Episode
UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning
- Podcast
- Daily Paper Cast
- Published
- Jul 8, 2026
- Duration seconds
- 1301
- Processing state
not_requested- Canonical source
- https://share.transistor.fm/s/6d7f3786
Actions
POST https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/ui-mopd-multi-platform-on-policy-distillation-for-continual-gui-agent-learning/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/daily-paper-cast-7079649/ui-mopd-multi-platform-on-policy-distillation-for-continual-gui-agent-learning.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
🤗 Upvotes: 63 | cs.CL, cs.AI, cs.CV, cs.LG, cs.MM Authors: Niu Lian, Alan Chen, Zhehao Yu, Chengzhen Duan, Fazhan Liu, Hui Liu, Pei Fu, Jian Luan, Yaowei Wang, Shu-Tao Xia, Jinpeng Wang Title: UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning Arxiv: http://arxiv.org/abs/2607.04425v1 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 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/.