AI Agent - arXivDaily 专题

2512.00027 2025-12-02 cs.RO cs.AI cs.CV cs.HC 70%

A Survey on Improving Human Robot Collaboration through Vision-and-Language Navigation

通过视觉-语言导航提升人机协作的综述

Nivedan Yakolli, Avinash Gautam, Abhijit Das, Yuankai Qi, Virendra Singh Shekhawat

机构 * Birla Institute of Technology and Science (BITS)（比拉理工学院和科学学院）； Macquarie University（麦考瑞大学）

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

AI总结本文综述了视觉-语言导航在提升人机协作中的最新进展，探讨了多机器人协作中的关键挑战，并提出通过先进NLU技术实现主动澄清和动态角色分配的未来方向。

2511.13087 2025-11-18 cs.AI cs.CV 70%

MEGA-GUI: Multi-stage Enhanced Grounding Agents for GUI Elements

SeokJoo Kwak, Jihoon Kim, Boyoun Kim, Jung Jae Yoon, Wooseok Jang, Jeonghoon Hong, Jaeho Yang, Yeong-Dae Kwon

机构 * Samsung SDS（三星SDS）

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

Comments 26 pages, 7 figures. Code available at https://github.com/samsungsds-research-papers/mega-gui

2511.04481 2025-11-07 cs.AI 70%

Promoting Sustainable Web Agents: Benchmarking and Estimating Energy Consumption through Empirical and Theoretical Analysis

Lars Krupp, Daniel Geißler, Vishal Banwari, Paul Lukowicz, Jakob Karolus

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

Comments Accepted by AAAI 2026 AISI

2506.05079 2025-11-03 cs.SE 70%

LLM-Guided Scenario-based GUI Testing

Shengcheng Yu, Yuchen Ling, Chunrong Fang, Quan Zhou, Yi Zhao, Chunyang Chen, Shaomin Zhu, Zhenyu Chen

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

2509.25047 2025-09-30 cs.AI 70%

Scaling Synthetic Task Generation for Agents via Exploration

Ram Ramrakhya, Andrew Szot, Omar Attia, Yuhao Yang, Anh Nguyen, Bogdan Mazoure, Zhe Gan, Harsh Agrawal, Alexander Toshev

机构 * Apple（苹果公司）

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

2504.15917 2025-09-12 cs.SE 70%

Towards Test Generation from Task Description for Mobile Testing with Multi-modal Reasoning

Hieu Huynh, Hai Phung, Hao Pham, Tien N. Nguyen, Vu Nguyen

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

Comments Change the method and experimentation

2407.17490 2025-08-15 cs.HC cs.AI cs.MM 70%

AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agents

Yuxiang Chai, Siyuan Huang, Yazhe Niu, Han Xiao, Liang Liu, Dingyu Zhang, Shuai Ren, Hongsheng Li

机构 * SJTU（上海交通大学）； vivo AI Lab（vivo人工智能实验室）

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

2412.16256 2025-07-09 cs.HC cs.AI 70%

Aria-UI: Visual Grounding for GUI Instructions

Yuhao Yang, Yue Wang, Dongxu Li, Ziyang Luo, Bei Chen, Chao Huang, Junnan Li

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

Comments ACL 2025

2409.10048 2025-06-24 cs.SD cs.AI eess.AS 70%

Audio-Driven Reinforcement Learning for Head-Orientation in Naturalistic Environments

Wessel Ledder, Yuzhen Qin, Kiki van der Heijden

机构 * Radboud University（拉德堡德大学）； Donders Institute（多纳德研究所）

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

Comments Accepted at ICASSP 2025

Journal ref Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), pp. 1-5, 2025

2506.17318 2025-06-24 cs.CR cs.AI 70%

Context manipulation attacks : Web agents are susceptible to corrupted memory

Atharv Singh Patlan, Ashwin Hebbar, Pramod Viswanath, Prateek Mittal

机构 * princeton（普林斯顿大学）

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

Comments 10 pages, 6 figures

2505.17500 2025-05-26 cond-mat.soft cs.AI 70%

The Discovery Engine: A Framework for AI-Driven Synthesis and Navigation of Scientific Knowledge Landscapes

Vladimir Baulin, Austin Cook, Daniel Friedman, Janna Lumiruusu, Andrew Pashea, Shagor Rahman, Benedikt Waldeck

机构 * Active Inference Institute（主动推断研究所）； Universitat Rovira i Virgili（罗维拉-维格利大学）

