语言大模型 / LLM - arXivDaily 专题

2310.18532 2023-12-19 cs.SE 89%

SkipAnalyzer: A Tool for Static Code Analysis with Large Language Models

Mohammad Mahdi Mohajer, Reem Aleithan, Nima Shiri Harzevili, Moshi Wei, Alvine Boaye Belle, Hung Viet Pham, Song Wang

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

2311.17365 2023-11-30 cs.CV 89%

Symbol-LLM: Leverage Language Models for Symbolic System in Visual Human Activity Reasoning

Xiaoqian Wu, Yong-Lu Li, Jianhua Sun, Cewu Lu

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

Comments Accepted by NeurIPS 2023

2311.11860 2023-11-28 cs.CV 89%

LION : Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge

Gongwei Chen, Leyang Shen, Rui Shao, Xiang Deng, Liqiang Nie

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

Comments Technical Report. Project page: https://rshaojimmy.github.io/Projects/JiuTian-LION Code: https://github.com/rshaojimmy/JiuTian

2311.08166 2023-11-15 cs.AI cond-mat.dis-nn cond-mat.mtrl-sci cs.CL cs.LG 89%

MechAgents: Large language model multi-agent collaborations can solve mechanics problems, generate new data, and integrate knowledge

Bo Ni, Markus J. Buehler

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

2311.01403 2023-11-03 cs.RO 89%

REAL: Resilience and Adaptation using Large Language Models on Autonomous Aerial Robots

Andrea Tagliabue, Kota Kondo, Tong Zhao, Mason Peterson, Claudius T. Tewari, Jonathan P. How

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

Comments 13 pages, 5 figures, conference workshop

2305.14078 2023-10-31 cs.RO 89%

Large Language Models as Commonsense Knowledge for Large-Scale Task Planning

Zirui Zhao, Wee Sun Lee, David Hsu

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

Comments In Proceedings of NeurIPS 2023

2310.05253 2023-10-23 cs.CL cs.AI cs.LG 89%

Explainable Claim Verification via Knowledge-Grounded Reasoning with Large Language Models

Haoran Wang, Kai Shu

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

Comments Findings of EMNLP 2023

2310.02046 2023-10-04 cs.SE 89%

Improving web element localization by using a large language model

Michel Nass, Emil Alegroth, Robert Feldt

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

2212.09597 2023-09-19 cs.CL cs.AI cs.CV cs.IR cs.LG 89%

Reasoning with Language Model Prompting: A Survey

Shuofei Qiao, Yixin Ou, Ningyu Zhang, Xiang Chen, Yunzhi Yao, Shumin Deng, Chuanqi Tan, Fei Huang, Huajun Chen

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

Comments ACL 2023, 24 pages, add references of theoretical analysis

2309.07062 2023-09-14 cs.PL cs.AI cs.CL cs.LG 89%

Large Language Models for Compiler Optimization

Chris Cummins, Volker Seeker, Dejan Grubisic, Mostafa Elhoushi, Youwei Liang, Baptiste Roziere, Jonas Gehring, Fabian Gloeckle, Kim Hazelwood, Gabriel Synnaeve, Hugh Leather

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

2308.11483 2023-08-23 cs.CL cs.AI cs.LG 89%

Large Language Models Sensitivity to The Order of Options in Multiple-Choice Questions

Pouya Pezeshkpour, Estevam Hruschka

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

2212.10071 2023-06-14 cs.CL cs.AI cs.LG 89%

Large Language Models Are Reasoning Teachers

Namgyu Ho, Laura Schmid, Se-Young Yun

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

Comments ACL 2023 camera-ready

2306.03917 2023-06-08 cs.CL cs.AI cs.LG 89%

Turning large language models into cognitive models

Marcel Binz, Eric Schulz

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

2305.04369 2023-06-02 cs.FL 89%

Getting More out of Large Language Models for Proofs

Shizhuo Dylan Zhang, Talia Ringer, Emily First

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

2209.08141 2023-05-23 cs.CL cs.AI cs.LG 89%

Psychologically-informed chain-of-thought prompts for metaphor understanding in large language models

