嵌入式与物联网系统开发中的技能型AI代理
Skilled AI Agents for Embedded and IoT Systems Development
AI总结:
本文提出技能型AI代理框架与IoT-SkillsBench基准,通过实测验证,展示结构化专家知识在嵌入式编程中的高效性。
摘要:
大型语言模型(LLMs)和代理系统在自动化软件开发中显示出潜力,但将其应用于硬件在环(HIL)嵌入式和物联网(IoT)系统仍具挑战性,因为软件逻辑与物理硬件行为存在紧密耦合。编译成功的代码在部署到真实设备时可能因定时约束、外设初始化要求或硬件特定行为而失败。为解决这一挑战,我们引入了针对HIL嵌入式开发的技能型代理框架,并提出了IoT-SkillsBench基准,该基准系统评估AI代理在真实嵌入式编程环境中的表现。IoT-SkillsBench涵盖三个代表嵌入式平台、23种外设和42个任务,跨越三个难度级别,每个任务在三种代理配置(无技能、LLM生成技能、人类专家技能)下进行评估,并通过真实硬件执行验证。在378次硬件验证实验中,我们展示了结构化专家知识的简洁技能能够实现跨平台的接近完美成功率。
英文摘要:
Large language models (LLMs) and agentic systems have shown promise for automated software development, but applying them to hardware-in-the-loop (HIL) embedded and Internet-of-Things (IoT) systems remains challenging due to the tight coupling between software logic and physical hardware behavior. Code that compiles successfully may still fail when deployed on real devices because of timing constraints, peripheral initialization requirements, or hardware-specific behaviors. To address this challenge, we introduce a skills-based agentic framework for HIL embedded development together with IoT-SkillsBench, a benchmark designed to systematically evaluate AI agents in real embedded programming environments. IoT-SkillsBench spans three representative embedded platforms, 23 peripherals, and 42 tasks across three difficulty levels, where each task is evaluated under three agent configurations (no-skills, LLM-generated skills, and human-expert skills) and validated through real hardware execution. Across 378 hardware validated experiments, we show that concise human-expert skills with structured expert knowledge enable near-perfect success rates across platforms.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。