GUI 智能體的高效自適應訓練:在哪裏學習、軌跡展開多遠
Where to Learn and How Far to Roll Out: Efficient Adaptive Training for GUI Agents
研究提出兩階段自適應訓練框架,提升多步 GUI 智能體訓練效率,並在 MobileGym 和 CUA-Gym-Hub 將環境互動量減少 56-61%,同時提升任務表現。框架從成功專家軌跡建立可重用中間檢查點,按動作分歧選出訓練位置,再逐步擴大策略的訓練範圍。
Published on Oct 29
Authors:
,
,
,
Abstract
A two-stage adaptive framework improves multi-step GUI agent training by using intermediate checkpoints and selective rollout ranges to reduce environment interactions while boosting performance.
Trajectory-level GRPO is a common approach for training multi-step GUI agents, but repeatedly rolling out complete trajectories from the task root can be inefficient: task-level rewards provide coarse supervision over which intermediate decisions require improvement, while already-mastered prefixes are repeatedly re-executed before reaching difficult states. We introduce a two-stage adaptive training framework that jointly addresses where to learn and how far to roll out. We first construct reusable intermediate checkpoints from successful expert trajectories and select informative pivots using action disagreement, which measures uncertainty directly from sampled GUI actions. Stage I performs one-step RL at these pivots to improve uncertain local decisions. Stage II then progressively expands policy responsibility through adaptive Local, Suffix, and Root training according to task progress. Recoverable checkpoints enable repeated training from intermediate states without replaying the preceding trajectory. Across MobileGym and CUA-Gym-Hub, our method reduces environment interaction by 56-61% relative to Vanilla GRPO while improving task performance, demonstrating that jointly allocating training across states and rollout ranges can substantially improve GUI-agent RL efficiency.
View arXiv page View PDF Add to collection
Get this paper in your agent:
hf papers read 2610.39251
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.39251 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.39251 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.39251 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co