语言大模型 / LLM

Information Seeking for Robust Decision Making under Partial Observability

Djengo Cyun-Jyun Fang, Tsung-Wei Ke

机构 * National Taiwan University（台湾大学） 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 The project page is available at https://infoseekerllm.github.io

TUMIX: Multi-Agent Test-Time Scaling with Tool-Use Mixture

Yongchao Chen, Jiefeng Chen, Rui Meng, Ji Yin, Na Li, Chuchu Fan, Chi Wang, Tomas Pfister, Jinsung Yoon

机构 * MIT Harvard（麻省理工学院哈佛大学） ； Google Cloud AI Research（谷歌云人工智能研究） ； Google DeepMind（谷歌DeepMind） ； MIT（麻省理工学院） 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 27 pages, 13 figures

Defend LLMs Through Self-Consciousness

Boshi Huang, Fabio Nonato de Paula

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 company requests to withdraw

Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs

Xumeng Wen, Zihan Liu, Shun Zheng, Shengyu Ye, Zhirong Wu, Yang Wang, Zhijian Xu, Xiao Liang, Junjie Li, Ziming Miao, Jiang Bian, Mao Yang

机构 * Microsoft Research Asia（微软亚洲研究院） ； Peking University（北京大学） ； The Chinese University of Hong Kong（香港中文大学） ； 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 Update with more experiments

FANS -- Formal Answer Selection for Natural Language Math Reasoning Using Lean4

Jiarui Yao, Ruida Wang, Tong Zhang

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 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

Reasoning over User Preferences: Knowledge Graph-Augmented LLMs for Explainable Conversational Recommendations

Zhangchi Qiu, Linhao Luo, Shirui Pan, Alan Wee-Chung Liew

机构 * School of ICT, Griffith University（格里菲斯大学信息与通信技术学院） ； Department of Data Science and AI, Monash University（莫纳什大学数据科学与人工智能系） 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 by ICDM 2025

OntoAligner Meets Knowledge Graph Embedding Aligners

Hamed Babaei Giglou, Jennifer D'Souza, Sören Auer, Mahsa Sanaei

机构 * TIB -- Leibniz Information Centre for Science and Technology（莱比锡信息科学与技术研究中心） ； University of Tabriz（塔布里兹大学） 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

Comments 10 pages of main content, 3 page references, 3 figures. Accepted to Ontology Matching Workshop at ISWC

Aligning Multilingual Reasoning with Verifiable Semantics from a High-Resource Expert Model

Fahim Faisal, Kaiqiang Song, Song Wang, Simin Ma, Shujian Liu, Haoyun Deng, Sathish Reddy Indurthi

机构 * Zoom 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

UML-CoT: Structured Reasoning and Planning with Unified Modeling Language for Robotic Room Cleaning

Hongyu Chen, Guangrun Wang

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

Video models are zero-shot learners and reasoners

Thaddäus Wiedemer, Yuxuan Li, Paul Vicol, Shixiang Shane Gu, Nick Matarese, Kevin Swersky, Been Kim, Priyank Jaini, Robert Geirhos

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 Project page: https://video-zero-shot.github.io/

Cogito, Ergo Ludo: An Agent that Learns to Play by Reasoning and Planning

Sai Wang, Yu Wu, Zhongwen Xu

机构 * Tencent（腾讯） ； Wuhan University（武汉大学） 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

DEL-ToM: Inference-Time Scaling for Theory-of-Mind Reasoning via Dynamic Epistemic Logic

Yuheng Wu, Jianwen Xie, Denghui Zhang, Zhaozhuo Xu

机构 * Stanford University（斯坦福大学） ； Lambda, Inc.（Lambda公司） ； Stevens Institute of Technology（史蒂文斯理工学院） 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

Rethinking the Embodied Gap in Vision-and-Language Navigation: A Holistic Study of Physical and Visual Disparities

Liuyi Wang, Xinyuan Xia, Hui Zhao, Hanqing Wang, Tai Wang, Yilun Chen, Chengju Liu, Qijun Chen, Jiangmiao Pang

机构 * Tongji University（同济大学） ； Shanghai AI Laboratory（上海人工智能实验室） ； Shanghai Jiao Tong University（上海交通大学） ； State Key Laboratory of Autonomous Intelligent Unmanned Systems（自主智能无人系统国家重点实验室） 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.AI

Comments Accepted by ICCV 2025

How LLMs Fail to Support Fact-Checking

Adiba Mahbub Proma, Neeley Pate, James Druckman, Gourab Ghoshal, Hangfeng He, Ehsan Hoque

机构 * University of Rochester（罗切斯特大学） 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 Adiba and Neeley contributed equally

ZERA: Zero-init Instruction Evolving Refinement Agent -- From Zero Instructions to Structured Prompts via Principle-based Optimization

Seungyoun Yi, Minsoo Khang, Sungrae Park

机构 * Upstage AI Research（Upstage人工智能研究院） 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 9 pages, 4 figures. To appear in EMNLP 2025 Main Conference (Oral Presentation)

