{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/ufo2-the-desktop-agentos","title":"UFO2: The Desktop AgentOS","arxiv_id":"2504.14603","date":"2025-04-20","proceeding":null,"authors":["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"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2504.14603v2","url_pdf":"https://arxiv.org/pdf/2504.14603v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"ufo2-the-desktop-agentos","repo_url":"https://github.com/microsoft/UFO","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2504.14603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.14603"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/microsoft/UFO","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"fb0ae895906b19c6","entry":"question_asker","repo":"microsoft/UFO","repo_kind":"official","path":"ufo/module/interactor.py","file_url":"https://github.com/microsoft/UFO/blob/HEAD/ufo/module/interactor.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fb0ae895906b19c6"}},{"code_sha256_prefix":"3726afeffaeaea05","entry":"sensitive_step_asker","repo":"microsoft/UFO","repo_kind":"official","path":"ufo/module/interactor.py","file_url":"https://github.com/microsoft/UFO/blob/HEAD/ufo/module/interactor.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3726afeffaeaea05"}},{"code_sha256_prefix":"67eae25b5568d731","entry":"validate_path_not_sensitive","repo":"microsoft/UFO","repo_kind":"official","path":"ufo/automator/path_validator.py","file_url":"https://github.com/microsoft/UFO/blob/HEAD/ufo/automator/path_validator.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"67eae25b5568d731"}},{"code_sha256_prefix":"0d2655dd06b008c5","entry":"validate_path_within_base","repo":"microsoft/UFO","repo_kind":"official","path":"ufo/automator/path_validator.py","file_url":"https://github.com/microsoft/UFO/blob/HEAD/ufo/automator/path_validator.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0d2655dd06b008c5"}},{"code_sha256_prefix":"df0573a74f4213db","entry":"validate_save_path","repo":"microsoft/UFO","repo_kind":"official","path":"ufo/automator/path_validator.py","file_url":"https://github.com/microsoft/UFO/blob/HEAD/ufo/automator/path_validator.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"df0573a74f4213db"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}