arXivDaily arXiv每日学术速递 周一至周五更新

AI 大模型

AI Agent

智能体、工具调用、规划、工作流、多智能体和自主任务执行。

共收录 3232 信号源:cs.AI, cs.CL, cs.LG, cs.SE

1. 软件智能体 3232 篇

2603.26990 2026-03-31 hep-ph 82%

Agentic Diagrammatica: Towards Autonomous Symbolic Computation in High Energy Physics

代理图示学:迈向高能物理中自主符号计算

Tony Menzo, Alexander Roman, George T. Fleming, Sergei Gleyzer, Konstantin T. Matchev, Stephen Mrenna

专题命中 软件智能体 :agentic(title,abstract);agent(abstract)

AI总结 本文提出Diagrammatica,通过HEPTAPOD框架扩展实现LLM代理的多步骤理论计算。通过工具约束计算和知识接地方法,实现符号计算的精确性与可验证性,验证了在高能物理中的应用效果。

Comments 54 pages, 6 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.14417 2026-03-17 cs.CY cs.AI cs.CL cs.LG 82%

Questionnaire Responses Do not Capture the Safety of AI Agents

问卷回复无法捕捉AI代理的安全性

Max Hellrigel-Holderbaum, Edward James Young

专题命中 软件智能体 :AI agent(title,abstract);分类 cs.AI、cs.CL、cs.LG

AI总结 本文指出问卷式评估无法准确衡量AI代理的安全性,因LLM在情景中的表现与实际代理行为存在差异,导致评估方法缺乏有效性。

Comments 31 pages, 11 pages main text

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.05621 2026-03-12 cs.RO cs.AI cs.CL cs.LG cs.MA 82%

RACAS: Controlling Diverse Robots With a Single Agentic System

RACAS:通过单一代理系统控制多样化机器人

Dylan R. Ashley, Jan Przepióra, Yimeng Chen, Ali Abualsaud, Nurzhan Yesmagambet, Shinkyu Park, Eric Feron, Jürgen Schmidhuber

机构 * Center of Excellence in Generative AI, King Abdullah University of Science and Technology (KAUST), Saudi Arabia(沙特王国科学与技术大学生成人工智能卓越中心) Dalle Molle Institute for Artificial Intelligence Research (IDSIA), Switzerland(人工智能研究达勒莫利 institute) Università della Svizzera italiana (USI), Switzerland(瑞士意大利大学) Scuola universitaria professionale della Svizzera italiana (SUPSI), Switzerland(瑞士意大利专业大学) Robotics, Intelligent Systems, and Control Lab, King Abdullah University of Science and Technology (KAUST), Saudi Arabia(机器人、智能系统与控制实验室,沙特王国科学与技术大学(KAUST)) Department of Process Control, AGH University of Krakow, Poland(波兰克拉科夫AGH大学过程控制系)

专题命中 软件智能体 :agentic(title,abstract);分类 cs.AI、cs.CL、cs.LG

AI总结 RACAS通过单一代理系统实现跨平台机器人控制,无需修改代码或模型,有效降低机器人原型开发难度。

Comments 7 pages in main text + 1 page of appendices + 1 page of references, 5 figures in main text + 1 figure in appendices, 2 tables in main text; source code available at https://github.com/janprz11/robot-agnostic-control

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.01918 2026-02-10 cs.HC 82%

When Workout Buddies Are Virtual: AI Agents and Human Peers in a Longitudinal Physical Activity Study

当训练伙伴是虚拟的:AI代理与人类同伴在长期身体活动研究中的应用

Alessandro Silacci, Mauro Cherubini, Arianna Boldi, Amon Rapp, Maurizio Caon

专题命中 软件智能体 :AI agent(title,abstract);agent(abstract)

AI总结 本文研究了AI代理与人类同伴在长期身体活动中的影响,发现AI能提供更稳定的鼓励,而人类同伴则增强社会存在感,两者互补促进持续锻炼。

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.20211 2025-10-24 cs.SE cs.AI cs.LG 82%

Automated Cloud Infrastructure-as-Code Reconciliation with AI Agents

Zhenning Yang, Hui Guan, Victor Nicolet, Brandon Paulsen, Joey Dodds, Daniel Kroening, Ang Chen

机构 * University of Michigan(密歇根大学) Amazon Web Services(亚马逊网络服务)

专题命中 软件智能体 :AI agent(title);agentic(abstract);分类 cs.AI、cs.LG、cs.SE

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.09740 2025-09-15 q-bio.QM cs.AI cs.CL cs.LG 82%

HypoGeneAgent: A Hypothesis Language Agent for Gene-Set Cluster Resolution Selection Using Perturb-seq Datasets

