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 2955 信号源:cs.AI, cs.CL, cs.LG, cs.SE

1. GUI与网页智能体 2955 篇

1410.4147 2014-10-16 cs.CR 78%

Mobile Agent Systems, Recent Security Threats and Counter Measures

Belal Amro

专题命中 GUI与网页智能体 :agent(title,abstract)

Comments international journal of computer science issues, march 2014

详情

展开后加载摘要…

URL PDF HTML 收藏
1401.5509 2014-01-23 cs.OH 78%

Intelligent Product: Mobile Agent Architecture Integrating the End of Life Cycle (EOL) For minimizing the lunch phase PLM

Abdelhak Boulaalam, El Habib Nfaoui, Omar El Beqqali

专题命中 GUI与网页智能体 :agent(title,abstract)

Comments 8 pages, 11 figures, The Proceeding of International Conference on Soft Computing and Software Engineering 2013

Journal ref International Journal of Soft Computing and Software Engineering [JSCSE], Vol. 3, No. 3, pp. 107-114, 2013, Doi: 10.7321/jscse.v3.n3.18

详情

展开后加载摘要…

URL PDF HTML 收藏
1307.7642 2013-07-30 q-bio.GN 78%

The genome of the medieval Black Death agent (extended abstract)

Ashok Rajaraman, Eric Tannier, Cedric Chauve

专题命中 GUI与网页智能体 :agent(title,abstract)

Comments Extended abstract of a talk presented at the conference JOBIM 2013, https://colloque.inra.fr/jobim2013_eng/. Full paper submitted

详情

展开后加载摘要…

URL PDF HTML 收藏
1210.4644 2012-10-18 cs.OH 78%

Dimensions and issues of mobile agent technology

Yashpal Singh, Kapil Gulati, S. Niranjan

专题命中 GUI与网页智能体 :agent(title,abstract)

Comments 11 pages, 6 figure

Journal ref International Journal of Artificial Intelligence & Applications (IJAIA), Vol.3, No.5, 2012, 51-61

详情

展开后加载摘要…

URL PDF HTML 收藏
1202.1941 2012-02-10 cs.NI cs.DC cs.MA 78%

An Intelligent Mobile-Agent Based Scalable Network Management Architecture for Large-Scale Enterprise System

A. K. Sharma, Atul Mishra, Vijay Singh

专题命中 GUI与网页智能体 :agent(title,abstract)

Comments 16 pages, 10 figures, published in IJCNC

Journal ref International Journal of Computer Networks and Communications (IJCNC), January 2012, Volume 4, Number 1, ISSN [online : 0974-9322]

详情

展开后加载摘要…

URL PDF HTML 收藏
1108.2095 2011-08-11 cs.NI cs.SI 78%

Mobile Agent as an Approach to Improve QoS in Vehicular Ad Hoc Network

Rakesh Kumar, Mayank Dave

专题命中 GUI与网页智能体 :agent(title,abstract)

Comments 6 pages,5 figures; IJCA Special Issue on "Mobile Ad-hoc Networks" 2011

详情

展开后加载摘要…

URL PDF HTML 收藏
1107.3674 2011-08-03 cs.MA 78%

Autonomous Traffic Control System Using Agent Based Technology

Venkatesh. M, K. Kumar, Srinivas. V

专题命中 GUI与网页智能体 :agent(title,abstract)

Comments This paper has been withdrawn by the authors. Total Pages 8 and 3 Figures, Author wishes to withdraw for some major changes and corrections

Journal ref International Journal of Advancements in Technology, Vol.2, No. 3, July 2011

详情

展开后加载摘要…

URL PDF HTML 收藏
1012.4485 2010-12-22 cs.NI cs.MA 78%

An Experimental Approach for Optimising Mobile Agent Migrations

Damianos Gavalas

专题命中 GUI与网页智能体 :agent(title,abstract)

Comments 8 pages, 7 figures

Journal ref Mediterranean Journal of Computers and Networks, 1(1), pp. 47-56, SoftMotor Ltd., ISSN: 1744-2397, July 2005

