UFO2：桌面代理操作系统

UFO2: The Desktop AgentOS

April 20, 2025

作者: Chaoyun Zhang, He Huang, Chiming Ni, Jian Mu, Si Qin, Shilin He, Lu Wang, Fangkai Yang, Pu Zhao, Chao Du, Liqun Li, Yu Kang, Zhao Jiang, Suzhen Zheng, Rujia Wang, Jiaxu Qian, Minghua Ma, Jian-Guang Lou, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang

cs.AI

摘要

近期，由多模态大语言模型（LLMs）驱动的计算机使用代理（CUAs）为通过自然语言自动化复杂桌面工作流提供了有前景的方向。然而，大多数现有的CUAs仍停留在概念原型阶段，受限于浅层次的操作系统集成、基于截图的脆弱交互以及中断式的执行。 我们推出了UFO2，一个面向Windows桌面的多代理操作系统，它将CUAs提升至实用、系统级的自动化水平。UFO2的核心是一个集中式的HostAgent，负责任务分解与协调，同时配备了一系列专为应用程序设计的AppAgent，这些AppAgent拥有原生API、领域特定知识以及统一的GUI-API操作层。这一架构在保持模块化和可扩展性的同时，实现了稳健的任务执行。通过融合Windows UI Automation (UIA)与基于视觉的解析，混合控制检测管道支持多样化的界面风格。运行时效率通过推测性多动作规划得到进一步提升，减少了每一步的LLM开销。最后，画中画（PiP）界面使得自动化能在隔离的虚拟桌面内进行，允许代理与用户并行操作，互不干扰。 我们在超过20个实际Windows应用程序中对UFO2进行了评估，结果显示其在鲁棒性和执行准确性上相较于先前的CUAs有显著提升。我们的成果表明，深度的操作系统集成为实现可靠、用户导向的桌面自动化开辟了一条可扩展的道路。

English

Recent Computer-Using Agents (CUAs), powered by multimodal large language models (LLMs), offer a promising direction for automating complex desktop workflows through natural language. However, most existing CUAs remain conceptual prototypes, hindered by shallow OS integration, fragile screenshot-based interaction, and disruptive execution. We present UFO2, a multiagent AgentOS for Windows desktops that elevates CUAs into practical, system-level automation. UFO2 features a centralized HostAgent for task decomposition and coordination, alongside a collection of application-specialized AppAgent equipped with native APIs, domain-specific knowledge, and a unified GUI--API action layer. This architecture enables robust task execution while preserving modularity and extensibility. A hybrid control detection pipeline fuses Windows UI Automation (UIA) with vision-based parsing to support diverse interface styles. Runtime efficiency is further enhanced through speculative multi-action planning, reducing per-step LLM overhead. Finally, a Picture-in-Picture (PiP) interface enables automation within an isolated virtual desktop, allowing agents and users to operate concurrently without interference. We evaluate UFO2 across over 20 real-world Windows applications, demonstrating substantial improvements in robustness and execution accuracy over prior CUAs. Our results show that deep OS integration unlocks a scalable path toward reliable, user-aligned desktop automation.