# MobileForge: Annotation-Free Adaptation for Mobile GUI Agents with Hierarchical Feedback-Guided Policy Optimization Source: [MobileForge: Annotation-Free Adaptation for Mobile GUI Agents with Hierarchical Feedback-Guided Policy Optimization]() Collection index: [llms.txt]() Data updated: 2026-08-11T05:02:11.192Z Authors: Guangyi Liu, Pengxiang Zhao, Gao Wu, Yiwen Yin, Mading Li, Liang Liu, Congxiao Liu, Zhang Qi, Mengyan Wang, Liang Guo, Jiangning Zhang, Yong Liu Published: 2026-06-18T08:29:33.000Z ## Abstract MLLM-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/. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Mobile agent task completion on AndroidWorld 116 tasks](): Mobile agent task completion; AndroidWorld 116 tasks; Task Success Rate (TSR): 90. - [Mobile GUI Navigation on MobileWorld GUI-Only 117 tasks (test)](): Mobile GUI Navigation; MobileWorld GUI-Only 117 tasks (test); Pass@1 Success Rate: 41. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()