ANDROIDGEN: Building an Android Language Agent under Data Scarcity
Lai, Hanyu Gao, Junjie Liu, Xiao Xu, Yifan Zhang, Shudan Dong, Yuxiao Tang, Jie
Lai, Hanyu
Gao, Junjie
Liu, Xiao
Xu, Yifan
Zhang, Shudan
Dong, Yuxiao
Tang, Jie
Supervisor
Department
Natural Language Processing
Embargo End Date
Type
Conference proceeding
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Large language models have opened up a world of possibilities for various NLP tasks, sparking optimism for the future. Despite their potential, LLMs have yet to be widely used as agents on real mobile devices. The main challenge is the need for high-quality data sources. Time constraints and labor intensity often hinder human annotation. On the other hand, existing LLMs exhibit inadequate completion rates and need a robust data filtration strategy. Given these challenges, we develop a framework called ANDROIDGEN to enhance the capabilities of LLM-based agents under data scarcity. In addition, we leverage ANDROIDGEN to collect trajectories given human tasks and train open-source LLMs on these trajectories to develop an open-source mobile agent without manually labeled trajectories. We extensively evaluate ANDROIDGEN with AndroidWorld, AitW, and various popular applications, demonstrating its improvements and revealing potential areas for future improvement. Code, model, and data are available at https://github.com/THUDM/AndroidGen.
Citation
H. Lai et al., “AndroidGen: Building an Android Language Agent under Data Scarcity,” vol. 1, pp. 2727–2749, Aug. 2025, doi: 10.18653/V1/2025.ACL-LONG.138.
Source
Proceedings of the Annual Meeting of the Association for Computational Linguistics
Conference
63rd Annual Meeting of the Association for Computational Linguistics, ACL 2025
Keywords
Android Language Agent, Data Scarcity, Language Model for Apps, Android Intent Generation, Multi-Modal App Interaction, Few-Shot Learning, Task Automation via LLMs, App Environment Simulation
Subjects
Source
63rd Annual Meeting of the Association for Computational Linguistics, ACL 2025
Publisher
Association for Computational Linguistics