Ying Yuan, Xing-Yue Monica Ge, Aaron Archer Waterman, Tommaso Biancalani, David Richmond, Yogesh Pandit, Avtar Singh, Russell Littman, Jin Liu, Jan-Christian Huetter, Vladimir Ermakov

专题命中 软件智能体 :agent(title,abstract);分类 cs.AI、cs.CL、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.13905 2025-09-10 cs.AR 82%

Spec2RTL-Agent: Automated Hardware Code Generation from Complex Specifications Using LLM Agent Systems

Zhongzhi Yu, Mingjie Liu, Michael Zimmer, Yingyan Celine Lin, Yong Liu, Haoxing Ren

专题命中 软件智能体 :agent(title,abstract);multi-agent(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.04227 2025-06-18 cs.HC cs.AI cs.CL cs.LG 82%

Agent Laboratory: Using LLM Agents as Research Assistants

Samuel Schmidgall, Yusheng Su, Ze Wang, Ximeng Sun, Jialian Wu, Xiaodong Yu, Jiang Liu, Michael Moor, Zicheng Liu, Emad Barsoum

专题命中 软件智能体 :agent(title,abstract);分类 cs.AI、cs.CL、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.15625 2025-06-02 cs.LG cs.AI cs.CL cs.DC 82%

Improving Parallel Program Performance with LLM Optimizers via Agent-System Interfaces

Anjiang Wei, Allen Nie, Thiago S. F. X. Teixeira, Rohan Yadav, Wonchan Lee, Ke Wang, Alex Aiken

专题命中 软件智能体 :agent(title,abstract);分类 cs.AI、cs.CL、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.11243 2025-04-16 cs.AI cs.CL cs.LG 82%

Towards Automated Safety Requirements Derivation Using Agent-based RAG

Balahari Vignesh Balu, Florian Geissler, Francesco Carella, Joao-Vitor Zacchi, Josef Jiru, Nuria Mata, Reinhard Stolle

专题命中 软件智能体 :agent(title,abstract);分类 cs.AI、cs.CL、cs.LG

Comments 9 pages, 3 figures

Journal ref Proceedings of the AAAI-make Spring Symposium, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.17703 2025-04-07 cs.RO 82%

RAIDER: Tool-Equipped Large Language Model Agent for Robotic Action Issue Detection, Explanation and Recovery

Silvia Izquierdo-Badiola, Carlos Rizzo, Guillem Alenyà

专题命中 软件智能体 :agent(title,abstract);agentic(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.18359 2025-02-26 cs.CY 82%

Responsible AI Agents

Deven R. Desai, Mark O. Riedl

专题命中 软件智能体 :AI agent(title,abstract);agent(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.12868 2024-10-18 cs.AI cs.CL cs.LG 82%

IMAS: A Comprehensive Agentic Approach to Rural Healthcare Delivery

Agasthya Gangavarapu, Ananya Gangavarapu

专题命中 软件智能体 :agentic(title,abstract);分类 cs.AI、cs.CL、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.09204 2024-10-15 cs.LG cs.AI cs.CL 82%

Encoding Agent Trajectories as Representations with Sequence Transformers

Athanasios Tsiligkaridis, Nicholas Kalinowski, Zhongheng Li, Elizabeth Hou

专题命中 软件智能体 :agent(title,abstract);分类 cs.AI、cs.CL、cs.LG

Comments 12 pages, to be presented at GeoAI workshop at ACM SigSpatial 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2407.03502 2024-07-08 cs.AI cs.CL cs.LG 82%

AgentInstruct: Toward Generative Teaching with Agentic Flows

Arindam Mitra, Luciano Del Corro, Guoqing Zheng, Shweti Mahajan, Dany Rouhana, Andres Codas, Yadong Lu, Wei-ge Chen, Olga Vrousgos, Corby Rosset, Fillipe Silva, Hamed Khanpour, Yash Lara, Ahmed Awadallah

专题命中 软件智能体 :agentic(title,abstract);分类 cs.AI、cs.CL、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
1803.10664 2023-03-23 cs.CR 82%

Autonomous Intelligent Cyber-defense Agent (AICA) Reference Architecture. Release 2.0

Alexander Kott, Paul Théron, Martin Drašar, Edlira Dushku, Benoît LeBlanc, Paul Losiewicz, Alessandro Guarino, Luigi Mancini, Agostino Panico, Mauno Pihelgas, Krzysztof Rzadca, Fabio De Gaspari

专题命中 软件智能体 :agent(title,abstract);autonomous agent(abstract)

Comments This is a major revision and extension of the earlier release of AICA Reference Architecture

