用多智能体协作让AI生成可解释的硬件代码，工程师能看懂每一步决策。
RTLSquad: Multi-Agent Based Interpretable RTL Design
- 分三阶段由专用智能体协同完成代码生成与优化
- 生成代码功能正确率高，且在性能功耗面积上表现优异
- 通过对话记录提供决策路径，适合需要可信AI的芯片设计场景
优化寄存器传输级（RTL）代码对提升硬件性能、功耗和面积（PPA）至关重要。大语言模型（LLMs）为自动RTL代码生成与优化提供了新思路。然而，现有方法往往缺乏决策可解释性（即决策有充分且可理解的理由），导致硬件工程师难以信任生成结果，阻碍其融入实际设计流程。为此，我们提出RTLSquad，一种基于LLM的多智能体系统，用于可解释的RTL代码生成。RTLSquad将设计过程分为探索、实现与验证评估三个阶段，由专业智能体小组协同管理，通过智能体间的通信生成优化后的RTL代码，并以通信过程提供决策可解释性。实验表明，RTLSquad在生成功能正确代码和优化PPA性能方面表现卓越，同时具备提供决策路径的能力，验证了该系统的实用价值。
原文摘要 · Abstract (English)
Optimizing Register-Transfer Level (RTL) code is crucial for improving hardware PPA performance. Large Language Models (LLMs) offer new approaches for automatic RTL code generation and optimization. However, existing methods often lack decision interpretability (sufficient, understandable justification for decisions), making it difficult for hardware engineers to trust the generated results, thus preventing these methods from being integrated into the design process. To address this, we propose RTLSquad, a novel LLM-Based Multi-Agent system for interpretable RTL code generation. RTLSquad divides the design process into exploration, implementation, and verification & evaluation stages managed by specialized agent squads, generating optimized RTL code through inter-agent collaboration, and providing decision interpretability through the communication process. Experiments show that RTLSquad excels in generating functionally correct RTL code and optimizing PPA performance, while also having the capability to provide decision paths, demonstrating the practical value of our system.
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。