titleMobileForge: Annotation-Free Adaptation for Mobile GUI Agents with Hierarchical Feedback-Guided Policy Optimization
authorsGuangyi Liu, Pengxiang Zhao, Gao Wu, Yiwen Yin, Mading Li, Liang Liu, Congxiao Liu, Zhang Qi, Mengyan Wang, Liang Guo, Yong Liu
date2026-06-18
venuearXiv (preprint, not peer reviewed)
idarXiv:2606.19930
affiliationkwai
upvotes44 (Hugging Face Daily Papers, 2026-11-01)
linksabs pdf hf code
abstractMLLM-based mobile GUI agents have made substantial progress in UI understanding and action execution, but adapting them to real target apps remains costly because mobile apps are numerous, frequently updated, and hard to cover with human-written tasks, demonstrations, or reward labels. Existing annotation-free GUI learning reduces manual supervision, yet lacks a unified substrate connecting target-app exploration, curriculum mining, rollout execution, and feedback, while policy optimization often relies on isolated rollouts and coarse rewards that are hard to convert into reliable improvement signals. We present MobileForge, an annotation-free adaptation system for mobile GUI agents. MobileForge consists of MobileGym, which grounds task generation and rollout evaluation in real mobile app interaction, and Hierarchical Feedback-Guided Policy Optimization (HiFPO), which turns trajectory outcomes, step-level process feedback, and corrective hints into hint-contextualized step-level GRPO updates. Using only automatically generated annotation-free adaptation data, MobileForge adapts Qwen3-VL-8B to 67.2% Pass@3 on AndroidWorld, close to the closed-data GUI-specialized GUI-Owl-1.5-8B base model at 69.0%. The MobileForge-adapted ForgeOwl-8B further reaches 77.6% Pass@3 on AndroidWorld and 41.0% success on the out-of-domain MobileWorld GUI-only split, establishing the strongest open-data mobile GUI agent in our evaluation. Code, data, and trained models will be released at https://mobile-forge.github.io/.

cite

@misc{liu2026mobileforge,
  title={MobileForge: Annotation-Free Adaptation for Mobile GUI Agents with Hierarchical Feedback-Guided Policy Optimization},
  author={Guangyi Liu and Pengxiang Zhao and Gao Wu and Yiwen Yin and Mading Li and Liang Liu and Congxiao Liu and Zhang Qi and Mengyan Wang and Liang Guo and Yong Liu},
  year={2026},
  eprint={2606.19930},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2606.19930}
}