{"ID":2864324,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.23866","arxiv_id":"2509.23866","title":"Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation","abstract":"Vision-language model (VLM) based GUI agents show promise for automating complex desktop and mobile tasks, but face significant challenges in applying reinforcement learning (RL): (1) slow multi-turn interactions with GUI environments for policy rollout, and (2) insufficient high-quality agent-environment interactions for policy learning. To address these challenges, we propose DART, a Decoupled Agentic RL Training framework for GUI agents, which coordinates heterogeneous modules in a highly decoupled manner. DART separates the training system into four asynchronous modules: environment cluster, rollout service, data manager, and trainer. This design enables non-blocking communication, asynchronous training, rollout-wise trajectory sampling, and per-worker model synchronization, significantly improving the system efficiency: 1.6*GPU utilization for rollout, 1.9* training throughput, and 5.5* environment utilization. To facilitate effective learning from abundant samples, we introduce an adaptive data curation scheme: (1) pre-collecting successful trajectories for challenging tasks to supplement sparse success in online sampling; (2) dynamically adjusting rollout numbers and trajectory lengths based on task difficulty; (3) training selectively on high-entropy steps to prioritize critical decisions; (4) stabilizing learning via truncated importance sampling for policy mismatch between policy rollout and updating. 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. We will fully open-source our training framework, data, and model checkpoints via computer-use-agents.github.io/dart-gui, which we believe is a timely contribution to the open-source community of agentic RL training.","short_abstract":"Vision-language model (VLM) based GUI agents show promise for automating complex desktop and mobile tasks, but face significant challenges in applying reinforcement learning (RL): (1) slow multi-turn interactions with GUI environments for policy rollout, and (2) insufficient high-quality agent-environment interactions...","url_abs":"https://arxiv.org/abs/2509.23866","url_pdf":"https://arxiv.org/pdf/2509.23866v1","authors":"[\"Pengxiang Li\",\"Zechen Hu\",\"Zirui Shang\",\"Jingrong Wu\",\"Yang Liu\",\"Hui Liu\",\"Zhi Gao\",\"Chenrui Shi\",\"Bofei Zhang\",\"Zihao Zhang\",\"Xiaochuan Shi\",\"Zedong YU\",\"Yuwei Wu\",\"Xinxiao Wu\",\"Yunde Jia\",\"Liuyu Xiang\",\"Zhaofeng He\",\"Qing Li\"]","published":"2025-09-28T13:19:20Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\",\"cs.CV\"]","methods":"[\"Reinforcement Learning\",\"Language Model\"]","has_code":false}