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。

2026-05-12 至 2026-05-12 共收录 8 信号源:cs.AI, cs.CL, cs.LG, cs.SE

1. GUI与网页智能体 8 篇

2605.08124 2026-05-12 cs.DC cs.CL cs.MA cs.NI 83%

Scaling Mobile Agent Systems: From Capability Density to Collective Intelligence

扩展移动代理系统:从能力密度到集体智能

Bowei He

机构 * Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)

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

AI总结 本文提出通过紧凑基础模型设计与压缩提升单个代理能力密度,并通过通信丰富的多代理协作实现集体智能,以解决移动代理系统的扩展性问题。

Comments Accepted by ACM MobiSys 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.09317 2026-05-12 cs.CL cs.CV cs.LG 62%

Mem-W: Latent Memory-Native GUI Agents

Mem-W: 基于潜在记忆的原生GUI代理

Guibin Zhang, Yaohui Ling, Fanci Meng, Kun Wang, Shuicheng Yan

机构 * LV-NUS Lab(LV-NUS实验室)

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

AI总结 Mem-W通过将记忆作为连续上下文的一部分,改进GUI代理的长期任务执行能力,实验证明其在多个导航基准测试中提升了性能,最高提升达+30.0。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.24954 2026-05-12 cs.LG cs.AI cs.CV 62%

Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence

Nemotron 3 Nano Omni:高效且开放的多模态智能

NVIDIA, :, Amala Sanjay Deshmukh, Kateryna Chumachenko, Tuomas Rintamaki, Matthieu Le, Tyler Poon, Danial Mohseni Taheri, Ilia Karmanov, Guilin Liu, Jarno Seppanen, Arushi Goel, Mike Ranzinger, Greg Heinrich, Guo Chen, Lukas Voegtle, Philipp Fischer, Timo Roman, Karan Sapra, Collin McCarthy, Shaokun Zhang, Fuxiao Liu, Hanrong Ye, Yi Dong, Mingjie Liu, Yifan Peng, Piotr Zelasko, Zhehuai Chen, Nithin Rao Koluguri, Nune Tadevosyan, Lilit Grigoryan, Ehsan Hosseini Asl, Pritam Biswas, Leili Tavabi, Yuanhang Su, Zhiding Yu, Peter Jin, Alexandre Milesi, Netanel Haber, Yao Xu, Sarah Amiraslani, Nabin Mulepati, Eric Tramel, Jaehun Jung, Ximing Lu, Brandon Cui, Jin Xu, Zhiqi Li, Shihao Wang, Yuanguo Kuang, Shaokun Zhang, Huck Yang, Boyi Li, Hongxu Yin, Song Han, Bilal Kartal, Pavlo Molchanov, Adi Renduchintala, Charles Wang, David Mosallanezhad, Soumye Singhal, Luis Vega, Katherine Cheung, Sreyan Ghosh, Yian Zhang, Alexander Bukharin, Venkat Srinivasan, Johnny Greco, Andre Manoel, Maarten Van Segbroeck, Suseella Panguliri, Rohit Watve, Divyanshu Kakwani, Shubham Pachori, Jeffrey Glick, Radha Sri-Tharan, Aileen Zaman, Khanh Nguyen, Shi Chen, Jiaheng Fang, Qing Miao, Wenfei Zhou, Yu Wang, Zaid Pervaiz Bhat, Varun Praveen, Arihant Jain, Ramanathan Arunachalam, Tomasz Kornuta, Ashton Sharabiani, Amy Shen, Wei Huang, Yi-Fu Wu, Ali Roshan Ghias, Huiying Li, Brian Yu, Nima Tajbakhsh, Chen Cui, Wenwen Gao, Li Ding, Terry Kong, Manoj Kilaru, Anahita Bhiwandiwalla, Marek Wawrzos, Daniel Korzekwa, Pablo Ribalta, Grzegorz Chlebus, Besmira Nushi, Ewa Dobrowolska, Maciej Jakub Mikulski, Kunal Dhawan, Steve Huang, Jagadeesh Balam, Yongqiang Wang, Nikolay Karpov, Valentin Mendelev, George Zelenfroynd, Meline Mkrtchyan, Qing Miao, Omri Almog, Bhavesh Pawar, Rameshwar Shivbhakta, Sudeep Sabnis, Ashrton Sharabiani, Negar Habibi, Geethapriya Venkataramani, Pamela Peng, Prerit Rodney, Serge Panev, Richard Mazzarese, Nicky Liu, Michael Fukuyama, Andrii Skliar, Roger Waleffe, Duncan Riach, Yunheng Zou, Jian Hu, Hao Zhang, Binfeng Xu, Yuhao Yang, Zuhair Ahmed, Alexandre Milesi, Carlo del Mundo, Chad Voegele, Zhiyu Cheng, Nave Assaf, Andrii Skliar, Daniel Afrimi, Natan Bagrov, Ran Zilberstein, Ofri Masad, Eugene Khvedchenia, Natan Bagrov, Borys Tymchenko, Tomer Asida, Daniel Afrimi, Parth Mannan, Victor Cui, Michael Evans, Katherine Luna, Jie Lou, Pinky Xu, Guyue Huang, Negar Habibi, Michael Boone, Pradeep Thalasta, Adeola Adesoba, Dina Yared, Christopher Parisien, Leon Derczynski, Shaona Ghosh, Wes Feely, Micah Schaffer, Radha Sri-Tharan, Jeffrey Glick, Barnaby Simkin, George Zelenfroynd, Tomasz Grzegorzek, Rishabh Garg, Aastha Jhunjhunwala, Sergei Kolchenko, Farzan Memarian, Haran Kumar, Shiv Kumar, Isabel Hulseman, Anjali Shah, Kari Briski, Padmavathy Subramanian, Joey Conway, Udi Karpas, Jane Polak Scowcroft, Annie Surla, Shilpa Ammireddy, Ellie Evans, Jesse Oliver, Tom Balough, Chia-Chih Chen, Sandip Bhaskar, Alejandra Rico, Bardiya Sadeghi, Seph Mard, Katherine Cheung, Meredith Price, Laya Sleiman, Saori Kaji, Wesley Helmholz, Wendy Quan, Michael Lightstone, Jonathan Cohen, Jian Zhang, Oleksii Kuchaiev, Boris Ginsburg, Jan Kautz, Eileen Long, Mohammad Shoeybi, Mostofa Patwary, Oluwatobi Olabiyi, Andrew Tao, Bryan Catanzaro, Udi Karpas

