MobileForge：无需注释的移动GUI代理自适应方法，采用分层反馈引导的策略优化机制
MobileForge: Annotation-Free Adaptation for Mobile GUI Agents with Hierarchical Feedback-Guided Policy Optimization
摘要
基于MLLM的移动GUI代理在UI理解与操作执行方面取得了显著进展，但将其应用于实际目标应用仍然成本高昂——因为移动应用数量众多、更新频繁，且难以通过人工编写的任务、示例或奖励标签来覆盖这些应用。现有的无需注释的GUI学习方法虽然减少了人工干预，但却缺乏一个能够连接目标应用探索、课程挖掘、部署执行与反馈的统一框架；而策略优化往往依赖于孤立的部署过程和粗略的奖励机制，这些机制很难转化为可靠的改进信号。我们提出了MobileForge这一无需注释的移动GUI代理适配系统。MobileForge由MobileGym和Hierarchical Feedback-Guided Policy Optimization（HiFPO）两大部分组成：MobileGym将任务生成与部署评估与真实的移动应用交互相结合；HiFPO则能够将轨迹结果、步骤级反馈以及修正提示转化为以提示为背景的步骤级GRPO更新。仅使用自动生成的无需注释的适配数据，MobileForge使得Qwen3-VL-8B在AndroidWorld上的Pass@3得分达到了67.2%，这一成绩接近基于封闭数据的GUI专用模型GUI-Owl-1.5-8B的69.0%水平。经过MobileForge适配后的ForgeOwl-8B在AndroidWorld上的Pass@3得分进一步达到了77.6%，在域外场景下的MobileWorld GUI-only测试中则达到了41.0%的成功率，这使其成为我们评估中表现最出色的开放数据移动GUI代理。代码、数据和训练好的模型都可以在https://mobile-forge.github.io/获取。
English 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/.