用大模型自动开发嵌入式物联网程序，准确率95.7%
EmbedGenius: Towards Automated Software Development for Generic Embedded IoT Systems
- 用大模型+硬件知识库自动处理软硬件依赖
- 71个模块测试中代码准确率达95.7%，任务成功率86.5%
- 适合想快速开发嵌入式系统的开发者和工程师
嵌入式物联网系统开发对实现各类应用的无缝连接与功能至关重要，但该过程复杂，需兼顾软硬件跨领域知识，通常需开发者直接参与，导致劳动密集、耗时且易出错。为此，本文提出EmbedGenius，首个面向通用嵌入式物联网系统的全自动软件开发平台。核心思路是利用大语言模型（LLMs）的推理能力与嵌入式系统专业知识，自动化实现软硬件协同开发。主要方法包括：面向组件的库解析方法解决硬件依赖问题；库知识生成方法将领域知识注入大模型；自动编程方法保障部署成功。我们在71个模块和4个主流嵌入式开发平台上，针对350多个物联网任务评估了EmbedGenius性能。实验结果表明，其代码生成准确率为95.7%，任务完成成功率达86.5%，优于人工介入基线15.6%–37.7%和25.5%–53.4%。案例研究还展示了其在环境监测与远程控制系统开发中的潜力。
原文摘要 · Abstract (English)
Embedded IoT system development is crucial for enabling seamless connectivity and functionality across a wide range of applications. However, such a complex process requires cross-domain knowledge of hardware and software and hence often necessitates direct developer involvement, making it labor-intensive, time-consuming, and error-prone. To address this challenge, this paper introduces EmbedGenius, the first fully automated software development platform for general-purpose embedded IoT systems. The key idea is to leverage the reasoning ability of Large Language Models (LLMs) and embedded system expertise to automate the hardware-in-the-loop development process. The main methods include a component-aware library resolution method for addressing hardware dependencies, a library knowledge generation method that injects utility domain knowledge into LLMs, and an auto-programming method that ensures successful deployment. We evaluate EmbedGenius's performance across 71 modules and four mainstream embedded development platforms with over 350 IoT tasks. Experimental results show that EmbedGenius can generate codes with an accuracy of 95.7% and complete tasks with a success rate of 86.5%, surpassing human-in-the-loop baselines by 15.6%--37.7% and 25.5%--53.4%, respectively. We also show EmbedGenius's potential through case studies in environmental monitoring and remote control systems development.
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。