{"ID":2879630,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.15144","arxiv_id":"2508.15144","title":"Mobile-Agent-v3: Fundamental Agents for GUI Automation","abstract":"This paper introduces GUI-Owl, a foundational GUI agent model that achieves state-of-the-art performance among open-source end-to-end models on ten GUI benchmarks across desktop and mobile environments, covering grounding, question answering, planning, decision-making, and procedural knowledge. GUI-Owl-7B achieves 66.4 on AndroidWorld and 29.4 on OSWorld. Building on this, we propose Mobile-Agent-v3, a general-purpose GUI agent framework that further improves performance to 73.3 on AndroidWorld and 37.7 on OSWorld, setting a new state-of-the-art for open-source GUI agent frameworks. GUI-Owl incorporates three key innovations: (1) Large-scale Environment Infrastructure: a cloud-based virtual environment spanning Android, Ubuntu, macOS, and Windows, enabling our Self-Evolving GUI Trajectory Production framework. This generates high-quality interaction data via automated query generation and correctness validation, leveraging GUI-Owl to refine trajectories iteratively, forming a self-improving loop. It supports diverse data pipelines and reduces manual annotation. (2) Diverse Foundational Agent Capabilities: by integrating UI grounding, planning, action semantics, and reasoning patterns, GUI-Owl supports end-to-end decision-making and can act as a modular component in multi-agent systems. (3) Scalable Environment RL: we develop a scalable reinforcement learning framework with fully asynchronous training for real-world alignment. We also introduce Trajectory-aware Relative Policy Optimization (TRPO) for online RL, achieving 34.9 on OSWorld. GUI-Owl and Mobile-Agent-v3 are open-sourced at https://github.com/X-PLUG/MobileAgent.","short_abstract":"This paper introduces GUI-Owl, a foundational GUI agent model that achieves state-of-the-art performance among open-source end-to-end models on ten GUI benchmarks across desktop and mobile environments, covering grounding, question answering, planning, decision-making, and procedural knowledge. GUI-Owl-7B achieves 66.4...","url_abs":"https://arxiv.org/abs/2508.15144","url_pdf":"https://arxiv.org/pdf/2508.15144v2","authors":"[\"Jiabo Ye\",\"Xi Zhang\",\"Haiyang Xu\",\"Haowei Liu\",\"Junyang Wang\",\"Zhaoqing Zhu\",\"Ziwei Zheng\",\"Feiyu Gao\",\"Junjie Cao\",\"Zhengxi Lu\",\"Jitong Liao\",\"Qi Zheng\",\"Fei Huang\",\"Jingren Zhou\",\"Ming Yan\"]","published":"2025-08-21T00:39:12Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Reinforcement Learning\"]","has_code":false,"code_links":[{"ID":610605,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2879630,"paper_url":"https://arxiv.org/abs/2508.15144","paper_title":"Mobile-Agent-v3: Fundamental Agents for GUI Automation","repo_url":"https://github.com/X-PLUG/MobileAgent","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}