用多智能体系统生成高质量电子设计脚本，解决数据少与幻觉问题。
JARVIS: A Multi-Agent Code Assistant for High-Quality EDA Script Generation
- 构建多智能体框架，融合领域LLM与编译验证机制。
- 在多个基准上准确率和可靠性显著优于现有模型。
- 适合芯片设计工程师及自动化工具开发者参考。
本文提出JARVIS，一种基于大语言模型（LLMs）与领域专业知识的多智能体框架，用于生成高质量的电子设计自动化（EDA）任务脚本。该框架结合领域专用的LLM（通过合成数据训练）、定制编译器实现结构验证与规则执行、代码修复功能以及先进检索机制，在应对数据稀缺与大模型幻觉问题方面表现优异。在多个基准测试中，其生成脚本的准确率与可靠性均显著超越现有领域模型。本工作为LLM在EDA领域的应用树立新范式，推动该方向的技术进步。
原文摘要 · Abstract (English)
This paper presents JARVIS, a novel multi-agent framework that leverages Large Language Models (LLMs) and domain expertise to generate high-quality scripts for specialized Electronic Design Automation (EDA) tasks. By combining a domain-specific LLM trained with synthetically generated data, a custom compiler for structural verification, rule enforcement, code fixing capabilities, and advanced retrieval mechanisms, our approach achieves significant improvements over state-of-the-art domain-specific models. Our framework addresses the challenges of data scarcity and hallucination errors in LLMs, demonstrating the potential of LLMs in specialized engineering domains. We evaluate our framework on multiple benchmarks and show that it outperforms existing models in terms of accuracy and reliability. Our work sets a new precedent for the application of LLMs in EDA and paves the way for future innovations in this field.
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。