang, Bohan Wang, Siran Wang, Luoxin Chen, Jiahui Wang, Haowei Chen, Allan Jie, Xinbo Zhang, Haocheng Wang, Luong Trung, Rong Ye, Phan Nhat Hoang, Huishuai Zhang, Peng Sun, Hang Li

机构 * University of science and technology of China（科学技术大学） ； Peking University（北京大学） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG