语言大模型 / LLM - arXivDaily 专题

2510.07358 2025-10-10 cs.LG cs.AI cs.CL 80%

Encode, Think, Decode: Scaling test-time reasoning with recursive latent thoughts

Yeskendir Koishekenov, Aldo Lipani, Nicola Cancedda

机构 * FAIR at Meta（Meta的FAIR）； University College London（伦敦大学学院）

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、cs.LG

2506.07778 2025-10-07 cs.CV 80%

A Neurosymbolic Agent System for Compositional Visual Reasoning

Yichang Xu, Gaowen Liu, Ramana Rao Kompella, Sihao Hu, Fatih Ilhan, Selim Furkan Tekin, Zachary Yahn, Ling Liu

机构 * Georgia Institute of Technology（佐治亚理工学院）； Cisco Systems（思科系统）

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；language agent(abstract)

2506.04405 2025-10-07 cs.CL cs.AI cs.LG 80%

MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Science

Ran Xu, Yuchen Zhuang, Yishan Zhong, Yue Yu, Zifeng Wang, Xiangru Tang, Hang Wu, May D. Wang, Peifeng Ruan, Donghan Yang, Tao Wang, Guanghua Xiao, Xin Liu, Carl Yang, Yang Xie, Wenqi Shi

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、cs.LG

2510.03349 2025-10-07 cs.LG cs.AI cs.CL physics.ao-ph 80%

AgentCaster: Reasoning-Guided Tornado Forecasting

Michael Chen

机构 * Department of Computing + Mathematical Sciences（计算与数学科学系）； California Institute of Technology（加州理工学院）

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、cs.LG

2510.01165 2025-10-02 cs.CL cs.AI cs.LG 80%

GRAD: Generative Retrieval-Aligned Demonstration Sampler for Efficient Few-Shot Reasoning

Oussama Gabouj, Kamel Charaf, Ivan Zakazov, Nicolas Baldwin, Robert West

机构 * EPFL（苏黎世联邦理工学院）

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、cs.LG

Comments EMNLP 2025 (findings)

2504.02670 2025-10-02 cs.AI cs.CL cs.IR cs.LG 80%

Affordable AI Assistants with Knowledge Graph of Thoughts

Maciej Besta, Lorenzo Paleari, Jia Hao Andrea Jiang, Robert Gerstenberger, You Wu, Jón Gunnar Hannesson, Patrick Iff, Ales Kubicek, Piotr Nyczyk, Diana Khimey, Nils Blach, Haiqiang Zhang, Tao Zhang, Peiran Ma, Grzegorz Kwaśniewski, Marcin Copik, Hubert Niewiadomski, Torsten Hoefler

机构 * ETH Zurich（苏黎世联邦理工学院）； Cledar（Cledar公司）； IDEAS Research Institute（IDEAS研究所）

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、cs.LG

2509.24193 2025-09-30 cs.CL cs.AI cs.IR cs.LG 80%

AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play

Ran Xu, Yuchen Zhuang, Zihan Dong, Jonathan Wang, Yue Yu, Joyce C. Ho, Linjun Zhang, Haoyu Wang, Wenqi Shi, Carl Yang

机构 * Emory University（埃默里大学）； Georgia Institute of Technology（佐治亚理工学院）； Rutgers University（罗格斯大学）； SUNY Albany（纽约州立大学阿尔巴尼分校）； UT Southwestern Medical Center（德克萨斯西南医学中心）

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、cs.LG

Comments Accepted to NeurIPS 2025 (Spotlight)

2509.22991 2025-09-30 cs.CL cs.AI cs.CV cs.IR cs.LG 80%

ADAM: A Diverse Archive of Mankind for Evaluating and Enhancing LLMs in Biographical Reasoning

Jasin Cekinmez, Omid Ghahroodi, Saad Fowad Chandle, Dhiman Gupta, Ehsaneddin Asgari

机构 * Qatar Computing Research Institute（卡塔尔计算研究所）； Princeton University（普林斯顿大学）； Virginia Tech（弗吉尼亚理工大学）； Amity University（阿米蒂大学）

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、cs.LG

2509.21482 2025-09-29 cs.CL cs.AI cs.LG 80%

Learning to Reason with Mixture of Tokens

Adit Jain, Brendan Rappazzo

机构 * Machine Learning Research, Morgan Stanley, New York, NY（机器学习研究部，摩根士丹利，纽约，纽约）； School of Electrical and Computer Engineering, Cornell University, Ithaca, NY（电气与计算机工程学院，康奈尔大学，伊萨卡，纽约）

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、cs.LG

Comments 30 page

2509.18458 2025-09-26 cs.CL cs.AI cs.LG 80%

CogniLoad: A Synthetic Natural Language Reasoning Benchmark With Tunable Length, Intrinsic Difficulty, and Distractor Density

Daniel Kaiser, Arnoldo Frigessi, Ali Ramezani-Kebrya, Benjamin Ricaud

机构 * UiT - The Arctic University of Norway（UiT - 北极大学）； Integreat - Norwegian Centre for knowledge-driven machine learning（Integreat - 挪威知识驱动机器学习中心）； University of Oslo（奥斯陆大学）

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、cs.LG

Comments 29 pages (main: 12 + supplemental material: 17), 6 figures, 4 tables, Code: https://github.com/kaiserdan/cogniload, Data: https://huggingface.co/datasets/cogniloadteam/cogniload

2505.14615 2025-09-23 cs.AI cs.CL cs.LG cs.LO 80%

SATBench: Benchmarking LLMs' Logical Reasoning via Automated Puzzle Generation from SAT Formulas

Anjiang Wei, Yuheng Wu, Yingjia Wan, Tarun Suresh, Huanmi Tan, Zhanke Zhou, Sanmi Koyejo, Ke Wang, Alex Aiken

机构 * Stanford University（斯坦福大学）； UCLA（加州大学洛杉矶分校）； UIUC（伊利诺伊大学香槟分校）； CMU（卡内基梅隆大学）； Nanjing University（南京大学）

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、cs.LG

2507.08627 2025-09-18 cs.SE 80%

NL in the Middle: Code Translation with LLMs and Intermediate Representations

Chi-en Amy Tai, Pengyu Nie, Lukasz Golab, Alexander Wong

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

2501.14179 2025-09-01 cs.HC 80%

AI Chatbots as Professional Service Agents: Developing a Professional Identity

Wenwen Li, Kangwei Shi, Yidong Chai

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

2508.20019 2025-08-28 cs.LG cs.AI cs.CL cs.MA 80%

Symphony: A Decentralized Multi-Agent Framework for Scalable Collective Intelligence

Ji Wang, Kashing Chen, Xinyuan Song, Ke Zhang, Lynn Ai, Eric Yang, Bill Shi

机构 * Gradient ； The Chinese University of Hong Kong（香港中文大学）； Department of Computer Science and Computer Engineering, Waseda University（计算机科学与工程系，早稻田大学）

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、cs.LG

2507.18973 2025-08-25 cs.CL cs.AI cs.LG 80%

A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool Aggregation

Bohan Yao, Vikas Yadav

机构 * ServiceNow AI ； University of Washington（华盛顿大学）

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、cs.LG

Comments Published at EMNLP Findings 2025; 21 pages, 3 figures

2508.15388 2025-08-22 cs.IR 80%

TrackRec: Iterative Alternating Feedback with Chain-of-Thought via Preference Alignment for Recommendation

Yu Xia, Rui Zhong, Zeyu Song, Wei Yang, Junchen Wan, Qingpeng Cai, Chi Lu, Peng Jiang

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；preference optimization(abstract)

2508.04714 2025-08-22 cs.AI cs.CL cs.LG cs.MA eess.SP 80%

Prescriptive Agents based on RAG for Automated Maintenance (PARAM)

Chitranshu Harbola, Anupam Purwar

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、cs.LG

2502.06855 2025-08-22 cs.CL cs.AI cs.LG 80%

Self-Supervised Prompt Optimization

Jinyu Xiang, Jiayi Zhang, Zhaoyang Yu, Xinbing Liang, Fengwei Teng, Jinhao Tu, Fashen Ren, Xiangru Tang, Sirui Hong, Chenglin Wu, Yuyu Luo

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、cs.LG

2507.03984 2025-08-21 cs.CV 80%

CoT-Segmenter: Enhancing OOD Detection in Dense Road Scenes via Chain-of-Thought Reasoning

Jeonghyo Song, Kimin Yun, DaeUng Jo, Jinyoung Kim, Youngjoon Yoo

机构 * Department of Artificial Intelligence, Chung-Ang University（Chung-Ang大学人工智能系）； Visual Intelligence Lab., ETRI（ETRI视觉智能实验室）； University of Science and Technology (UST)（科技大学（UST））； School of Electronics Engineering, Kyungpook National University（Kyungpook国立大学电子工程学院）

专题命中推理与问题求解：large language model(abstract)；language model(abstract)；foundation model(abstract)；prompting(abstract)

Comments 6 pages, 3 figures. Accepted at IEEE International Conference on Advanced Visual and Signal-Based Systems 2025

2508.12086 2025-08-19 cs.CL cs.AI cs.LG 80%

J6: Jacobian-Driven Role Attribution for Multi-Objective Prompt Optimization in LLMs

Yao Wu

机构 * School of Engineering（工程学院）； Westlake University（西湖大学）

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、cs.LG

Comments 9 pages, 3 tables, 1 algorithm

2508.11305 2025-08-18 cs.SE 80%

Defects4Log: Benchmarking LLMs for Logging Code Defect Detection and Reasoning

Xin Wang, Zhenhao Li, Zishuo Ding

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

2506.00160 2025-08-12 cs.CL cs.AI cs.LG 80%

Verbal Werewolf: Engage Users with Verbalized Agentic Werewolf Game Framework

Qihui Fan, Wenbo Li, Enfu Nan, Yixiao Chen, Lei Lu, Pu Zhao, Yanzhi Wang

机构 * Northeastern University（东北大学）

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、cs.LG

2508.03366 2025-08-06 cs.AI cs.CL cs.LG cs.SC 80%

A Comparative Study of Neurosymbolic AI Approaches to Interpretable Logical Reasoning

Michael K. Chen

机构 * Raffles Institution（拉夫斯学院）

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、cs.LG

Comments Accepted to NeSy 2025

2508.00957 2025-08-05 cs.LG cs.AI cs.CL 80%

Small sample-based adaptive text classification through iterative and contrastive description refinement

Amrit Rajeev, Udayaadithya Avadhanam, Harshula Tulapurkar, SaiBarath Sundar

机构 * Mphasis Limited（Mphasis公司）

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、cs.LG

2502.13820 2025-07-31 cs.AI cs.CL cs.LG cs.SE 80%

Scoring Verifiers: Evaluating Synthetic Verification for Code and Reasoning

Aleksander Ficek, Somshubra Majumdar, Vahid Noroozi, Boris Ginsburg

机构 * NVIDIA Santa Clara, CA 15213, USA（英伟达圣克拉拉分校）

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、cs.LG

Comments COLM 2025

2507.19849 2025-07-29 cs.LG cs.AI cs.CL 80%

Agentic Reinforced Policy Optimization

Guanting Dong, Hangyu Mao, Kai Ma, Licheng Bao, Yifei Chen, Zhongyuan Wang, Zhongxia Chen, Jiazhen Du, Huiyang Wang, Fuzheng Zhang, Guorui Zhou, Yutao Zhu, Ji-Rong Wen, Zhicheng Dou

