AI 学会跨平台操作手机和电脑，但别高兴太早
你让 AI 帮你订外卖，它在手机上点几下，换到电脑上就傻了——因为不同 App 的按钮位置、操作逻辑完全不同。这篇论文想解决的就是这个：让一个 AI 同时学会操作多个平台（比如 Windows 和 Android），而且学新平台时不忘记旧平台。他们先自己造了一个跨平台的操作数据集（Uni-GUI），然后设计了一个训练方法（UI-MOPD）：给每个平台配一个专属的“老师”，AI 在哪个平台干活，就听哪个老师的指导，这样既学得快又不串味。结果呢？在 OSWorld（桌面）上成功率 38.2%，在 MobileWorld（手机）上 12.0%——听着不高，但已经是目前最好的跨平台成绩。不过，这离“一个 AI 帮你搞定所有 App”还远，它更像一个靠谱的起点：证明这条路能走通。
📄 原文摘要(英文)
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/.