TreeCUA: Efficiently Scaling GUI Automation with Tree-Structured Verifiable Evolution

2026-02-10

AI Summary

This work addresses the limitation of existing GUI automation approaches, which predominantly focus on interface element localization yet lack scalable and efficient data support for complex task planning. To overcome this, we propose a multi-agent collaborative framework grounded in a tree-structured trajectory topology, which orchestrates exploration, verification, and summarization through adaptive depth-breadth exploration, world-knowledge guidance, and global memory recall. We further introduce TreeCUA-DPO, a novel algorithm that leverages trajectory branching information to optimize planning policies. Our method significantly enhances GUI task planning performance and demonstrates strong generalization capabilities in out-of-domain scenarios. All trajectory data and code are publicly released to support future research.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Multiagent Systems: Multiagent Planning
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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.

Problem

• GUI automation
• GUI planning
• trajectory scaling
• computer-use agents
• data efficiency

Innovation

• Tree-structured exploration
• Multi-agent collaboration
• Adaptive exploration algorithm
• GUI planning
• TreeCUA-DPO