Skip to content

Source paper

Mobile-Agent-v3: Foundamental Agents for GUI Automation

Jiabo Ye, Xi Zhang, Haiyang Xu and 12 more

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

arXiv 2508.15144 · 202565 upvotes on Hugging Face

Research ideas from this paper (3)

Generated by AI. The paper’s authors did not write these.

AI summary

This paper presents GUI-Owl and Mobile-Agent-v3, a foundational end-to-end multimodal model and multi-agent framework designed for cross-platform GUI automation (Mobile, PC, Web). The authors introduce a self-evolving data production pipeline that synthesizes large-scale training data through model rollouts, critic-based filtering, and VLM-generated guidance, followed by a scalable reinforcement learning framework using Trajectory-aware Relative Policy Optimization (TRPO) to handle long-horizon tasks.

How it works (AI summary)

The core methodology utilizes Qwen2.5-VL as the base model, fine-tuned on a massive dataset generated via a self-evolving pipeline that includes 'Step-Level' and 'Trajectory-Level' critics. The model is further optimized using an asynchronous reinforcement learning framework (Mobile-Agent-v3) that employs TRPO to assign trajectory-level rewards to individual steps, mitigating sparse reward issues in multi-step GUI tasks.