DroidCall: A Dataset for LLM-powered Android Intent Invocation

Weikai Xie, Li Zhang, Shihe Wang, Rongjie Yi, Mengwei Xu
11/30/2024
cs.AI

Official code: UbiquitousLearning/DroidCall (18 stars, MIT, last commit 2025-04-01).

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.

View on arXivView PDF

Code Implementations(1)

UbiquitousLearning/DroidCallOfficial100%
MIT
183Jinja, ShellNov 21, 20241 years agoMIT

Similar Papers

A Contemporary Overview: Trends and Applications of Large Language Models on Mobile Devices

83% match2024

Foundations and Recent Trends in Multimodal Mobile Agents: A Survey

83% match1 repo1582024

AutoDroid-V2: Boosting SLM-based GUI Agents via Code Generation

83% match2024

MobileAgentBench: An Efficient and User-Friendly Benchmark for Mobile LLM Agents

83% match2024

Revolutionizing Mobile Interaction: Enabling a 3 Billion Parameter GPT LLM on Mobile

83% match2023

Your Co-Workers Matter: Evaluating Collaborative Capabilities of Language Models in Blocks World

82% match1 repo22024

Cite this paper

@article{xie2024droidcall,
  title  = {DroidCall: A Dataset for LLM-powered Android Intent Invocation},
  author = {Weikai Xie and Li Zhang and Shihe Wang and Rongjie Yi and Mengwei Xu},
  year   = {2024},
  eprint = {2412.00402},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2412.00402v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2412.00402.svg)](https://codeofpaper.com/paper/2412.00402)

Discussion