{"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/efficient-agent-training-for-computer-use","title":"Efficient Agent Training for Computer Use","arxiv_id":"2505.13909","date":"2025-05-20","proceeding":null,"authors":["Yanheng He","Jiahe Jin","PengFei Liu"],"abstract":"Scaling up high-quality trajectory data has long been a critical bottleneck for developing human-like computer use agents. We introduce PC Agent-E, an efficient agent training framework that significantly reduces reliance on large-scale human demonstrations. Starting with just 312 human-annotated computer use trajectories, we further improved data quality by synthesizing diverse action decisions with Claude 3.7 Sonnet. Trained on these enriched trajectories, our PC Agent-E model achieved a remarkable 141% relative improvement, surpassing the strong Claude 3.7 Sonnet with extended thinking on WindowsAgentArena-V2, an improved benchmark we also released. Furthermore, PC Agent-E demonstrates strong generalizability to different operating systems on OSWorld. Our findings suggest that strong computer use capabilities can be stimulated from a small amount of high-quality trajectory data.","url_abs":"https://arxiv.org/abs/2505.13909v1","url_pdf":"https://arxiv.org/pdf/2505.13909v1.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":"efficient-agent-training-for-computer-use","repo_url":"https://github.com/gair-nlp/pc-agent-e","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"efficient-agent-training-for-computer-use","repo_url":"https://github.com/GAIR-NLP/PC-Agent","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.13909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.13909"}},"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/GAIR-NLP/PC-Agent","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gair-nlp/pc-agent-e","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_violates":2,"ran_honours":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":"4250070126900a96","entry":"clean_fail_and_error","repo":"GAIR-NLP/PC-Agent-E","repo_kind":"official","path":"postprocess/refinement.py","file_url":"https://github.com/GAIR-NLP/PC-Agent-E/blob/HEAD/postprocess/refinement.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4250070126900a96"}},{"code_sha256_prefix":"c357e4535b022512","entry":"clean_tracker_interface","repo":"GAIR-NLP/PC-Agent-E","repo_kind":"official","path":"postprocess/refinement.py","file_url":"https://github.com/GAIR-NLP/PC-Agent-E/blob/HEAD/postprocess/refinement.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c357e4535b022512"}},{"code_sha256_prefix":"4e3517904e50135f","entry":"screenshot_of_tracker","repo":"GAIR-NLP/PC-Agent-E","repo_kind":"official","path":"postprocess/refinement.py","file_url":"https://github.com/GAIR-NLP/PC-Agent-E/blob/HEAD/postprocess/refinement.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4e3517904e50135f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}