@inproceedings{wang-etal-2025-fedmabench,
    title = "{F}ed{MAB}ench: Benchmarking Mobile {GUI} Agents on Decentralized Heterogeneous User Data",
    author = "Wang, WenHao  and
      Yu, Zijie  and
      Ye, Rui  and
      Zhang, Jianqing  and
      Liu, Guangyi  and
      Liu, Liang  and
      Chen, Siheng  and
      Wang, Yanfeng",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1341/",
    pages = "26398--26419",
    ISBN = "979-8-89176-332-6",
    abstract = "Mobile GUI agents have attracted tremendous research participation recently. Traditional approaches to mobile agent training rely on centralized data collection, leading to high cost and limited scalability. Distributed training utilizing federated learning offers an alternative by harnessing real-world user data, providing scalability and reducing costs. However, pivotal challenges, including the absence of standardized benchmarks, hinder progress in this field. To tackle the challenges, we introduce FedMABench, the first benchmark for federated training and evaluation of mobile GUI agents, specifically designed for heterogeneous scenarios. FedMABench features 6 datasets with 30+ subsets, 8 federated algorithms, 10+ base models, and over 800 apps across 5 categories, providing a comprehensive framework for evaluating mobile agents across diverse environments. Through extensive experiments, we uncover several key insights: federated algorithms consistently outperform local training; the distribution of specific apps plays a crucial role in heterogeneity; and, even apps from distinct categories can exhibit correlations during training. FedMABench is publicly available at: https://github.com/wwh0411/FedMABench."
}