@inproceedings{xie-etal-2025-droidcall,
    title = "{D}roid{C}all: A Dataset for {LLM}-powered Android Intent Invocation",
    author = "Xie, Weikai  and
      Zhang, Li  and
      Wang, Shihe  and
      Yi, Rongjie  and
      Xu, Mengwei",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.484/",
    doi = "10.18653/v1/2025.findings-emnlp.484",
    pages = "9116--9134",
    ISBN = "979-8-89176-335-7",
    abstract = "The growing capabilities of large language models in natural language understanding significantly strengthen existing agentic systems. To power performant on-device mobile agents for better data privacy, we introduce DroidCall, the first training and testing dataset for accurate Android Intent invocation. With a highly flexible and reusable data generation pipeline, we constructed 10k samples in DroidCall. Given a task instruction in natural language, small language models such as Qwen2.5-3B and Gemma2-2B fine-tuned with DroidCall can approach or even surpass the capabilities of GPT-4o for accurate Android intent invocation. We also provide an end-to-end Android app equipped with these fine-tuned models to demonstrate the Android intent invocation process. The code and dataset are available at https://github.com/UbiquitousLearning/DroidCall"
}