JARVIS: A Multi-Agent Code Assistant for High-Quality EDA Script Generation

TL;DR

JARVIS introduces a multi-agent framework utilizing domain-specific LLMs and verification tools to generate high-quality EDA scripts, significantly improving accuracy and reliability in specialized engineering tasks.

Contribution

The paper presents a novel multi-agent system combining LLMs, custom verification, and retrieval mechanisms for high-quality EDA script generation, addressing data scarcity and hallucination issues.

Findings

Outperforms state-of-the-art models in accuracy and reliability

Effectively addresses data scarcity and hallucination in LLMs

Demonstrates potential for LLMs in specialized engineering domains

Abstract

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.