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

2505.14963 2025-05-22 cs.CL 70%

MedBrowseComp: Benchmarking Medical Deep Research and Computer Use

Shan Chen, Pedro Moreira, Yuxin Xiao, Sam Schmidgall, Jeremy Warner, Hugo Aerts, Thomas Hartvigsen, Jack Gallifant, Danielle S. Bitterman

机构 * Harvard（哈佛大学）； Mass General Brigham（麻省总医院）； Boston Children’s Hospital（波士顿儿童医院）； MIT（麻省理工学院）； Universitat Pompeu Fabra（庞培法华大学）； Johns Hopkins University（约翰霍普金斯大学）； Brown University（布朗大学）； Maastricht University（马斯特里赫特大学）； University of Virginia（弗吉尼亚大学）

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

Comments You can visit our project page at: https://moreirap12.github.io/mbc-browse-app/

2504.13936 2025-05-21 cs.HC cs.LG cs.SY eess.SY 70%

ViMo: A Generative Visual GUI World Model for App Agents

Dezhao Luo, Bohan Tang, Kang Li, Georgios Papoudakis, Jifei Song, Shaogang Gong, Jianye Hao, Jun Wang, Kun Shao

机构 * Queen Mary University of London（伦敦女王学院）； University of Oxford（牛津大学）； Huawei Noah’s Ark Lab（华为诺亚实验室）； University College London（伦敦大学学院）

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

Comments https://ai-agents-2030.github.io/ViMo/

2505.09427 2025-05-16 cs.LG cs.RO 70%

SafePath: Conformal Prediction for Safe LLM-Based Autonomous Navigation

Achref Doula, Max Mühlhäuser, Alejandro Sanchez Guinea

机构 * Technical University of Darmstadt（德累斯顿技术大学）； NTT Data（NTT数据）

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

2504.20464 2025-05-14 cs.AI 70%

A Survey on GUI Agents with Foundation Models Enhanced by Reinforcement Learning

Jiahao Li, Kaer Huang

机构 * Lenovo Research（联想研究院）

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

2412.04454 2025-05-06 cs.CL 70%

Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction

Yiheng Xu, Zekun Wang, Junli Wang, Dunjie Lu, Tianbao Xie, Amrita Saha, Doyen Sahoo, Tao Yu, Caiming Xiong

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

Comments ICML 2025

2505.00416 2025-05-02 cs.AI 70%

ScaleTrack: Scaling and back-tracking Automated GUI Agents

Jing Huang, Zhixiong Zeng, Wenkang Han, Yufeng Zhong, Liming Zheng, Shuai Fu, Jingyuan Chen, Lin Ma

机构 * Meituan（美团）； Zhejiang University（浙江大学）； University of Adelaide（阿德莱德大学）

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

2504.17526 2025-04-25 cs.LG 70%

Cooperative Task Offloading through Asynchronous Deep Reinforcement Learning in Mobile Edge Computing for Future Networks

Yuelin Liu, Haiyuan Li, Xenofon Vasilakos, Rasheed Hussain, Dimitra Simeonidou

机构 * High Performance Networks (HPN) Research Group, Smart Internet Lab, University of Bristol（布里斯托大学智能互联网实验室）

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

2410.13232 2025-04-01 cs.CL 70%

Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation

Hyungjoo Chae, Namyoung Kim, Kai Tzu-iunn Ong, Minju Gwak, Gwanwoo Song, Jihoon Kim, Sunghwan Kim, Dongha Lee, Jinyoung Yeo

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

Comments ICLR 2025

2503.21141 2025-03-31 cs.RO cs.LG cs.MA 70%

Safe Human Robot Navigation in Warehouse Scenario

Seth Farrell, Chenghao Li, Hongzhan Yu, Ryo Yoshimitsu, Sicun Gao, Henrik I. Christensen

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

2502.16690 2025-02-25 cs.AI 70%

From Text to Space: Mapping Abstract Spatial Models in LLMs during a Grid-World Navigation Task

Nicolas Martorell

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

2412.13693 2025-02-06 cs.SE 70%

UITrans: Seamless UI Translation from Android to HarmonyOS

Lina Gong, Chen Wang, Yujun Huang, Di Cui, Mingqiang Wei

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

Comments 5 pages

2402.12498 2024-12-16 cs.CV cs.LG cs.RO 70%

Feudal Networks for Visual Navigation

Faith Johnson, Bryan Bo Cao, Ashwin Ashok, Shubham Jain, Kristin Dana

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

2412.05445 2024-12-12 cs.HC cs.AI 70%

From Voice to Value: Leveraging AI to Enhance Spoken Online Reviews on the Go

Kavindu Ravishan, Dániel Szabó, Niels van Berkel, Aku Visuri, Chi-Lan Yang, Koji Yatani, Simo Hosio

