UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning
Summary
This paper introduces UI-MOPD, a method combining multi-teacher on-policy distillation with continual learning for training GUI agents across multiple platforms, along with the Uni-GUI dataset. It achieves task success rates of 38.2% and 12.0% on OSWorld and MobileWorld respectively, demonstrating effective cross-platform capability retention and adaptation.
View Cached Full Text
Cached at: 07/07/26, 06:42 AM
Paper page - UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning
Source: https://huggingface.co/papers/2607.04425 Authors:
,
,
,
,
,
,
,
,
,
Abstract
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.
Recent advances inmultimodal foundation modelsandagent systemshave drivenGUI agentsfrom single-platform task execution towardcross-platform interaction. However, building multi-platformGUI agentsremains challenging. On one hand, high-quality and executablecross-platform interactiontrajectories 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 tobehavioral pattern mixing, platform-specific capability degradation, andcatastrophic 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 incorporatesmulti-teacher on-policy distillationintocontinual learningforGUI agents. UI-MOPD dynamically selects a platform-specific teacher according to the current environment and transfers platform-specific behavioral priors to a shared policy throughplatform-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/.
View arXiv pageView PDFAdd to collection
Get this paper in your agent:
hf papers read 2607\.04425
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2607.04425 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2607.04425 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2607.04425 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training
MOPD proposes a multi-teacher on-policy distillation paradigm for LLM post-training, enabling efficient integration of multiple domain capabilities by distilling specialized RL teachers into a student model using its own rollouts. It outperforms existing methods like Mix-RL and Cascade RL, and has been deployed in industrial-scale models.
Skill-Guided Continuation Distillation for GUI Agents
The paper proposes Skill-Guided Continuation Distillation (SGCD), an iterative self-improvement framework that uses skill-guided policies to generate supervision for off-trajectory states during closed-loop execution, improving GUI agent success rates on OSWorld-Verified from around 30% to over 50%.
DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models
DiffusionOPD proposes a multi-task training paradigm for diffusion models that uses online policy distillation to efficiently combine task-specific teachers into a unified student, achieving state-of-the-art results on all evaluated benchmarks.
UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning
UI-TARS-2 is a native GUI-centered agent model that addresses data scalability, multi-turn RL, and environment stability challenges, achieving state-of-the-art results on GUI benchmarks (88.2 on Online-Mind2Web, 47.5 on OSWorld, 50.6 on WindowsAgentArena,73.3 on AndroidWorld) and outperforming Claude and OpenAI agents.
Multi-Rollout On-Policy Distillation via Peer Successes and Failures
Introduces Multi-Rollout On-Policy Distillation (MOPD), a method that conditions the teacher on both successful and failed peer rollouts to provide denser token-level supervision for language model post-training, improving performance across multiple benchmarks.