首个用于精准安卓意图调用的LLM训练数据集，提升本地化智能代理性能。
DroidCall: A Dataset for LLM-powered Android Intent Invocation
- 基于灵活生成管道构建1万条自然语言指令样本。
- 微调后的小模型性能接近甚至超越GPT-4o的意图调用准确率。
- 适合研究移动代理、隐私保护智能系统的人群使用。
大型语言模型在自然语言理解方面的进步显著增强了现有智能体系统的能力。为实现更高效且保护数据隐私的本地化移动端智能体，我们提出了DroidCall，这是首个用于精确安卓意图调用的训练与测试数据集。通过高度灵活可复用的数据生成流水线，我们构建了10,000个样本。给定自然语言任务指令，使用DroidCall微调的小型语言模型（如Qwen2.5-3B和Gemma2-2B）在安卓意图调用上的表现可接近甚至超过GPT-4o。我们还提供一个集成微调模型的端到端安卓应用，演示完整的意图调用流程。代码与数据集已公开于https://github.com/UbiquitousLearning/DroidCall。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。