Mobile-Agent-v3: Fundamental Agents for GUI Automation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908511259066368 |
|---|---|
| author | Ye, Jiabo Zhang, Xi Xu, Haiyang Liu, Haowei Wang, Junyang Zhu, Zhaoqing Zheng, Ziwei Gao, Feiyu Cao, Junjie Lu, Zhengxi Liao, Jitong Zheng, Qi Huang, Fei Zhou, Jingren Yan, Ming |
| author_facet | Ye, Jiabo Zhang, Xi Xu, Haiyang Liu, Haowei Wang, Junyang Zhu, Zhaoqing Zheng, Ziwei Gao, Feiyu Cao, Junjie Lu, Zhengxi Liao, Jitong Zheng, Qi Huang, Fei Zhou, Jingren Yan, Ming |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_15144 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Mobile-Agent-v3: Fundamental Agents for GUI Automation Ye, Jiabo Zhang, Xi Xu, Haiyang Liu, Haowei Wang, Junyang Zhu, Zhaoqing Zheng, Ziwei Gao, Feiyu Cao, Junjie Lu, Zhengxi Liao, Jitong Zheng, Qi Huang, Fei Zhou, Jingren Yan, Ming Artificial Intelligence 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. |
| title | Mobile-Agent-v3: Fundamental Agents for GUI Automation |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2508.15144 |