不只是成败，考虑操作路径长度的对比学习，教你训练更智能的GUI代理，研究角度新颖。
arXiv:2608.21830v1 Announce Type: new Abstract: Graphical User Interface (GUI) agents powered by Multimodal Large Language Models (MLLMs) have shown s…
小米发布新一代GUI智能体，解锁跨应用真实操作！技术报告详解模型能力，必读干货。
arXiv:2606.31410v1 Announce Type: new Abstract: Graphical user interface (GUI) agents build on vision-language models to complete user tasks end-to-en…
传统验证码已失效，新研究用认知差距设计下一代验证码，专防GUI智能体，看点十足。
arXiv:2602.09012v2 Announce Type: replace-cross Abstract: The rapid evolution of GUI-enabled agents has rendered traditional CAPTCHAs obsolete. While …