Paper 2607.04425
UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning
- Published
- Jul 2026
- Research lab
- Independent
- Citations
- 1
- GitHub
- 56 stars
01 In brief
Summary
The paper introduces UI-MOPD, a method for continual learning of multi-platform GUI agents, addressing challenges like scarce cross-platform data and behavioral pattern mixing.
It constructs Uni-GUI, a dataset of ~10K high-quality trajectories from desktop and mobile environments, and proposes multi-teacher on-policy distillation (MOPD) with platform-conditioned teacher routing.
The shared student policy samples rollouts and aligns with platform-specific teachers via reverse KL divergence, preserving platform-specific behaviors while adapting to new platforms.
Experiments on OSWorld and MobileWorld show UI-MOPD achieves task success rates of 38.2% and 12.0%, respectively, outperforming baselines like mixed SFT and model merging.
It also maintains GUI grounding and static understanding, with improvements over the base model on AndroidControl and OSWorld-G.
02 From the paper
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/.