{"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/aguvis-unified-pure-vision-agents-for","title":"Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction","arxiv_id":"2412.04454","date":"2024-12-05","proceeding":null,"authors":["Yiheng Xu","Zekun Wang","Junli Wang","Dunjie Lu","Tianbao Xie","Amrita Saha","Doyen Sahoo","Tao Yu","Caiming Xiong"],"abstract":"Automating GUI tasks remains challenging due to reliance on textual representations, platform-specific action spaces, and limited reasoning capabilities. We introduce Aguvis, a unified vision-based framework for autonomous GUI agents that directly operates on screen images, standardizes cross-platform interactions and incorporates structured reasoning via inner monologue. To enable this, we construct Aguvis Data Collection, a large-scale dataset with multimodal grounding and reasoning annotations, and develop a two-stage training pipeline that separates GUI grounding from planning and reasoning. Experiments show that Aguvis achieves state-of-the-art performance across offline and real-world online benchmarks, marking the first fully autonomous vision-based GUI agent that operates without closed-source models. We open-source all datasets, models, and training recipes at https://aguvis-project.github.io to advance future research.","url_abs":"https://arxiv.org/abs/2412.04454v2","url_pdf":"https://arxiv.org/pdf/2412.04454v2.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":"aguvis-unified-pure-vision-agents-for","repo_url":"https://github.com/xlang-ai/aguvis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"multimodal-reasoning","task_name":"Multimodal Reasoning"},{"task_slug":"natural-language-visual-grounding","task_name":"Natural Language Visual Grounding"},{"task_slug":"navigate","task_name":"Navigate"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/natural-language-visual-grounding-on","task":"Natural Language Visual Grounding","dataset":"ScreenSpot","model":"Aguvis-7B","rank_in_archive_order":2,"of":18,"metrics":{"Accuracy (%)":"83.0"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-visual-grounding-on","task":"Natural Language Visual Grounding","dataset":"ScreenSpot","model":"Aguvis-G-7B","rank_in_archive_order":5,"of":18,"metrics":{"Accuracy (%)":"81.0"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2412.04454","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}