Paper 2508.15144
Mobile-Agent-v3: Fundamental Agents for GUI Automation
- Published
- Aug 2025
- Research lab
- Independent
- Citations
- 150
- GitHub
- 9K stars
01 In brief
Summary
The paper introduces GUI-Owl, a foundational GUI agent model built on Qwen2.5-VL, and Mobile-Agent-v3, a multi-agent framework.
GUI-Owl-7B achieves state-of-the-art scores among open-source models, including 66.4 on AndroidWorld and 34.9 on OSWorld-Verified, while Mobile-Agent-v3 further improves these to 73.3 and 37.7, respectively.
Key innovations include a cloud-based virtual environment infrastructure for self-evolving trajectory production, diverse data pipelines for grounding, planning, and action semantics, and a scalable reinforcement learning framework with Trajectory-aware Relative Policy Optimization (TRPO).
The model unifies perception, grounding, reasoning, planning, and action execution, and can be deployed as specialized agents within Mobile-Agent-v3, which coordinates Manager, Worker, Reflector, and Notetaker agents.
Experiments show GUI-Owl-32B surpasses proprietary models like GPT-4o and Claude 3.7 on several benchmarks, including MMBench-GUI and AndroidControl.
The self-evolving pipeline reduces manual annotation, and the RL framework improves stability and performance in long-horizon tasks.
02 From the paper
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.