Spec2RTL-Agent: Automated Hardware Code Generation from Complex Specifications Using LLM Agent Systems
Zhongzhi Yu, Mingjie Liu, Michael Zimmer, Yingyan Celine, Yong Liu, Haoxing Ren
Abstract
Despite recent progress in generating hardware register transfer level (RTL) code with large language models (LLMs), existing solutions still suffer from a substantial gap between practical application scenarios and the requirements of real-world RTL code development. Prior approaches either focus on overly simplified hardware descriptions or depend on extensive human guidance to process complex specifications, limiting their scalability and automation potential. In this paper, we address this gap by proposing an LLM agent system, termed Spec2RTL-Agent, designed to directly process complex specification documentation and generate corresponding RTL code implementations, advancing LLM-based RTL code generation toward more realistic application settings. To achieve this goal, Spec2RTL-Agent introduces a novel multi-agent collaboration framework that integrates three key enablers: (1) a reasoning and understanding module that translates specifications into structured, step-by-step implementation plans; (2) a progressive coding and prompt optimization module that iteratively refines the code across multiple representations (pseudocode, Python, and C++) to enhance correctness and synthesisability for RTL conversion; and (3) an adaptive reflection module that identifies and traces the source of errors during generation, ensuring a more robust code generation flow. Instead of directly generating RTL from natural language, our system strategically generates synthesizable C++ code, which is then optimized for high-level synthesis (HLS). This agent-driven refinement ensures greater correctness and compatibility compared to naive direct RTL generation approaches. We evaluate Spec2RTL-Agent on a benchmark of three specification documents, demonstrating its effectiveness in generating accurate RTL code with as much as 75% fewer human interventions compared to existing approaches. These results underscore Spec2RTL-Agent’s role as the first fully automated multi-agent system for RTL generation from unstructured specification documents, reducing the reliance on human effort and expertise in hardware design.