MobileGUI-RL: Advancing Mobile GUI Agent through Reinforcement Learning in Online Environment
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912472020025344 |
|---|---|
| author | Shi, Yucheng Yu, Wenhao Li, Zaitang Wang, Yonglin Zhang, Hongming Liu, Ninghao Mi, Haitao Yu, Dong |
| author_facet | Shi, Yucheng Yu, Wenhao Li, Zaitang Wang, Yonglin Zhang, Hongming Liu, Ninghao Mi, Haitao Yu, Dong |
| contents | Recently, there has been a surge of vision-based GUI agents designed to automate everyday mobile and web tasks. These agents interpret raw GUI screenshots and autonomously decide where to click, scroll, or type, which bypasses handcrafted rules and app-specific APIs. However, most existing methods trained GUI agent in the offline environment using pre-collected trajectories. This approach limits scalability, causes overfitting to specific UI templates, and leads to brittle policies when faced with unseen environment. We present MobileGUI-RL, a scalable framework that trains GUI agent in online environment. MobileGUI-RL contains two key components. It (i) synthesizes a curriculum of learnable tasks through self-exploration and filtering, and (ii) adapts GRPO to GUI navigation with trajectory-aware advantages and composite rewards that balance task success and execution efficiency. Experiments on three online mobile-agent benchmarks show consistent gains, validating the effectiveness of our approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_05720 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MobileGUI-RL: Advancing Mobile GUI Agent through Reinforcement Learning in Online Environment Shi, Yucheng Yu, Wenhao Li, Zaitang Wang, Yonglin Zhang, Hongming Liu, Ninghao Mi, Haitao Yu, Dong Machine Learning Computation and Language Recently, there has been a surge of vision-based GUI agents designed to automate everyday mobile and web tasks. These agents interpret raw GUI screenshots and autonomously decide where to click, scroll, or type, which bypasses handcrafted rules and app-specific APIs. However, most existing methods trained GUI agent in the offline environment using pre-collected trajectories. This approach limits scalability, causes overfitting to specific UI templates, and leads to brittle policies when faced with unseen environment. We present MobileGUI-RL, a scalable framework that trains GUI agent in online environment. MobileGUI-RL contains two key components. It (i) synthesizes a curriculum of learnable tasks through self-exploration and filtering, and (ii) adapts GRPO to GUI navigation with trajectory-aware advantages and composite rewards that balance task success and execution efficiency. Experiments on three online mobile-agent benchmarks show consistent gains, validating the effectiveness of our approach. |
| title | MobileGUI-RL: Advancing Mobile GUI Agent through Reinforcement Learning in Online Environment |
| topic | Machine Learning Computation and Language |
| url | https://arxiv.org/abs/2507.05720 |