Ben Prystawski, Paul Thibodeau, Christopher Potts, Noah D. Goodman

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

Comments 7 pages, 1 figure

2305.05364 2023-05-10 cs.LG cs.AI cs.CL 89%

Large Language Model Programs

Imanol Schlag, Sainbayar Sukhbaatar, Asli Celikyilmaz, Wen-tau Yih, Jason Weston, Jürgen Schmidhuber, Xian Li

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

2303.05510 2023-03-10 cs.LG cs.AI cs.CL cs.PL 89%

Planning with Large Language Models for Code Generation

Shun Zhang, Zhenfang Chen, Yikang Shen, Mingyu Ding, Joshua B. Tenenbaum, Chuang Gan

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

Comments ICLR 2023. Project page:https://codeaimcts.github.io

2205.05718 2022-05-13 cs.CL cs.AI cs.LG cs.SC 89%

Structured, flexible, and robust: benchmarking and improving large language models towards more human-like behavior in out-of-distribution reasoning tasks

Katherine M. Collins, Catherine Wong, Jiahai Feng, Megan Wei, Joshua B. Tenenbaum

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

Comments Originally accepted to the 2022 Cognitive Science (CogSci) conference

2506.04867 2026-02-25 cs.AI cs.HC cs.LG cs.RO 89%

Sensory-Motor Control with Large Language Models via Iterative Policy Refinement

通过迭代策略优化实现大语言模型的感官-运动控制

Jônata Tyska Carvalho, Stefano Nolfi

机构 * Federal University of Santa Catarina (UFSC)（圣卡塔琳娜联邦大学）； Institute of Cognitive Sciences and Technologies (ISTC-CNR)（认知科学与技术研究所）

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

AI总结本文提出通过迭代策略优化，利用大语言模型控制具身代理，结合符号知识与子符号感官运动数据实现高效控制。

Comments Final version of the article accepted for publication on Scientific Reports. 29 pages (13 pages are from appendix), 8 figures, 2 tables, code for experiments replication and supplementary material provided at https://github.com/jtyska/llm-robotics-article/

2510.05016 2025-10-08 astro-ph.IM cs.AI cs.CL 89%

Large Language Models Achieve Gold Medal Performance at the International Olympiad on Astronomy & Astrophysics (IOAA)

Lucas Carrit Delgado Pinheiro, Ziru Chen, Bruno Caixeta Piazza, Ness Shroff, Yingbin Liang, Yuan-Sen Ting, Huan Sun

机构 * The Ohio State University（俄亥俄州立大学）； Universidade de São Paulo（圣保罗大学）

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

Comments 18 pages, 6 figures, to be submitted, comments are welcome. Reproducibility details can be found at: https://github.com/OSU-NLP-Group/LLM-IOAA

2404.02508 2024-04-04 cs.CV cs.AI cs.LG 89%

VIAssist: Adapting Multi-modal Large Language Models for Users with Visual Impairments

Bufang Yang, Lixing He, Kaiwei Liu, Zhenyu Yan

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

Comments Accepted to IEEE International Workshop on Foundation Models for Cyber-Physical Systems & Internet of Things (FMSys 2024)

2312.13876 2023-12-22 cs.LG cs.CL stat.ML 89%

Capture the Flag: Uncovering Data Insights with Large Language Models

Issam Laradji, Perouz Taslakian, Sai Rajeswar, Valentina Zantedeschi, Alexandre Lacoste, Nicolas Chapados, David Vazquez, Christopher Pal, Alexandre Drouin

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

Comments 14 pages, 1 figure, Foundation Models for Decision Making Workshop at NeurIPS 2023

2605.06737 2026-08-17 cs.SE cs.AI 89%

A Self-Healing Framework for Reliable LLM-Based Autonomous Agents

基于大语言模型的自主代理的自修复框架

Cheonsu Jeong, Younggun Shin

机构 * AX Center, SAMSUNG SDS（三星SDS AX中心）； Dept. of Artificial Intelligence, Graduate School of Engineering, Yonsei University（延世大学工程研究生院人工智能系）