详情

展开后加载摘要…

URL PDF HTML 收藏
1006.4538 2010-06-24 cs.NI 78%

Computational Analysis of .NET Remoting and Mobile agent in Distributed Environment

Vivek Tiwari, G. Shailendra, Renu Tiwari, Malam Kirar

专题命中 GUI与网页智能体 :agent(title,abstract)

Comments IEEE Publication Format, https://sites.google.com/site/journalofcomputing/

Journal ref Journal of Computing, Vol. 2, No. 6, June 2010, NY, USA, ISSN 2151-9617

详情

展开后加载摘要…

URL PDF HTML 收藏
0806.2308 2009-12-01 q-bio.PE q-bio.OT 78%

Dynamics and Steady States in excitable mobile agent systems

Fernando Peruani, Gustavo J. Sibona

专题命中 GUI与网页智能体 :agent(title,abstract)

Journal ref Phys. Rev. Lett. 100, 168103 (2008)

详情

展开后加载摘要…

URL PDF HTML 收藏
math/0405439 2009-12-01 math.OC math.DS 78%

Self-organization in a group of mobile autonomous agents

Long Wang

专题命中 GUI与网页智能体 :autonomous agent(title,abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.00432 2026-08-04 cs.CL 新提交 77%

Deep Research Pretraining via Predictive Navigation

基于预测导航的深度研究预训练

Jiang Zhou, Zhiyuan Fan, Xing Wu, Tinghao Yu, Feng Zhang, Lilin Wang

机构 * Tencent(腾讯) Hunyuan Team(混元团队)

专题命中 GUI与网页智能体 :agent(abstract);tool-use(abstract);agentic(abstract);分类 cs.CL

AI总结 提出Deep Research Pretraining(DRP)离线框架,在学术引用图和维基百科超链接上预训练Qwen3-14B-Base模型,可提升智能体在多个基准任务上的表现,是轨迹智能体训练的补充方法。

Comments working in progress; correspondence to {ucaswu,maxwellyu}@tencent.com or wuxing@iie.ac.cn

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.26266 2026-07-01 cs.AI cs.CV 版本更新 77%

GUIDE: Resolving Domain Bias in GUI Agents through Real-Time Web Video Retrieval and Plug-and-Play Annotation

GUIDE:通过实时网络视频检索和即插即用标注解决GUI代理的领域偏见

Rui Xie, Zhi Gao, Chenrui Shi, Zirui Shang, Lu Chen, Qing Li

机构 * Shanghai Jiao Tong University(上海交通大学) State Key Laboratory for General Artificial Intelligence, BIGAI(通用人工智能国家重点实验室,北京通用人工智能研究院) Beijing Institute of Technology(北京理工大学)

专题命中 GUI与网页智能体 :agent(abstract);planning(abstract);multi-agent(abstract);分类 cs.AI

AI总结 GUIDE通过实时网络视频检索和即插即用标注框架,解决GUI代理的领域偏见问题,通过视频语义分析和自动化标注流程提升代理对特定应用的操作流程和UI布局的理解,实验表明其在多代理系统和单模型代理中均能提升性能。

Comments Accepted to ECCV 2026. 30 pages: 15-page main paper followed by supplementary material as an appendix (Sections A-F). Project page: https://sharryXR.github.io/GUIDE/

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.16802 2026-06-16 cs.AI 新提交 77%

LabOSBench: Benchmarking Computer Use Agents for Scientific Instrument Control

LabOSBench: 科学仪器控制的计算机使用智能体基准测试

Anqi Zou, Han Deng, Chengyu Zhang, Junquan Hu, Yu Wang, Yuxiang Xing, Aokai Zhang, Hanling Zhang, Zhaoyang Liu, Ben Fei, Zhihui Wang, Wanli Ouyang

机构 * Shenzhen Loop Area Institute(深圳河套学院) Dalian University of Technology(大连理工大学) The Chinese University of Hong Kong(香港中文大学) The Hong Kong University of Science and Technology(香港科技大学)

