UFO: A UI-Focused Agent for Windows OS Interaction
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929353234841600 |
|---|---|
| author | Zhang, Chaoyun Li, Liqun He, Shilin Zhang, Xu Qiao, Bo Qin, Si Ma, Minghua Kang, Yu Lin, Qingwei Rajmohan, Saravan Zhang, Dongmei Zhang, Qi |
| author_facet | Zhang, Chaoyun Li, Liqun He, Shilin Zhang, Xu Qiao, Bo Qin, Si Ma, Minghua Kang, Yu Lin, Qingwei Rajmohan, Saravan Zhang, Dongmei Zhang, Qi |
| contents | We introduce UFO, an innovative UI-Focused agent to fulfill user requests tailored to applications on Windows OS, harnessing the capabilities of GPT-Vision. UFO employs a dual-agent framework to meticulously observe and analyze the graphical user interface (GUI) and control information of Windows applications. This enables the agent to seamlessly navigate and operate within individual applications and across them to fulfill user requests, even when spanning multiple applications. The framework incorporates a control interaction module, facilitating action grounding without human intervention and enabling fully automated execution. Consequently, UFO transforms arduous and time-consuming processes into simple tasks achievable solely through natural language commands. We conducted testing of UFO across 9 popular Windows applications, encompassing a variety of scenarios reflective of users' daily usage. The results, derived from both quantitative metrics and real-case studies, underscore the superior effectiveness of UFO in 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 environment. The open-source code for UFO is available on https://github.com/microsoft/UFO. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_07939 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | UFO: A UI-Focused Agent for Windows OS Interaction Zhang, Chaoyun Li, Liqun He, Shilin Zhang, Xu Qiao, Bo Qin, Si Ma, Minghua Kang, Yu Lin, Qingwei Rajmohan, Saravan Zhang, Dongmei Zhang, Qi Human-Computer Interaction Artificial Intelligence Computation and Language We introduce UFO, an innovative UI-Focused agent to fulfill user requests tailored to applications on Windows OS, harnessing the capabilities of GPT-Vision. UFO employs a dual-agent framework to meticulously observe and analyze the graphical user interface (GUI) and control information of Windows applications. This enables the agent to seamlessly navigate and operate within individual applications and across them to fulfill user requests, even when spanning multiple applications. The framework incorporates a control interaction module, facilitating action grounding without human intervention and enabling fully automated execution. Consequently, UFO transforms arduous and time-consuming processes into simple tasks achievable solely through natural language commands. We conducted testing of UFO across 9 popular Windows applications, encompassing a variety of scenarios reflective of users' daily usage. The results, derived from both quantitative metrics and real-case studies, underscore the superior effectiveness of UFO in 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 environment. The open-source code for UFO is available on https://github.com/microsoft/UFO. |
| title | UFO: A UI-Focused Agent for Windows OS Interaction |
| topic | Human-Computer Interaction Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2402.07939 |