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

AI总结本文提出一种可靠性感知的自修复框架，通过故障检测、可靠性评估和自动恢复机制提升基于大语言模型的自主代理的可靠性，实验表明该方法显著提高了任务成功率并增强了系统鲁棒性。

Comments 13 pages, 3 figures,1 table

Journal ref International Journal of Software Engineering and Knowledge Engineering,2026

2608.12679 2026-08-14 cs.AI cs.NE 新提交 89%

Beyond the Best Guess: Improving LLM Solution Coverage with Evolution Strategies

超越最佳猜测：用进化策略提升大语言模型的解决方案覆盖率

Conor F. Hayes, Elliot Meyerson, Kajetan Schweighofer, Roberto Dailey, Babak Hodjat, Risto Miikkulainen, Xin Qiu

机构 * The University of Texas at Austin（德克萨斯大学奥斯汀分校）； Cognizant AI Lab（高知特人工智能实验室）

专题命中推理与问题求解：LLM(title,summary_cn)；large language model(abstract)；language model(abstract)；post-training(abstract)

AI总结该研究针对LLM后训练中RL导致pass@k受限、解决方案覆盖率不足的问题，采用进化策略（ES）方法，提升了pass@k与解决方案覆盖率，在数学基准上取得更好结果，为相关领域后训练提供了更好基础。

2608.08477 2026-08-11 cs.CL 新提交 89%

VectraYX-Vision-1B: A Sub-2B Spanish/LATAM Cybersecurity Vision-Language Model with Structured Visual Reasoning and Native Tool Use

VectraYX-Vision-1B：一款具备结构化视觉推理与原生工具使用能力的20亿参数以下西班牙语/拉丁美洲网络安全多模态模型

Juan S. Santillana

专题命中推理与问题求解：language model(title,abstract)；LLM(abstract,abstract_cn)；SFT(abstract,abstract_cn)；分类 cs.CL

AI总结本研究推出VectraYX-Vision-1B，一款20亿参数以下西班牙语/拉丁美洲网络安全多模态模型，支持结构化推理与工具调用，针对网络UI优化，同时报告了其视觉定位的负面结果及相关修复方案，开源了模型与数据。

Comments 11 pages, 1 figure

2605.08876 2026-08-04 cs.LG 版本更新 89%

OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents

OTora：一种用于LLM代理推理层面拒绝服务攻击的统一红队框架

Xinyu Li, Ronghui Mu, Lin Li, Tianjin Huang, Gaojie Jin

机构 * Department of Computer Science, University of Exeter（埃克塞特大学计算机科学系）； Department of Computer Science, University of Oxford（牛津大学计算机科学系）； Department of Mathematics and Computer Science, Eindhoven University of Technology（埃因霍温理工大学数学与计算机科学系）

专题命中推理与问题求解：LLM(title,title_cn)；large language model(abstract)；language model(abstract)；分类 cs.LG

AI总结 OTora是首个统一的两阶段红队框架，用于实现推理层面拒绝服务攻击，通过优化对抗触发器和生成代理感知的推理负载，提升推理token数量和延迟，同时保持任务准确性。

Comments Accepted to ICML 2026

2607.21196 2026-07-24 cs.LO cs.AI 新提交 89%

Case study: solving P-99 with LPTP and an LLM

案例研究：使用LPTP和语言模型解决P-99问题

Fred Mesnard, Thierry Marianne, Étienne Payet, Wim Vanhoof

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

AI总结该研究以九十九个Prolog问题（P-99）为对象，借助向语言模型Claude提问，生成Prolog代码及测试文件，再用LPTP进行验证，完成了前三十三个问题的解决，介绍了具体过程与细节，为他人重现实验提供便利。

Comments In Proceedings ICLP 2026, arXiv:2607.17707

Journal ref EPTCS 450, 2026, pp. 209-222

2309.05898 2026-07-15 cs.GT cs.AI cs.CY cs.HC econ.TH 89%

Strategic Behavior of Large Language Models: Game Structure vs. Contextual Framing