专题命中 GUI与网页智能体 :agent(abstract);workflow(abstract);agentic(abstract);分类 cs.AI

AI总结 提出LabOSBench基准,基于Web科学仪器模拟器评估多模态GUI智能体在仪器控制中的表现,揭示现有智能体在反馈驱动操作和长流程执行上的不足。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.09923 2026-06-05 cs.AI 77%

CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents

CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents

Hanna Foerster, Tom Blanchard, Kristina Nikolić, Ilia Shumailov, Cheng Zhang, Robert Mullins, Nicolas Papernot, Florian Tramèr, Yiren Zhao

机构 * University of Cambridge(剑桥大学) University of Toronto & Vector Institute(多伦多大学及向量研究所) ETH Zurich(苏黎世联邦理工学院) AI Security Company(人工智能安全公司)

专题命中 GUI与网页智能体 :agent(abstract);AI agent(abstract);planning(abstract);分类 cs.AI

AI总结 本文提出了一种系统级安全方法,用于计算机使用代理(CUAs),通过单次规划和NOVA框架在动态UI状态下提供控制流完整性保障,同时在保持性能的同时提升安全性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.13527 2026-06-02 cs.AI 77%

MMSkills: Towards Multimodal Skills for General Visual Agents

MMSkills: 面向通用视觉智能体的多模态技能

Kangning Zhang, Shuai Shao, Qingyao Li, Jianghao Lin, Lingyue Fu, Shijian Wang, Wenxiang Jiao, Yuan Lu, Weiwen Liu, Weinan Zhang, Yong Yu

机构 * Shanghai Jiao Tong University(上海交通大学) Xiaohongshu Inc.(小红书公司) Southeast University(东南大学)

专题命中 GUI与网页智能体 :agent(abstract);workflow(abstract);agentic(abstract);分类 cs.AI

AI总结 提出MMSkills框架,通过将多模态程序知识编码为紧凑的状态条件包(包含文本程序、运行时状态卡和多视角关键帧),并利用轨迹到技能生成器和分支加载多模态技能智能体,显著提升GUI和游戏场景下视觉智能体的决策能力。

Comments 25 pages, 8 figures, 8 tables. Project page: https://zkangning.github.io/MMSkills_for_Visual_Agents/

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.28534 2026-05-28 cs.CL 77%

GUI-CIDER: Mid-training GUI Agents via Causal Internalization and Density-aware Exemplar Reselection

GUI-CIDER:通过因果内化和密度感知示例重选进行GUI代理的中期训练

Zheng Wu, Chengcheng Han, Zhengxi Lu, Tianjie Ju, Yanyu Chen, Qi Gu, Xunliang Cai, Zhuosheng Zhang

机构 * School of Computer Science, Shanghai Jiao Tong University(上海交通大学计算机科学学院) Meituan(美团) Zhejiang University(浙江大学) The Chinese University of Hong Kong(香港中文大学)

专题命中 GUI与网页智能体 :agent(abstract);planning(abstract);multi-agent(abstract);分类 cs.CL

AI总结 提出GUI-CIDER中期训练方法,通过因果内化和密度感知示例重选显式内化GUI世界知识,提升代理对GUI操作的理解和任务成功率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.12481 2026-05-13 cs.AI 77%

ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents

ToolCUA:迈向计算机使用代理的最优GUI工具路径协调

Xuhao Hu, Xi Zhang, Haiyang Xu, Kyle Qiao, Jingyi Yang, Xuanjing Huang, Jing Shao, Ming Yan, Jieping Ye

机构 * Tongyi Lab, Alibaba Group(通义实验室,阿里巴巴集团) Fudan University(复旦大学) Shanghai Artificial Intelligence Laboratory(上海人工智能实验室)

专题命中 GUI与网页智能体 :agent(abstract);tool use(abstract);agentic(abstract);分类 cs.AI

AI总结 本文提出ToolCUA,通过分阶段训练范式学习最优GUI-工具路径选择,利用交互式轨迹缩放管道和工具引导的GUI RFT提升关键切换点决策,实验显示其在OSWorld-MCP上准确率达46.85%,优于基线模型66%,证明了有效的GUI-工具协调。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.07671 2026-05-11 cs.GT cs.AI cs.MA econ.TH math.OC 77%