机构 * Renmin University of China（中国人民大学）； Kuaishou Technology（快手科技）

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、cs.LG

Comments Working on progress

2505.22334 2025-07-24 cs.CL cs.AI cs.CV cs.LG 80%

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start

Lai Wei, Yuting Li, Kaipeng Zheng, Chen Wang, Yue Wang, Linghe Kong, Lichao Sun, Weiran Huang

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

2507.15501 2025-07-22 cs.CL cs.AI cs.LG 80%

ASPERA: A Simulated Environment to Evaluate Planning for Complex Action Execution

Alexandru Coca, Mark Gaynor, Zhenxing Zhang, Jianpeng Cheng, Bo-Hsiang Tseng, Pete Boothroyd, Héctor Martinez Alonso, Diarmuid Ó Séaghdha, Anders Johannsen

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、cs.LG

Comments 37 pages, 22 figures. To appear at ACL 2025

2502.01100 2025-07-16 cs.AI cs.CL cs.LG 80%

ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning

Bill Yuchen Lin, Ronan Le Bras, Kyle Richardson, Ashish Sabharwal, Radha Poovendran, Peter Clark, Yejin Choi

机构 * Allen Institute for AI（艾伦人工智能研究所）； University of Washington（华盛顿大学）； Stanford University（斯坦福大学）

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、cs.LG

Comments Accepted to ICML 2025

2507.06742 2025-07-10 cs.CR 80%

PenTest2.0: Towards Autonomous Privilege Escalation Using GenAI

Haitham S. Al-Sinani, Chris J. Mitchell

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments 45 pages, 23 figures

1. 推理与问题求解 19038 篇

Encode, Think, Decode: Scaling test-time reasoning with recursive latent thoughts

A Neurosymbolic Agent System for Compositional Visual Reasoning

MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Science

AgentCaster: Reasoning-Guided Tornado Forecasting

GRAD: Generative Retrieval-Aligned Demonstration Sampler for Efficient Few-Shot Reasoning

Affordable AI Assistants with Knowledge Graph of Thoughts

AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play

ADAM: A Diverse Archive of Mankind for Evaluating and Enhancing LLMs in Biographical Reasoning

Learning to Reason with Mixture of Tokens

CogniLoad: A Synthetic Natural Language Reasoning Benchmark With Tunable Length, Intrinsic Difficulty, and Distractor Density

SATBench: Benchmarking LLMs' Logical Reasoning via Automated Puzzle Generation from SAT Formulas

NL in the Middle: Code Translation with LLMs and Intermediate Representations

AI Chatbots as Professional Service Agents: Developing a Professional Identity

Symphony: A Decentralized Multi-Agent Framework for Scalable Collective Intelligence

A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool Aggregation

TrackRec: Iterative Alternating Feedback with Chain-of-Thought via Preference Alignment for Recommendation

Prescriptive Agents based on RAG for Automated Maintenance (PARAM)

Self-Supervised Prompt Optimization

CoT-Segmenter: Enhancing OOD Detection in Dense Road Scenes via Chain-of-Thought Reasoning

J6: Jacobian-Driven Role Attribution for Multi-Objective Prompt Optimization in LLMs

Defects4Log: Benchmarking LLMs for Logging Code Defect Detection and Reasoning

Verbal Werewolf: Engage Users with Verbalized Agentic Werewolf Game Framework

A Comparative Study of Neurosymbolic AI Approaches to Interpretable Logical Reasoning

Small sample-based adaptive text classification through iterative and contrastive description refinement

Scoring Verifiers: Evaluating Synthetic Verification for Code and Reasoning

Agentic Reinforced Policy Optimization

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start

ASPERA: A Simulated Environment to Evaluate Planning for Complex Action Execution

ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning

PenTest2.0: Towards Autonomous Privilege Escalation Using GenAI