大语言模型的战略行为：游戏结构与情境框架

Nunzio Lorè, Babak Heydari

专题命中推理与问题求解：large language model(title,abstract)；language model(title,abstract)；分类 cs.AI

AI总结本文研究三种大语言模型在不同博弈结构和情境框架下的战略决策能力，揭示其在抽象推理和情境适应方面的差异与局限。

Comments 25 pages, 12 figures

Journal ref Lorè, N., Heydari, B. Strategic behavior of large language models and the role of game structure versus contextual framing. Sci Rep 14, 18490 (2024)

2606.29929 2026-06-30 cs.AI 89%

HippoSpark: An On-Demand Experience System for LLM Reasoning

HippoSpark: 一种用于LLM推理的按需经验系统

Jingyao Liu, Danling Meng, Chen Huang, Yukun Yan, Zhenghao Liu, Wenqiang Lei, See-Kiong Ng, Maosong Sun

专题命中推理与问题求解：LLM(title,title_cn)；prompting(abstract)；分类 cs.AI

AI总结提出HippoSpark状态级经验系统，在推理过程中按需检索局部瓶颈的精确指导，在数学、科学和编程基准上优于标准提示和任务级经验基线。

2512.23601 2026-06-23 cs.AI 版本更新 89%

Enhancing Diversity of LLM-Generated Educational Tasks

增强大语言模型生成教育任务的多样性

Manh Hung Nguyen, Sebastian Tschiatschek, Adish Singla

机构 * MPI-SWS（马克斯·普朗克研究所-斯图加特研究所）； University of Vienna（维也纳大学）

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

AI总结针对大语言模型生成教育任务时内容同质化的问题，提出基于发散-收敛思维的两阶段提示框架CreativeDC，在Python编程领域生成的任务多样性提升约1.6倍，同时保持高实用性。

Comments EDM 2026 Poster Paper

1. 推理与问题求解 18936 篇

SkipAnalyzer: A Tool for Static Code Analysis with Large Language Models

Symbol-LLM: Leverage Language Models for Symbolic System in Visual Human Activity Reasoning

LION : Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge

MechAgents: Large language model multi-agent collaborations can solve mechanics problems, generate new data, and integrate knowledge

REAL: Resilience and Adaptation using Large Language Models on Autonomous Aerial Robots

Large Language Models as Commonsense Knowledge for Large-Scale Task Planning

Explainable Claim Verification via Knowledge-Grounded Reasoning with Large Language Models

Improving web element localization by using a large language model

Reasoning with Language Model Prompting: A Survey

Large Language Models for Compiler Optimization

Large Language Models Sensitivity to The Order of Options in Multiple-Choice Questions

Large Language Models Are Reasoning Teachers

Turning large language models into cognitive models

Getting More out of Large Language Models for Proofs

Psychologically-informed chain-of-thought prompts for metaphor understanding in large language models

Large Language Model Programs

Planning with Large Language Models for Code Generation

Structured, flexible, and robust: benchmarking and improving large language models towards more human-like behavior in out-of-distribution reasoning tasks

Sensory-Motor Control with Large Language Models via Iterative Policy Refinement

Large Language Models Achieve Gold Medal Performance at the International Olympiad on Astronomy & Astrophysics (IOAA)

VIAssist: Adapting Multi-modal Large Language Models for Users with Visual Impairments

Capture the Flag: Uncovering Data Insights with Large Language Models

A Self-Healing Framework for Reliable LLM-Based Autonomous Agents

Beyond the Best Guess: Improving LLM Solution Coverage with Evolution Strategies

VectraYX-Vision-1B: A Sub-2B Spanish/LATAM Cybersecurity Vision-Language Model with Structured Visual Reasoning and Native Tool Use

OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents

Case study: solving P-99 with LPTP and an LLM

Strategic Behavior of Large Language Models: Game Structure vs. Contextual Framing

HippoSpark: An On-Demand Experience System for LLM Reasoning

Enhancing Diversity of LLM-Generated Educational Tasks