A Multi-Agent Generative AI Framework for IC Module-Level Verification Automation

TL;DR

This paper introduces a multi-agent AI framework that automates chip verification tasks, significantly improving over traditional methods and single-agent AI approaches in generating verification documents and testbenches.

Contribution

The paper presents a novel multi-agent framework that automates complex verification processes in chip design, addressing limitations of existing single-agent AI methods.

Findings

MAVF outperforms manual methods in verification tasks

MAVF surpasses single-dialogue AI in accuracy and efficiency

Framework effectively handles complex chip modules

Abstract

As large language models demonstrate enormous potential in the field of Electronic Design Automation (EDA), generative AI-assisted chip design is attracting widespread attention from academia and industry. Although these technologies have made preliminary progress in tasks such as code generation, their application in chip verification -- a critical bottleneck in the chip development cycle -- remains at an exploratory stage. This paper proposes an innovative Multi-Agent Verification Framework (MAVF) aimed at addressing the limitations of current single-LLM approaches in complex verification tasks. Our framework builds an automated transformation system from design specifications to testbench through the collaborative work of multiple specialized agents, including specification parsing, verification strategy generation, and code implementation. Through verification experiments on multiple chip modules of varying complexity, results show that MAVF significantly outperforms traditional manual methods and single-dialogue generative AI approaches in verification document parsing and generation, as well as automated testbench generation. This research opens new directions for exploring generative AI applications in verification automation, potentially providing effective approaches to solving the most challenging bottleneck issues in chip design.