机构 * NVIDIA

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

AI总结 Nemotron 3 Nano Omni是首个原生支持音频输入的多模态模型,通过架构、数据和训练方法的改进,在所有模态上均实现了更准确的性能,同时提供更低的推理延迟和更高的吞吐量。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.08261 2026-05-12 cs.SE cs.AI 62%

Computer Use at the Edge of the Statistical Precipice

在统计悬崖边缘的计算机使用

Pierluca D'Oro, Sneha Silwal, William Wong, Yuxuan Sun, Fanyi Xiao, Manchen Wang, Eric Gan, Allen Bolourchi, Joseph Tighe

机构 * Meta Superintelligence Labs(Meta超智能实验室)

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

AI总结 本文指出现有交互环境评估方法存在系统性缺陷,提出PRISM原则设计更真实的环境,并开发新的聚合框架以提升CUA评估的准确性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.09497 2026-05-12 cs.AI cs.CR 57%

Don't Click That: Teaching Web Agents to Resist Deceptive Interfaces

别点那个:教网络代理抵抗欺骗界面

Yilin Zhang, Yingkai Hua, Chunyu Wei, Xin Wang, Yueguo Chen

机构 * Renmin University of China(中国人民大学) Ant Digital Technologies, Ant Group(蚂蚁集团数字技术部)

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

AI总结 本文提出DUDE框架,通过混合奖励学习和不对称惩罚,结合经验总结,提升网络代理对欺骗界面的抵抗力,实验显示欺骗敏感度降低53.8%。

Comments Accepted to ACL 2026 Main Conference. 23 pages, 8 figures, 19 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.11604 2026-05-12 cs.CL 57%

Talk to Your Slides: High-Efficiency Slide Editing via Language-Driven Structured Data Manipulation

与幻灯片对话:通过语言驱动的结构化数据操作实现高效幻灯片编辑

Kyudan Jung, Hojun Cho, Jooyeol Yun, Soyoung Yang, Jaehyeok Jang, Jaegul Choo

机构 * KAIST AI(韩国科学技术院人工智能研究所) Chung-Ang University(Chung-Ang 大学)

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

AI总结 本文提出Talk-to-Your-Slides,通过语言驱动的结构化数据操作实现高效幻灯片编辑,相较于基于图像的GUI方法,其在文本处理和格式任务中更快、更准确且成本更低。

Comments 30 pages, Accepted at ACL2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.08310 2026-05-12 cs.CR cs.AI 57%

WebTrap: Stealthy Mid-Task Hijacking of Browser Agents During Navigation

WebTrap: 隐秘的中任务劫持攻击浏览器代理在导航过程中的行为

Zhichao Liu, Wenbo Pan, Haining Yu, Ge Gao, Tianqing Zhu, Xiaohua Jia

机构 * Harbin Institute of Technology(哈尔滨工业大学) City University of Hong Kong(香港城市大学) City University of Macau(澳门城市大学)

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

AI总结 WebTrap通过多步骤指令融合引导实现浏览器代理在导航任务中的隐秘劫持,提升攻击成功率同时保持系统可用性。

Comments 31 pages, 4 figures, 10 tables. Code: https://github.com/liuyaojialiuyaojia/WebTrap

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.10440 2026-05-12 cs.CY 50%

TourMart: A Parametric Audit Instrument for Commission Steering in LLM Travel Agents

TourMart: 一种用于LLM旅行代理佣金管理的参数审计工具

Yao Liu

专题命中 GUI与网页智能体 :agent(abstract)

AI总结 TourMart通过参数lambda和kappa驱动反事实分析,区分LLM工程故障与真实商业引导,验证代理引导效果,输出合规报告。

详情

展开后加载摘要…

URL PDF HTML 收藏