Embodied AI: From LLMs to World Models

Tongtong Feng, Xin Wang, Yu-Gang Jiang, Wenwu Zhu

机构 * Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系） ； Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心） ； Institute of Trustworthy Embodied AI, Fudan University（复旦大学可信具身人工智能研究院） 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 by IEEE CASM

Cross-Cultural Transfer of Commonsense Reasoning in LLMs: Evidence from the Arab World

Saeed Almheiri, Rania Hossam, Mena Attia, Chenxi Wang, Preslav Nakov, Timothy Baldwin, Fajri Koto

机构 * Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学） 纠错

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

Comments EMNLP 2025 - Findings

Single-stream Policy Optimization

Zhongwen Xu, Zihan Ding

机构 * Tencent（腾讯） 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

SymRTLO: Enhancing RTL Code Optimization with LLMs and Neuron-Inspired Symbolic Reasoning

Yiting Wang, Wanghao Ye, Ping Guo, Yexiao He, Ziyao Wang, Bowei Tian, Shwai He, Guoheng Sun, Zheyu Shen, Sihan Chen, Ankur Srivastava, Qingfu Zhang, Gang Qu, Ang Li

机构 * University of Maryland, College Park（马里兰大学科帕克分校） ； City University of Hong Kong（香港城市大学） ； University of Southern California（南加州大学） 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

Comments NeurIPS 2025

Question Answering with LLMs and Learning from Answer Sets

Manuel Borroto, Katie Gallagher, Antonio Ielo, Irfan Kareem, Francesco Ricca, Alessandra Russo

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 Under consideration for TPLP journal

Using Natural Language for Human-Robot Collaboration in the Real World

Peter Lindes, Kaoutar Skiker

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 34 pages, 11 figures, 5 tables. Submitted for publication (2026) in W.F. Lawless, Ranjeev Mittu, Shannon P. McGrarry, & Marco Brambilla (Eds.), Generative AI Risks and Benefits within Human-Machine Teams, Elsevier, Chapter 6

Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning

Yaorui Shi, Sihang Li, Chang Wu, Zhiyuan Liu, Junfeng Fang, Hengxing Cai, An Zhang, Xiang Wang

机构 * University of Science and Technology of China（中国科学技术大学） ； National University of Singapore（新加坡国立大学） ； DP Technology（DP技术） 纠错

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

Spatial Audio Motion Understanding and Reasoning

Arvind Krishna Sridhar, Yinyi Guo, Erik Visser

机构 * Qualcomm Technologies Inc.（高通技术公司） 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 5 pages, 2 figures, 3 tables

The Sum Leaks More Than Its Parts: Compositional Privacy Risks and Mitigations in Multi-Agent Collaboration

Vaidehi Patil, Elias Stengel-Eskin, Mohit Bansal

机构 * UNC Chapel Hill（北卡罗来纳大学教堂山分校） ； The University of Texas at Austin（德克萨斯大学奥斯汀分校） 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 Code: https://github.com/Vaidehi99/MultiAgentPrivacy

MovieCORE: COgnitive REasoning in Movies

Gueter Josmy Faure, Min-Hung Chen, Jia-Fong Yeh, Ying Cheng, Hung-Ting Su, Yung-Hao Tang, Shang-Hong Lai, Winston H. Hsu

机构 * National Taiwan University（国立台湾大学） ； NVIDIA ； National Tsing Hua University（国立清华大学） 纠错

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

Comments Accepted for EMNLP'2025 Main Conference (Oral Presentation). Project Page: https://joslefaure.github.io/assets/html/moviecore.html

FRIT: Using Causal Importance to Improve Chain-of-Thought Faithfulness

Anand Swaroop, Akshat Nallani, Saksham Uboweja, Adiliia Uzdenova, Michael Nguyen, Kevin Zhu, Sunishchal Dev, Ashwinee Panda, Vasu Sharma, Maheep Chaudhary

机构 * Algoverse AI Research（Algoverse AI研究院） 纠错

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

Zero-shot Graph Reasoning via Retrieval Augmented Framework with LLMs

Hanqing Li, Kiran Sheena Jyothi, Henry Liang, Sharika Mahadevan, Diego Klabjan

机构 * Northwestern University（西北大学） ； EXL Service（EXL服务） ； Vail Systems（Vail系统） ； Netflix 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

TokenSkip: Controllable Chain-of-Thought Compression in LLMs

Heming Xia, Chak Tou Leong, Wenjie Wang, Yongqi Li, Wenjie Li

机构 * Department of Computing, The Hong Kong Polytechnic University（计算学系，香港理工大学） 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 EMNLP 2025 (Long Paper), camera-ready version

CAC-CoT: Connector-Aware Compact Chain-of-Thought for Efficient Reasoning Data Synthesis Across Dual-System Cognitive Tasks

Sunguk Choi, Yonghoon Kwon, Heondeuk Lee

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 Accepted at EMNLP 2025 findings

Scaling Truth: The Confidence Paradox in AI Fact-Checking

Ihsan A. Qazi, Zohaib Khan, Abdullah Ghani, Agha A. Raza, Zafar A. Qazi, Wassay Sajjad, Ayesha Ali, Asher Javaid, Muhammad Abdullah Sohail, Abdul H. Azeemi

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 65 pages, 26 figures, 6 tables