AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents
Yifan Xu, Xiao Liu, Xueqiao Sun, Siyi Cheng, Hao Yu, Hanyu Lai, Shudan Zhang, Dan Zhang
Abstract
Autonomous agents have become increasingly important for interacting with the real world. Android agents, in particular, have been a frequently-mentioned interaction method. However, existing studies for training and evaluating Android agents lack systematic research on both open-source and closed-source models. In this work, we propose AndroidLab as a systematic Android agent framework. It includes an operation environment with different modalities, action space, and a reproducible benchmark. It supports both large language models (LLMs) and multimodal models (LMMs) in the same action space. AndroidLab benchmark includes predefined Android virtual devices and 138 tasks across nine apps built on these devices. By using the AndroidLab environment, we develop an Android Instruction dataset and train six open-source LLMs and LMMs, lifting the average success rates from 4.59% to 21.50% for LLMs and from 1.93% to 13.28% for LMMs. AndroidLab is open-sourced and publicly available at https://github.com/THUDM/Android-Lab.
BibTeX
@inproceedings{xu-etal-2025-androidlab,
title = "{A}ndroid{L}ab: Training and Systematic Benchmarking of Android Autonomous Agents",
author = "Xu, Yifan and
Liu, Xiao and
Sun, Xueqiao and
Cheng, Siyi and
Yu, Hao and
Lai, Hanyu and
Zhang, Shudan and
Zhang, Dan and
Tang, Jie and
Dong, Yuxiao",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.107/",
doi = "10.18653/v1/2025.acl-long.107",
pages = "2144--2166",
ISBN = "979-8-89176-251-0"
}