UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning

• URL: http://arxiv.org/abs/2607.04425v1
• Date: Sun, 05 Jul 2026 17:37:12 GMT
• Title: UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning
• Abstract summary: We propose UI-MOPD, a method that incorporates multi-teacher on-policy distillation into continual learning for GUI agents.<n>Experiments on OSWorld and MobileWorld show that UI-MOPD achieves task success rates of 38.2% and 12.0%, respectively.
• Score: 67.45909103605858
• License: http://creativecommons.org/licenses/by/4.0/
• 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/.

Related papers

• JarvisGUI: Towards Cross-Device GUI Agents with Dynamic Task Composition [51.15720718264743]
  We introduce JarvisGUI, a dynamic benchmark that evaluates GUI agents on cross-device requiring coordinated interaction across platforms.<n>JarvisGUI formulates GUI tasks as input-output transformations under a lightweight type system, which allows us to automatically compose multi-step, cross-device transformations.<n>We show that state-of-the-art open-source GUI agents struggle with the state-transfer awareness, cross-platform contextual reasoning, and long-horizon dependency management required for real-world usage.
  arXiv  Detail & Related papers  (2026-09-09T16:59:59Z)
• LLM-Augmented Digital Twin for Policy Evaluation in Short-Video Platforms [12.693132563364342]
  Short-video platforms are closed-loop, human-in-the-loop ecosystems where policy, creator incentives, and user behavior co-evolve.<n>We propose a large language model (LLM)-augmented digital twin for short-video platforms with a modular four-twin architecture.
  arXiv  Detail & Related papers  (2026-03-11T21:50:21Z)
• Yanyun-3: Enabling Cross-Platform Strategy Game Operation with Vision-Language Models [30.591909012704978]
  Yanyun-3 is a VLM-based agent that integrates Qwen2.5-VL for visual reasoning and UI-TARS for interface execution.<n>We propose a novel data organization principle to distinguish intra-sample fusion and inter-sample mixing of multimodal data.<n>Yanyun-3 offers a generalizable framework for GUI automation, with broader implications for robotics and autonomous systems.
  arXiv  Detail & Related papers  (2025-11-17T03:45:15Z)
• Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation [65.3648667980258]
  Vision-language model (VLM) based GUI agents show promise for automating complex tasks, but face significant challenges in applying reinforcement learning (RL)<n>We propose DART, a Decoupled Agentic RL Training framework for GUI agents, which coordinates heterogeneous modules in a highly decoupled manner.<n>On the OSWorld benchmark, DART-GUI-7B achieves a 42.13% task success rate, a 14.61% absolute gain over the base model, and 7.34% higher than open-source SOTA.
  arXiv  Detail & Related papers  (2025-09-28T13:19:20Z)
• UIPro: Unleashing Superior Interaction Capability For GUI Agents [33.77980648230746]
  Building autonomous agents that perceive and operate graphical user interfaces (GUIs) like humans has long been a vision in the field of artificial intelligence.<n>Existing methods have tried developing GUI agents based on the multi-modal comprehension ability of vision-language models (VLMs)<n>This paper proposes textUIPro, a novel generalist GUI agent trained with extensive multi-platform and multi-task GUI interaction data.
  arXiv  Detail & Related papers  (2025-09-22T03:04:53Z)
• MobileGUI-RL: Advancing Mobile GUI Agent through Reinforcement Learning in Online Environment [63.62778707277929]
  MobileGUI-RL is a scalable framework that trains GUI agent in online environment.<n>It synthesizes a curriculum of learnable tasks through self-exploration and filtering.<n>It adapts GRPO to GUI navigation with trajectory-aware advantages and composite rewards.
  arXiv  Detail & Related papers  (2025-07-08T07:07:53Z)
• AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning [82.42421823672954]
  AgentCPM-GUI is built for robust and efficient on-device GUI interaction.<n>Our training pipeline includes grounding-aware pre-training to enhance perception.<n>AgentCPM-GUI achieves state-of-the-art performance on five public benchmarks.
  arXiv  Detail & Related papers  (2025-06-02T07:30:29Z)
• UI-TARS: Pioneering Automated GUI Interaction with Native Agents [58.18100825673032]
  This paper introduces UI-TARS, a native GUI agent model that solely perceives the screenshots as input and performs human-like interactions.<n>In the OSWorld benchmark, UI-TARS achieves scores of 24.6 with 50 steps and 22.7 with 15 steps, outperforming Claude (22.0 and 14.9 respectively)
  arXiv  Detail & Related papers  (2025-01-21T17:48:10Z)
• Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction [69.57190742976091]
  Aguvis is a vision-based framework for autonomous GUI agents.<n>It standardizes cross-platform interactions and incorporates structured reasoning via inner monologue.<n>It achieves state-of-the-art performance across offline and real-world online benchmarks.
  arXiv  Detail & Related papers  (2024-12-05T18:58:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.