Year: 2026
Type: preprint
Abstract: Effectively scaling GUI automation is essential for computer-use agents (CUAs); however, existing work primarily focuses on scaling GUI grounding rather than the more crucial GUI planning, which requires more sophisticated data collection. In reality, the exploration process of a CUA across apps/desktops/web pages typically follows a tree structure, with earlier functional entry points often being explored more frequently. Thus, organizing large-scale trajectories into tree structures can reduce data cost and streamline the data scaling of GUI planning. In this work, we propose TreeCUA to efficiently scale GUI automation with tree-structured verifiable evolution. We propose a multi-agent collaborative framework to explore the environment, verify actions, summarize trajectories, and evaluate quality to generate high-quality and scalable GUI trajectories. To improve efficiency, we devise a novel tree-based topology to store and replay duplicate exploration nodes, and design an adaptive exploration algorithm to balance the depth (\emph{i.e.}, trajectory difficulty) and breadth (\emph{i.e.}, trajectory diversity). Moreover, we develop world knowledge guidance and global memory backtracking to avoid low-quality generation. Finally, we naturally extend and propose the TreeCUA-DPO method from abundant tree node information, improving GUI planning capability by referring to the branch information of adjacent trajectories. Experimental results show that TreeCUA and TreeCUA-DPO offer significant improvements, and out-of-domain (OOD) studies further demonstrate strong generalization. All trajectory node information and code will be available at https://github.com/UITron-hub/TreeCUA.
Source: arXiv (Cornell University)
Authors: Jiang, Deyang, Huang, Jing, Zhao, Xuanle, Chen, Lei, Zheng, Liming, Liu, Fanfan, Qiu, Haibo, Shi, Peng, Zeng, Zhixiong
Institution: Meituan (China)
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7128637383
Cites:
Cited by:
Related to: