研究人员开发了UI-MOPD，一种用于训练可在多个平台上运行的GUI代理的新颖方法。该方法解决了跨平台数据稀缺以及在适应新平台的同时保持现有平台性能的挑战。UI-MOPD利用多教师策略内蒸馏，动态选择特定平台的教师来转移知识并防止灾难性遗忘。在OSWorld和MobileWorld上的实验分别证明了该方法的有效性，任务成功率分别为38.2%和12.0%。 AI
影响 使GUI代理更加通用和适应性强，可能简化跨平台自动化和用户交互。
排序理由 该集群包含一篇详细介绍AI研究新方法和数据集的学术论文。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2607.04425v1 Announce Type: cross Abstract: 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 on…
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…
Uni-GUI dataset and UI-MOPD method enable cross-platform GUI agent training by addressing limited data and platform-specific capability degradation through multi-teacher on-policy distillation.