The Endogeneity of Miscalibration: Impossibility and Escape in Scored Reporting

误校准的内生性:在评分报告中的不可能性与逃避

Lauri Lovén, Sasu Tarkoma

机构 * Future Computing Group, University of Oulu(未来计算组,奥卢大学) University of Oulu(奥卢大学) University of Helsinki(赫尔辛基大学)

专题命中 GUI与网页智能体 :agent(abstract);AI agent(abstract);autonomous agent(abstract);分类 cs.AI

AI总结 研究探讨了在评分报告中如何避免误校准的内生性问题,发现使用非线性批准函数可实现最优监督,但会导致诚实报告次优。提出通过阶梯状批准阈值可实现最优筛选,尤其在布里尔评分下,二阶效用等价性独特。

Comments 38 pages, no figures. Targeting ACM Transactions on Economics and Computation (TEAC); preprint

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.17420 2026-03-19 cs.AI 77%

From Digital Twins to World Models:Opportunities, Challenges, and Applications for Mobile Edge General Intelligence

从数字孪生到世界模型:移动边缘通用智能的机会、挑战与应用

Jie Zheng, Dusit Niyato, Changyuan Zhao, Jiawen Kang, Jiacheng Wang

机构 * State-Province Joint Engineering and Research Center of Advanced Networking and Intelligent Information Services, College of Computer, Northwest University(高级网络与智能信息服务省州联合工程研究中心,计算机学院,西北大学) College of Computing and Data Science, Nanyang Technological University(计算与数据科学学院,南洋理工大学) Automation of School, Guangdong University of Technology(自动化学院,广东工业大学)

专题命中 GUI与网页智能体 :agent(abstract);planning(abstract);agentic(abstract);分类 cs.AI

AI总结 本文探讨了从数字孪生到世界模型的转变,分析了其在移动边缘通用智能中的作用,涵盖概念差异、设计原则、关键组件及应用挑战。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.10814 2026-02-12 cs.AI 77%

See, Plan, Snap: Evaluating Multimodal GUI Agents in Scratch

见、计划、快照:评估Scratch中的多模态GUI代理

Xingyi Zhang, Yulei Ye, Kaifeng Huang, Wenhao Li, Xiangfeng Wang

机构 * Tongji University(同济大学) East China Normal University(华东师范大学)

专题命中 GUI与网页智能体 :agent(abstract);AI agent(abstract);planning(abstract);分类 cs.AI

AI总结 本文提出ScratchWorld基准,用于评估多模态GUI代理在Scratch中的程序构建能力,揭示了推理与执行之间的显著差距。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.10046 2026-01-27 cs.AI 77%

SimWorld-Robotics: Synthesizing Photorealistic and Dynamic Urban Environments for Multimodal Robot Navigation and Collaboration

SimWorld-Robotics: 为多模态机器人导航与协作合成逼真动态城市环境

Yan Zhuang, Jiawei Ren, Xiaokang Ye, Jianzhi Shen, Ruixuan Zhang, Tianai Yue, Muhammad Faayez, Xuhong He, Ziqiao Ma, Lianhui Qin, Zhiting Hu, Tianmin Shu

机构 * University of Virginia(弗吉尼亚大学) UC San Diego(加州大学圣地亚哥分校) Johns Hopkins University(约翰霍普金斯大学) Carnegie Mellon University(卡内基梅隆大学) University of Michigan(密歇根大学)

专题命中 GUI与网页智能体 :agent(abstract);planning(abstract);multi-agent(abstract);分类 cs.AI

AI总结 SimWorld-Robotics通过合成逼真动态城市环境,提出两个多模态机器人基准测试,评估机器人在复杂场景中的导航、协作与通信能力。

Comments Conference: NeurIPS 2025 (main)

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.04500 2026-01-09 cs.AI 77%

GUITester: Enabling GUI Agents for Exploratory Defect Discovery

GUITester: 使GUI代理用于探索性缺陷发现

Yifei Gao, Jiang Wu, Xiaoyi Chen, Yifan Yang, Zhe Cui, Tianyi Ma, Jiaming Zhang, Jitao Sang

机构 * Beijing Jiaotong University(北京交通大学) Hithink Research(慧思科技) Nanyang Technological University(南洋理工大学)

专题命中 GUI与网页智能体 :agent(abstract);planning(abstract);multi-agent(abstract);分类 cs.AI

AI总结 GUITester通过解耦导航与验证的多代理框架,有效解决了探索性GUI测试中目标导向遮蔽和执行偏差归因的问题,实现了48.90%的F1分数。

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.20425 2025-09-03 cs.AI cs.RO 77%

Perspective-Shifted Neuro-Symbolic World Models: A Framework for Socially-Aware Robot Navigation

Kevin Alcedo, Pedro U. Lima, Rachid Alami

机构 * Institute for Systems and Robotics, Instituto Superior Técnico, Universidade de Lisboa(系统机器人研究所,理工学院,里斯本大学) LAAS-CNRS, Artificial and Natural Intelligence Toulouse Institute (ANITI)(LAAS-CNRS,图卢兹人工智能研究所(ANITI))

专题命中 GUI与网页智能体 :agent(abstract);planning(abstract);multi-agent(abstract);分类 cs.AI

Comments Accepted as a regular paper at the 2025 IEEE International Conference on Robot & Human Interactive Communication (RO-MAN). \c{opyright} 2025 IEEE. The final version will appear in IEEE Xplore

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.16987 2025-08-26 cs.AI cs.CV 77%

WebSight: A Vision-First Architecture for Robust Web Agents

Tanvir Bhathal, Asanshay Gupta

机构 * Stanford University(斯坦福大学)

专题命中 GUI与网页智能体 :agent(abstract);planning(abstract);multi-agent(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.20850 2025-07-29 cs.RO cs.AI 77%

Free Energy-Inspired Cognitive Risk Integration for AV Navigation in Pedestrian-Rich Environments

Meiting Dang, Yanping Wu, Yafei Wang, Dezong Zhao, David Flynn, Chongfeng Wei

专题命中 GUI与网页智能体 :agent(abstract);planning(abstract);multi-agent(abstract);分类 cs.AI

Comments 14 pages, 5 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.12981 2025-05-21 cs.CR cs.AI cs.HC 77%

From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents

Liangxuan Wu, Chao Wang, Tianming Liu, Yanjie Zhao, Haoyu Wang

机构 * Huazhong University of Science and Technology(华中科技大学)

专题命中 GUI与网页智能体 :agent(abstract);AI agent(abstract);workflow(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2307.09206 2024-10-08 cs.RO cs.LG 77%

Context-Conditional Navigation with a Learning-Based Terrain- and Robot-Aware Dynamics Model

Suresh Guttikonda, Jan Achterhold, Haolong Li, Joschka Boedecker, Joerg Stueckler

专题命中 GUI与网页智能体 :agent(abstract);autonomous agent(abstract);planning(abstract);分类 cs.LG

Comments ©2023 IEEE. Accepted for publication in European Conference on Mobile Robots (ECMR), 2023. Version including corrections (see p. 8)

详情

展开后加载摘要…

URL PDF HTML 收藏
2407.00632 2024-07-02 cs.RO cs.CL cs.CV cs.MA 77%

CAMON: Cooperative Agents for Multi-Object Navigation with LLM-based Conversations

Pengying Wu, Yao Mu, Kangjie Zhou, Ji Ma, Junting Chen, Chang Liu

专题命中 GUI与网页智能体 :agent(abstract);planning(abstract);multi-agent(abstract);分类 cs.CL

Comments Accepted to the RSS 2024 Workshop: GROUND

详情

展开后加载摘要…

URL PDF HTML 收藏
2401.17914 2024-02-01 cs.RO cs.AI 77%

Attention Graph for Multi-Robot Social Navigation with Deep Reinforcement Learning

Erwan Escudie, Laetitia Matignon, Jacques Saraydaryan

专题命中 GUI与网页智能体 :agent(abstract);planning(abstract);multi-agent(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