UI-MOPD：用於持續GUI智能體學習的多平台在策略蒸餾

摘要

多模態基礎模型與智能體系統的最新進展，已將GUI代理從單一平台的任務執行推向跨平台互動。然而，構建多平台GUI代理仍然充滿挑戰。一方面，高質量且可執行的跨平台互動軌跡仍然稀缺，現有數據常受限於平台覆蓋範圍不足。另一方面，不同平台展現出截然不同的互動規範，使得聯合訓練或持續訓練容易出現行為模式混淆、特定平台能力衰退以及災難性遺忘等問題。為應對這些挑戰，我們構建了Uni-GUI，一個高品質的跨平台GUI互動資料集，並提出UI-MOPD——首個將多教師同策略蒸餾整合至GUI代理持續學習的方法。UI-MOPD能根據當前環境動態選擇平台專屬教師，並透過平台條件蒸餾將平台特定的行為先驗轉移至共享策略，從而在保留既有平台能力的同時，實現對新平台的適應。在OSWorld與MobileWorld上的實驗結果顯示，UI-MOPD分別達成了38.2%與12.0%的任務成功率，證明了其在跨平台能力保留與新平台適應之間的平衡效果。專案頁面：https://elispectre.github.io/UI-MOPD/ 。

English

Recent advances in multimodal foundation models and agent systems have driven GUI agents from single-platform task execution toward cross-platform interaction. However, building multi-platform GUI agents remains challenging. On one hand, high-quality and executable cross-platform interaction trajectories are still scarce, and existing data often suffer from limited platform coverage. On the other hand, different platforms exhibit distinct interaction conventions, making joint or continual training prone to behavioral pattern mixing, platform-specific capability degradation, and catastrophic forgetting. To address these challenges, we construct Uni-GUI, a high-quality cross-platform GUI interaction dataset, and propose UI-MOPD, the first method that incorporates multi-teacher on-policy distillation into continual learning for GUI agents. UI-MOPD dynamically selects a platform-specific teacher according to the current environment and transfers platform-specific behavioral priors to a shared policy through platform-conditioned distillation, enabling adaptation to new platforms while preserving capabilities on existing ones. Experiments on OSWorld and MobileWorld show that UI-MOPD achieves task success rates of 38.2% and 12.0%, respectively, demonstrating its effectiveness in balancing cross-platform capability retention and new-platform adaptation. Project page: https://elispectre.github.io/UI-MOPD/.