{"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/agent-s2-a-compositional-generalist","title":"Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents","arxiv_id":"2504.00906","date":"2025-04-01","proceeding":null,"authors":["Saaket Agashe","Kyle Wong","Vincent Tu","Jiachen Yang","Ang Li","Xin Eric Wang"],"abstract":"Computer use agents automate digital tasks by directly interacting with graphical user interfaces (GUIs) on computers and mobile devices, offering significant potential to enhance human productivity by completing an open-ended space of user queries. However, current agents face significant challenges: imprecise grounding of GUI elements, difficulties with long-horizon task planning, and performance bottlenecks from relying on single generalist models for diverse cognitive tasks. To this end, we introduce Agent S2, a novel compositional framework that delegates cognitive responsibilities across various generalist and specialist models. We propose a novel Mixture-of-Grounding technique to achieve precise GUI localization and introduce Proactive Hierarchical Planning, dynamically refining action plans at multiple temporal scales in response to evolving observations. Evaluations demonstrate that Agent S2 establishes new state-of-the-art (SOTA) performance on three prominent computer use benchmarks. Specifically, Agent S2 achieves 18.9% and 32.7% relative improvements over leading baseline agents such as Claude Computer Use and UI-TARS on the OSWorld 15-step and 50-step evaluation. Moreover, Agent S2 generalizes effectively to other operating systems and applications, surpassing previous best methods by 52.8% on WindowsAgentArena and by 16.52% on AndroidWorld relatively. Code available at https://github.com/simular-ai/Agent-S.","url_abs":"https://arxiv.org/abs/2504.00906v1","url_pdf":"https://arxiv.org/pdf/2504.00906v1.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":"agent-s2-a-compositional-generalist","repo_url":"https://github.com/simular-ai/agent-s","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"ai-agent","task_name":"AI Agent"},{"task_slug":"task-planning","task_name":"Task Planning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2504.00906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.00906"}},"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/simular-ai/agent-s","reach":{"status":"ok","spdx":"Apache-2.0"}}],"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":"80e0cd7f0c4f74bf","entry":"execute_code","repo":"simular-ai/agent-s","repo_kind":"official","path":"gui_agents/s3/agents/code_agent.py","file_url":"https://github.com/simular-ai/agent-s/blob/HEAD/gui_agents/s3/agents/code_agent.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"80e0cd7f0c4f74bf"}},{"code_sha256_prefix":"5b5848f799f23954","entry":"extract_code_block","repo":"simular-ai/agent-s","repo_kind":"official","path":"gui_agents/s3/agents/code_agent.py","file_url":"https://github.com/simular-ai/agent-s/blob/HEAD/gui_agents/s3/agents/code_agent.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5b5848f799f23954"}},{"code_sha256_prefix":"41a765b894e86972","entry":"format_result","repo":"simular-ai/agent-s","repo_kind":"official","path":"gui_agents/s3/agents/code_agent.py","file_url":"https://github.com/simular-ai/agent-s/blob/HEAD/gui_agents/s3/agents/code_agent.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"41a765b894e86972"}},{"code_sha256_prefix":"91057ba978e5ccad","entry":"run_agent_s","repo":"simular-ai/agent-s","repo_kind":"official","path":"integrations/openclaw/agent_s_wrapper.py","file_url":"https://github.com/simular-ai/agent-s/blob/HEAD/integrations/openclaw/agent_s_wrapper.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"91057ba978e5ccad"}},{"code_sha256_prefix":"6cf040f5818fa058","entry":"show_permission_dialog","repo":"simular-ai/agent-s","repo_kind":"official","path":"gui_agents/s1/cli_app.py","file_url":"https://github.com/simular-ai/agent-s/blob/HEAD/gui_agents/s1/cli_app.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6cf040f5818fa058"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}