MobileForge：基於分層回饋引導策略最佳化的無標註行動GUI代理適應方法

摘要

基於多模態大語言模型的行動端GUI代理在UI理解與動作執行方面取得了顯著進展，但將其適應至真實目標應用仍成本高昂，原因在於行動應用數量龐大、更新頻繁，且難以透過人工編寫的任務、示範或獎勵標籤進行全面覆蓋。現有的免標註GUI學習雖能減少人工監督，但缺乏統一的基礎架構來銜接目標應用探索、課程挖掘、軌跡執行與反饋機制，且策略優化常依賴孤立的軌跡與粗糙的獎勵，難以將其轉化為可靠的改進訊號。我們提出MobileForge，這是一個無需標註的行動端GUI代理適應系統。MobileForge包含MobileGym（將任務生成與軌跡評估立基於真實行動應用互動）與分層反饋引導策略優化（HiFPO）（將軌跡結果、步驟層級過程反饋與修正提示轉化為提示情境化的步驟層級GRPO更新）。僅使用自動生成的免標註適應資料，MobileForge將Qwen3-VL-8B在AndroidWorld上的Pass@3提升至67.2%，接近使用閉源資料的專用GUI模型GUI-Owl-1.5-8B的69.0%。經MobileForge適應的ForgeOwl-8B更進一步在AndroidWorld上達到77.6%的Pass@3，並在跨領域的MobileWorld GUI-only子任務中取得41.0%的成功率，在我們的評測中樹立了最強的開源資料行動端GUI代理。程式碼、資料與訓練模型將於 https://mobile-forge.github.io/ 釋出。

English

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/.