M$^2$-Miner: Multi-Agent Enhanced MCTS for Mobile GUI Agent Data Mining

2026-02-05

AI Summary

This work addresses the challenges of high data cost, low quality, and insufficient diversity in training mobile GUI agents by proposing a multi-agent enhanced Monte Carlo Tree Search (MCTS) framework for automated data mining. The framework leverages collaborative exploration among an InferAgent, an OrchestraAgent, and a JudgeAgent, integrating an intent reuse mechanism and a progressive model-in-the-loop training strategy to efficiently generate high-quality, diverse user interaction trajectories. GUI agents fine-tuned on the mined data achieve state-of-the-art performance across multiple mainstream mobile GUI benchmarks, demonstrating significant improvements in both data efficiency and task generalization capability.

Technology Category

• Multiagent Systems: Multiagent Learning
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Humans and AI: Intelligent User Interfaces

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

Graphical User Interface (GUI) agent is pivotal to advancing intelligent human-computer interaction paradigms. Constructing powerful GUI agents necessitates the large-scale annotation of high-quality user-behavior trajectory data (i.e., intent-trajectory pairs) for training. However, manual annotation methods and current GUI agent data mining approaches typically face three critical challenges: high construction cost, poor data quality, and low data richness. To address these issues, we propose M$^2$-Miner, the first low-cost and automated mobile GUI agent data-mining framework based on Monte Carlo Tree Search (MCTS). For better data mining efficiency and quality, we present a collaborative multi-agent framework, comprising InferAgent, OrchestraAgent, and JudgeAgent for guidance, acceleration, and evaluation. To further enhance the efficiency of mining and enrich intent diversity, we design an intent recycling strategy to extract extra valuable interaction trajectories. Additionally, a progressive model-in-the-loop training strategy is introduced to improve the success rate of data mining. Extensive experiments have demonstrated that the GUI agent fine-tuned using our mined data achieves state-of-the-art performance on several commonly used mobile GUI benchmarks. Our work will be released to facilitate the community research.

Problem

• GUI agent
• data mining
• user-behavior trajectory
• data annotation
• mobile GUI

Innovation

• Multi-Agent MCTS
• GUI Agent Data Mining
• Intent Recycling
• Model-in-the-Loop Training
• Mobile GUI Automation