@inproceedings{zhang-etal-2025-ufo,
title = "{UFO}: A {UI}-Focused Agent for Windows {OS} Interaction",
author = "Zhang, Chaoyun and
Li, Liqun and
He, Shilin and
Zhang, Xu and
Qiao, Bo and
Qin, Si and
Ma, Minghua and
Kang, Yu and
Lin, Qingwei and
Rajmohan, Saravan and
Zhang, Dongmei and
Zhang, Qi",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.26/",
doi = "10.18653/v1/2025.naacl-long.26",
pages = "597--622",
ISBN = "979-8-89176-189-6",
abstract = "We introduce UFO, a UI-Fcused agent designed to fulfill user requests tailored to Windows OS applications by observing and analyzing the GUI and control information of these applications. UFO utilizes a hierarchical dual-agent framework that decomposes user requests using a divide-and-conquer approach, enabling seamless navigation and addressing sub-tasks across multiple applications. It also incorporates a control interaction module tailored for Windows OS, which detects control elements effectively and allows for fully automated execution. As a result, UFO simplifies complex and time-consuming processes into tasks that can be completed with natural language commands.We conducted testing of UFO across 9 popular Windows applications, encompassing a variety of scenarios. The results derived from both quantitative metrics and real-case studies, underscore the superior effectiveness of UFOin fulfilling user requests. To the best of our knowledge, UFO stands as the first UI agent specifically tailored for task completion within the Windows OS."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2025-ufo">
<titleInfo>
<title>UFO: A UI-Focused Agent for Windows OS Interaction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chaoyun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liqun</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shilin</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Qiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Si</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghua</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qingwei</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saravan</namePart>
<namePart type="family">Rajmohan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongmei</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-189-6</identifier>
</relatedItem>
<abstract>We introduce UFO, a UI-Fcused agent designed to fulfill user requests tailored to Windows OS applications by observing and analyzing the GUI and control information of these applications. UFO utilizes a hierarchical dual-agent framework that decomposes user requests using a divide-and-conquer approach, enabling seamless navigation and addressing sub-tasks across multiple applications. It also incorporates a control interaction module tailored for Windows OS, which detects control elements effectively and allows for fully automated execution. As a result, UFO simplifies complex and time-consuming processes into tasks that can be completed with natural language commands.We conducted testing of UFO across 9 popular Windows applications, encompassing a variety of scenarios. The results derived from both quantitative metrics and real-case studies, underscore the superior effectiveness of UFOin fulfilling user requests. To the best of our knowledge, UFO stands as the first UI agent specifically tailored for task completion within the Windows OS.</abstract>
<identifier type="citekey">zhang-etal-2025-ufo</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-long.26</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-long.26/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>597</start>
<end>622</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UFO: A UI-Focused Agent for Windows OS Interaction
%A Zhang, Chaoyun
%A Li, Liqun
%A He, Shilin
%A Zhang, Xu
%A Qiao, Bo
%A Qin, Si
%A Ma, Minghua
%A Kang, Yu
%A Lin, Qingwei
%A Rajmohan, Saravan
%A Zhang, Dongmei
%A Zhang, Qi
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F zhang-etal-2025-ufo
%X We introduce UFO, a UI-Fcused agent designed to fulfill user requests tailored to Windows OS applications by observing and analyzing the GUI and control information of these applications. UFO utilizes a hierarchical dual-agent framework that decomposes user requests using a divide-and-conquer approach, enabling seamless navigation and addressing sub-tasks across multiple applications. It also incorporates a control interaction module tailored for Windows OS, which detects control elements effectively and allows for fully automated execution. As a result, UFO simplifies complex and time-consuming processes into tasks that can be completed with natural language commands.We conducted testing of UFO across 9 popular Windows applications, encompassing a variety of scenarios. The results derived from both quantitative metrics and real-case studies, underscore the superior effectiveness of UFOin fulfilling user requests. To the best of our knowledge, UFO stands as the first UI agent specifically tailored for task completion within the Windows OS.
%R 10.18653/v1/2025.naacl-long.26
%U https://aclanthology.org/2025.naacl-long.26/
%U https://doi.org/10.18653/v1/2025.naacl-long.26
%P 597-622
Markdown (Informal)
[UFO: A UI-Focused Agent for Windows OS Interaction](https://aclanthology.org/2025.naacl-long.26/) (Zhang et al., NAACL 2025)
ACL
- Chaoyun Zhang, Liqun Li, Shilin He, Xu Zhang, Bo Qiao, Si Qin, Minghua Ma, Yu Kang, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, and Qi Zhang. 2025. UFO: A UI-Focused Agent for Windows OS Interaction. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 597–622, Albuquerque, New Mexico. Association for Computational Linguistics.