发表机构
Tsinghua Shenzhen International Graduate School, Tsinghua University; Xiaomi; Harbin Institute of Technology, Shenzhen; Zhejiang University; Peng Cheng Laboratory（清华大学深圳国际研究生院; 小米; 哈尔滨工业大学（深圳）; 浙江大学; 鹏城实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对构建多平台GUI智能体的挑战，构建高质量数据集Uni-GUI，提出UI-MOPD方法，通过多教师策略蒸馏实现持续学习，动态选教师并转移行为先验，实验证明其能平衡跨平台能力保留与新平台适应。
AI 中文摘要
多模态基础模型和智能体系统的进展推动GUI智能体从单平台任务执行向跨平台交互发展。构建多平台GUI智能体仍具挑战。一方面，高质量可执行跨平台交互轨迹稀缺，现有数据平台覆盖有限；另一方面，不同平台交互惯例不同，联合或持续训练易出现问题。为应对这些挑战，我们构建了Uni-GUI，一个高质量的跨平台GUI交互数据集，并提出了UI-MOPD，这是第一种将多教师策略蒸馏纳入GUI智能体持续学习的方法。UI-MOPD根据当前环境动态选择特定平台的教师，并通过平台条件蒸馏将特定平台的行为先验转移到共享策略中，从而在保留现有平台能力的同时适应新平台。在OSWorld和MobileWorld上的实验表明，UI-MOPD分别实现了38.2%和12.0%的任务成功率，证明了其在平衡跨平台能力保留和新平台适应方面的有效性。项目页面：此https URL。
英文摘要
Recent advances in multimodal foundation models and agent systems have driven GUI agents from single-platform task execution toward cross-platform interaction. However, unified multi-platform GUI learning remains challenging: high-quality cross-platform trajectories remain scarce, while platforms share transferable capabilities but differ in action semantics and interaction conventions. Naively mixing supervision or merging specialized models can blur native behaviors and produce imbalanced performance. To address these challenges, we construct Uni-GUI, a high-quality dataset containing nearly 10K executable cross-platform interaction trajectories collected through a unified desktop-mobile harness. Building on Uni-GUI, we propose UI-MOPD, the first framework to introduce multi-teacher on-policy distillation (MOPD) into unified multi-platform GUI agent training. UI-MOPD trains a shared student on its own rollouts and dynamically routes each rollout to the corresponding platform-specialized teacher. At student-visited states, teacher guidance serves as a platform-conditioned behavioral anchor, enabling the integration of complementary desktop and mobile expertise without averaging their distinct interaction conventions. On OSWorld and MobileWorld, UI-MOPD achieves task success rates of 38.2% and 12.0%, respectively, outperforming parameter-matched integration strategies while preserving general GUI grounding. These results demonstrate that multi-teacher on-policy distillation provides an effective approach to building unified cross-platform GUI agents. Project page: https://elispectre.github.io/UI-MOPD/.
CommentsTechnical report. 27 pages, 7 figures, 7 tables
