Spec2RTL-Agent：基于LLM代理系统从复杂规范自动生成硬件代码
Spec2RTL-Agent: Automated Hardware Code Generation from Complex Specifications Using LLM Agent Systems
June 16, 2025
作者: Zhongzhi Yu, Mingjie Liu, Michael Zimmer, Yingyan Celine Lin, Yong Liu, Haoxing Ren
cs.AI
摘要
尽管近期在利用大语言模型（LLMs）生成硬件RTL代码方面取得了进展，现有解决方案仍面临实际应用场景与真实世界RTL代码开发需求之间的显著差距。先前的方法要么聚焦于过于简化的硬件描述，要么依赖大量人工指导来处理复杂规格，这限制了其可扩展性和自动化潜力。本文中，我们通过提出一个名为Spec2RTL-Agent的LLM代理系统来弥合这一差距，该系统旨在直接处理复杂的规格文档并生成相应的RTL代码实现，推动基于LLM的RTL代码生成向更实际的应用场景迈进。为实现这一目标，Spec2RTL-Agent引入了一种新颖的多代理协作框架，集成了三大关键赋能模块：(1) 一个推理与理解模块，将规格转化为结构化的、分步实施的计划；(2) 一个渐进式编码与提示优化模块，通过多种表示形式迭代精炼代码，以提升RTL转换的正确性与可综合能力；(3) 一个自适应反思模块，在生成过程中识别并追踪错误来源，确保更稳健的代码生成流程。与直接从自然语言生成RTL不同，我们的系统策略性地生成可综合的C++代码，随后针对高层次综合（HLS）进行优化。这种代理驱动的精炼过程相比直接生成RTL的简单方法，确保了更高的正确性和兼容性。我们在三份规格文档上评估了Spec2RTL-Agent，结果显示其生成的RTL代码准确，且比现有方法减少了高达75%的人工干预。这凸显了其作为首个从非结构化规格到RTL生成的全自动化多代理系统的角色，显著降低了硬件设计中对人力的依赖。
English
Despite recent progress in generating hardware RTL code with 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 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 HLS. This
agent-driven refinement ensures greater correctness and compatibility compared
to naive direct RTL generation approaches. We evaluate Spec2RTL-Agent on three
specification documents, showing it generates accurate RTL code with up to 75%
fewer human interventions than existing methods. This highlights its role as
the first fully automated multi-agent system for RTL generation from
unstructured specs, reducing reliance on human effort in hardware design.