详情

展开后加载摘要…

URL PDF HTML 收藏
2101.10072 2022-01-10 cs.MA nlin.CG 82%

Agents.jl: A performant and feature-full agent based modelling software of minimal code complexity

George Datseris, Ali R. Vahdati, Timothy C. DuBois

专题命中 软件智能体 :agent(title,abstract);autonomous agent(abstract)

Comments SIMULATION. January 2022

详情

展开后加载摘要…

URL PDF HTML 收藏
2008.00283 2021-05-06 cond-mat.mtrl-sci 82%

Crystallography companion agent for high-throughput materials discovery

Phillip M. Maffettone, Lars Banko, Peng Cui, Yury Lysogorskiy, Marc A. Little, Daniel Olds, Alfred Ludwig, Andrew I. Cooper

专题命中 软件智能体 :agent(title,abstract);AI agent(abstract)

Comments For associated code, see https://github.com/maffettone/xca

Journal ref Nat. Comput. Sci. 1, 290 (2021)

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.10906 2026-08-12 cs.SE cs.AI 新提交 82%

GitSkills: A Dataset of Agent Skills on GitHub

GitSkills:GitHub上的智能体技能数据集

Giuseppe Destefanis, Daniel Graziotin, Matteo Vaccargiu, Marco Ortu

专题命中 软件智能体 :agent(title,abstract);分类 cs.AI、cs.SE

AI总结 本文提出GitSkills数据集,包含从28.22万个公开GitHub代码库收集的379.7117万个智能体技能相关文件,为智能体技能的多维度研究提供了数据支撑。

Comments Giuseppe Destefanis, Daniel Graziotin, Matteo Vaccargiu, and Marco Ortu. 2027. GitSkills: A Dataset of Agent Skills on GitHub. In Proceedings of the 24th International Conference on Mining Software Repositories (MSR '27). Association for Computing Machinery, New York, NY, USA, 3 pages. To appear

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.19692 2026-02-18 cs.SE cs.AI cs.MA 82%

Toward Agentic Software Engineering Beyond Code: Framing Vision, Values, and Vocabulary

迈向超越代码的代理软件工程:构架视野、价值观和词汇

Rashina Hoda

机构 * Monash University(墨尔本大学)

专题命中 软件智能体 :agentic(title,abstract);分类 cs.AI、cs.SE

AI总结 本文提出代理软件工程应超越代码,构建全过程愿景,基于SE基础和新兴框架,提出价值观和原则,并指导词汇设计,推动SE范式转变。

Comments 5 pages

Journal ref Rashina Hoda, Toward agentic software engineering beyond code: Framing vision, values, and vocabulary. In 2026 IEEE/ACM 48th International Conference on Software Engineering: Companion Proceedings (ICSE-Companion), 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.19635 2025-11-26 cs.SE cs.LG 82%

Agint: Agentic Graph Compilation for Software Engineering Agents

Agint:软件工程代理的代理图编译

Abhi Chivukula, Jay Somasundaram, Vijay Somasundaram

专题命中 软件智能体 :agentic(title,abstract);分类 cs.LG、cs.SE

AI总结 Agint通过代理图编译器和运行时实现高效、可靠的软件工程代理,支持自然语言到代码的自动化转换与协作开发。

Comments 18 pages, 5 figures, NeurIPS 2025: Deep Learning for Code in the Agentic Era

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.05179 2025-10-17 cs.CR cs.AI cs.LG 82%

Agentic Misalignment: How LLMs Could Be Insider Threats

Aengus Lynch, Benjamin Wright, Caleb Larson, Stuart J. Ritchie, Soren Mindermann, Evan Hubinger, Ethan Perez, Kevin Troy

机构 * University College London(伦敦大学学院) Anthropic MATS Mila

专题命中 软件智能体 :agentic(title,abstract);分类 cs.AI、cs.LG

Comments 20 pages, 12 figures. Code available at https://github.com/anthropic-experimental/agentic-misalignment

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.24820 2026-06-24 cs.CL 新提交 81%

SHERLOC: Structured Diagnostic Localization for Code Repair Agents

SHERLOC: 代码修复智能体的结构化诊断定位

Hovhannes Tamoyan, Sean Narenthiran, Erik Arakelyan, Mira Mezini, Boris Ginsburg

机构 * NVIDIA(英伟达) Santa Clara, CA 95051, USA(美国加利福尼亚州圣克拉拉) TU Darmstadt(达姆施塔特工业大学) National Research Center for Applied Cybersecurity ATHENE(国家应用网络安全研究中心 ATHENE)

专题命中 软件智能体 :agent(abstract);tool use(abstract);agentic(abstract);multi-agent(abstract)

