UFO2: The Desktop AgentOS

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Chaoyun, Huang, He, Ni, Chiming, Mu, Jian, Qin, Si, He, Shilin, Wang, Lu, Yang, Fangkai, Zhao, Pu, Du, Chao, Li, Liqun, Kang, Yu, Jiang, Zhao, Zheng, Suzhen, Wang, Rujia, Qian, Jiaxu, Ma, Minghua, Lou, Jian-Guang, Lin, Qingwei, Rajmohan, Saravan, Zhang, Dongmei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917998490550272
author Zhang, Chaoyun
Huang, He
Ni, Chiming
Mu, Jian
Qin, Si
He, Shilin
Wang, Lu
Yang, Fangkai
Zhao, Pu
Du, Chao
Li, Liqun
Kang, Yu
Jiang, Zhao
Zheng, Suzhen
Wang, Rujia
Qian, Jiaxu
Ma, Minghua
Lou, Jian-Guang
Lin, Qingwei
Rajmohan, Saravan
Zhang, Dongmei
author_facet Zhang, Chaoyun
Huang, He
Ni, Chiming
Mu, Jian
Qin, Si
He, Shilin
Wang, Lu
Yang, Fangkai
Zhao, Pu
Du, Chao
Li, Liqun
Kang, Yu
Jiang, Zhao
Zheng, Suzhen
Wang, Rujia
Qian, Jiaxu
Ma, Minghua
Lou, Jian-Guang
Lin, Qingwei
Rajmohan, Saravan
Zhang, Dongmei
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2504_14603
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle UFO2: The Desktop AgentOS
Zhang, Chaoyun
Huang, He
Ni, Chiming
Mu, Jian
Qin, Si
He, Shilin
Wang, Lu
Yang, Fangkai
Zhao, Pu
Du, Chao
Li, Liqun
Kang, Yu
Jiang, Zhao
Zheng, Suzhen
Wang, Rujia
Qian, Jiaxu
Ma, Minghua
Lou, Jian-Guang
Lin, Qingwei
Rajmohan, Saravan
Zhang, Dongmei
Artificial Intelligence
Human-Computer Interaction
Operating Systems
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.
title UFO2: The Desktop AgentOS
topic Artificial Intelligence
Human-Computer Interaction
Operating Systems
url https://arxiv.org/abs/2504.14603