Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2602.05429 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915777689419776 |
|---|---|
| author | Lv, Rui Mo, Juncheng Chu, Tianyi Rao, Chen Jing, Hongyi Teng, Jiajie Chen, Jiafu Zhang, Shiqi Ding, Liangzi Fang, Shuo Lin, Huaizhong Dang, Ziqiang Ma, Chenguang Zhao, Lei |
| author_facet | Lv, Rui Mo, Juncheng Chu, Tianyi Rao, Chen Jing, Hongyi Teng, Jiajie Chen, Jiafu Zhang, Shiqi Ding, Liangzi Fang, Shuo Lin, Huaizhong Dang, Ziqiang Ma, Chenguang Zhao, Lei |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_05429 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | M$^2$-Miner: Multi-Agent Enhanced MCTS for Mobile GUI Agent Data Mining Lv, Rui Mo, Juncheng Chu, Tianyi Rao, Chen Jing, Hongyi Teng, Jiajie Chen, Jiafu Zhang, Shiqi Ding, Liangzi Fang, Shuo Lin, Huaizhong Dang, Ziqiang Ma, Chenguang Zhao, Lei Artificial Intelligence Computer Vision and Pattern Recognition 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. |
| title | M$^2$-Miner: Multi-Agent Enhanced MCTS for Mobile GUI Agent Data Mining |
| topic | Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.05429 |