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

Comments \c{opyright} Kavindu Ravishan | ACM 2024. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in the Proceedings of the ACM Conference on Mobile and Ubiquitous Multimedia (MUM '24), http://dx.doi.org/10.1145/3701571.3701593

Journal ref International Conference on Mobile and Ubiquitous Multimedia MUM '24, December 1-4, 2024, Stockholm, Sweden

2412.06313 2024-12-10 cs.RO cs.CV cs.LG 70%

Vision-Based Deep Reinforcement Learning of UAV Autonomous Navigation Using Privileged Information

Junqiao Wang, Zhongliang Yu, Dong Zhou, Jiaqi Shi, Runran Deng

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

Comments 19 pages, 9 figures

2407.03037 2024-12-05 cs.SE 70%

Seeing is Believing: Vision-driven Non-crash Functional Bug Detection for Mobile Apps

Zhe Liu, Cheng Li, Chunyang Chen, Junjie Wang, Mengzhuo Chen, Boyu Wu, Yawen Wang, Jun Hu, Qing Wang

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

2410.19461 2024-11-05 cs.AI 70%

EDGE: Enhanced Grounded GUI Understanding with Enriched Multi-Granularity Synthetic Data

Xuetian Chen, Hangcheng Li, Jiaqing Liang, Sihang Jiang, Deqing Yang

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

2410.13886 2024-10-23 cs.CR cs.LG 70%

Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents

Priyanshu Kumar, Elaine Lau, Saranya Vijayakumar, Tu Trinh, Scale Red Team, Elaine Chang, Vaughn Robinson, Sean Hendryx, Shuyan Zhou, Matt Fredrikson, Summer Yue, Zifan Wang

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

2409.17922 2024-09-27 cs.AI 70%

Navigation in a simplified Urban Flow through Deep Reinforcement Learning

Federica Tonti, Jean Rabault, Ricardo Vinuesa

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

2407.08474 2024-07-12 cs.HC cs.SE 70%

DIDUP: Dynamic Iterative Development for UI Prototyping

Jenny Ma, Karthik Sreedhar, Vivian Liu, Sitong Wang, Pedro Alejandro Perez, Lydia B. Chilton

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

Comments 5 pages, 3 figures

1. GUI与网页智能体 2971 篇

A Survey on Improving Human Robot Collaboration through Vision-and-Language Navigation

MEGA-GUI: Multi-stage Enhanced Grounding Agents for GUI Elements

Promoting Sustainable Web Agents: Benchmarking and Estimating Energy Consumption through Empirical and Theoretical Analysis

LLM-Guided Scenario-based GUI Testing

Scaling Synthetic Task Generation for Agents via Exploration

Towards Test Generation from Task Description for Mobile Testing with Multi-modal Reasoning

AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agents

Aria-UI: Visual Grounding for GUI Instructions

Audio-Driven Reinforcement Learning for Head-Orientation in Naturalistic Environments

Context manipulation attacks : Web agents are susceptible to corrupted memory

The Discovery Engine: A Framework for AI-Driven Synthesis and Navigation of Scientific Knowledge Landscapes

MedBrowseComp: Benchmarking Medical Deep Research and Computer Use

ViMo: A Generative Visual GUI World Model for App Agents

SafePath: Conformal Prediction for Safe LLM-Based Autonomous Navigation

A Survey on GUI Agents with Foundation Models Enhanced by Reinforcement Learning

Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction

ScaleTrack: Scaling and back-tracking Automated GUI Agents

Cooperative Task Offloading through Asynchronous Deep Reinforcement Learning in Mobile Edge Computing for Future Networks

Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation

Safe Human Robot Navigation in Warehouse Scenario

From Text to Space: Mapping Abstract Spatial Models in LLMs during a Grid-World Navigation Task

UITrans: Seamless UI Translation from Android to HarmonyOS

Feudal Networks for Visual Navigation

From Voice to Value: Leveraging AI to Enhance Spoken Online Reviews on the Go

Vision-Based Deep Reinforcement Learning of UAV Autonomous Navigation Using Privileged Information

Seeing is Believing: Vision-driven Non-crash Functional Bug Detection for Mobile Apps

EDGE: Enhanced Grounded GUI Understanding with Enriched Multi-Granularity Synthetic Data

Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents

Navigation in a simplified Urban Flow through Deep Reinforcement Learning

DIDUP: Dynamic Iterative Development for UI Prototyping