AI总结 提出SHERLOC框架,通过推理LLM与紧凑仓库工具及自恢复机制,实现无需微调的结构化诊断定位,在SWE-Bench上达到最优定位精度,并提升修复率、降低令牌消耗。

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.01359 2026-06-17 cs.CR cs.AI 版本更新 81%

Breaking the Code: Security Assessment of AI Code Agents Through Systematic Jailbreaking Attacks

破解代码:通过系统性越狱攻击对AI代码代理进行安全评估

Shoumik Saha, Jifan Chen, Sam Mayers, Sanjay Krishna Gouda, Zijian Wang, Varun Kumar

机构 * University of Maryland – College Park(马里兰大学-College Park) AWS AI Labs(AWS人工智能实验室) Meta Superintelligence Labs(Meta超智能实验室)

专题命中 软件智能体 :agent(abstract,abstract_cn);tool use(abstract);planning(abstract);分类 cs.AI

AI总结 提出JAWS-Bench基准测试,通过三级工作区评估代码LLM代理的越狱风险,发现代理化使攻击成功率提升1.6倍,并揭示可执行攻击代码的高比例。

Comments 22 pages, 18 figures, 8 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.15585 2026-05-18 cs.AI cs.CV 81%

See Before You Code: Learning Visual Priors for Spatially Aware Educational Animation Generation

在编码前看到:学习视觉先验以生成空间感知的教育动画

Yuejia Li, Ke He, Junheng Li, Shutong Chen, Jingkang Xia, Zhiyue Su, Junchi Zhang, Mang Ye

机构 * Wuhan University(武汉大学) University of Chinese Academy of Sciences(中国科学院大学)

专题命中 软件智能体 :agent(abstract,abstract_cn);planning(abstract);multi-agent(abstract);分类 cs.AI

AI总结 本文提出OmniManim框架,通过视觉规划和反馈机制提升教育动画生成质量,改进渲染效果和教学效果。

Comments 21 pages, 4 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.27555 2026-05-01 cs.AI 81%

SpatialGrammar: A Domain-Specific Language for LLM-Based 3D Indoor Scene Generation

SpatialGrammar: 一种面向领域的语言用于基于LLM的3D室内场景生成

Song Tang, Kaiyong Zhao, Yuliang Li, Qingsong Yan, Penglei Sun, Junyi Zou, Qiang Wang, Xiaowen Chu

机构 * The Hong Kong University of Science and Technology (Guangzhou)(香港科学与技术大学(广州)) Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳))

专题命中 软件智能体 :agent(summary_cn,abstract);分类 cs.AI

AI总结 本文提出SpatialGrammar,一种领域特定语言,通过BEV网格放置确定性编译生成有效3D几何,提升空间准确性和物理合理性。SG-Agent通过编译器反馈迭代优化场景,SG-Mini在单次生成场景中表现优异。

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.00083 2025-10-01 cs.SE cs.AI cs.CL cs.LG 81%

A Survey on Code Generation with LLM-based Agents

Yihong Dong, Xue Jiang, Jiaru Qian, Tian Wang, Kechi Zhang, Zhi Jin, Ge Li

机构 * School of Computer Science, Peking University(计算机科学学院,北京大学)

专题命中 软件智能体 :agent(abstract);workflow(abstract);multi-agent(abstract);分类 cs.AI、cs.CL、cs.LG

Comments Work in progress (V2)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.03011 2025-06-04 cs.CL 81%

Coding Agents with Multimodal Browsing are Generalist Problem Solvers

Aditya Bharat Soni, Boxuan Li, Xingyao Wang, Valerie Chen, Graham Neubig

专题命中 软件智能体 :agent(abstract);AI agent(abstract);workflow(abstract);multi-agent(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2407.18901 2024-07-29 cs.SE cs.AI cs.CL cs.LG 81%

AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents

Harsh Trivedi, Tushar Khot, Mareike Hartmann, Ruskin Manku, Vinty Dong, Edward Li, Shashank Gupta, Ashish Sabharwal, Niranjan Balasubramanian

专题命中 软件智能体 :agent(abstract);autonomous agent(abstract);tool use(abstract);分类 cs.AI、cs.CL、cs.LG

Comments ACL'24 Camera Ready

详情

展开后加载摘要…

URL PDF HTML 收藏
2404.12983 2024-04-22 cs.MA cs.CR cs.SI 81%

Private Agent-Based Modeling

Ayush Chopra, Arnau Quera-Bofarull, Nurullah Giray-Kuru, Michael Wooldridge, Ramesh Raskar

专题命中 软件智能体 :agent(title,abstract);autonomous agent(comments);multi-agent(comments)

Comments Accepted at the 23rd International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS 2024)

详情

展开后加载摘要…

URL PDF HTML 收藏