paper-with-me

홈 › Papers

UFO2: The Desktop AgentOS

2025-04-20 · 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

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.

📄 PDF Abstract BibTeX arXiv:2504.14603

Code (1)

microsoft/UFO 공식 구현

Similar Papers 제목 키워드 기반

AgentOS: From Application Silos to a Natural Language-Driven Data Ecosystem

2026-03-09 · Rui Liu, Tao Zhe, Dongjie Wang, Zijun Yao 외 arxiv

The rapid emergence of open-source, locally hosted intelligent agents marks a critical inflection point in human-computer interaction. Systems such as OpenClaw demonstrate that Large Language Model (LLM)-based agents can…

Sequential Pattern MiningKnowledge Graphs

ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory

2026-07-11 · Jiayi Tian, Shiao Liu, Yuting Xu, Jia Lu 외 arxiv

Recent VLM and VLA systems have improved robotic perception and action prediction, yet long-horizon embodied agents still require a general runtime layer for reasoning, memory, tool use, verification, and cross-embodimen…

HoloAgent-0: A Unified Embodied Agent Framework with 3D Spatial Memory

2026-06-22 · Xiaolin Zhou, Liu Liu, Tingyang Xiao, Wei Feng 외 arxiv

LLM agents follow a practical execution loop in digital environments: they reason over structured states, invoke tools, inspect feedback, and revise actions. Extending this loop to physical robots is difficult because ph…

Architecting AgentOS: From Token-Level Context to Emergent System-Level Intelligence

2026-02-24 · ChengYou Li, XiaoDong Liu, XiangBao Meng, XinYu Zhao arxiv

The paradigm of Large Language Models is undergoing a fundamental transition from static inference engines to dynamic autonomous cognitive systems.While current research primarily focuses on scaling context windows or op…

Prompt Engineering

D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI

2025-10-07 · Suhwan Choi, Jaeyoon Jung, Haebin Seong, Minchan Kim 외 arxiv

Large language models leverage internet-scale text data, yet embodied AI remains constrained by the prohibitive costs of physical trajectory collection. Desktop environments -- particularly gaming -- offer a compelling a…

Zero-shot Generalization