用可组合的电路技能模块化设计前端，让大模型更高效生成硬件代码。
LEGO: An LLM Skill-Based Front-End Design Generation Platform
- 将前端设计拆为六步，每步封装为可插拔的标准化电路技能。
- 在41个难题上，通过技能组合将通过率从0提升至80.5%。
- 适合做芯片前端自动化、大模型硬件编程的研究者和工程师。
现有基于大模型的EDA代理多为孤立的任务特定系统，导致重复工程投入且成功的设计与调试策略难以复用。本文提出LEGO，一个统一的基于技能的前端设计生成平台。该平台将数字前端流程分解为六个独立步骤，并将每个代理能力表示为插件式架构中的标准化可组合电路技能。为构建技能库，我们调研了100多篇论文，选取11个代表性开源项目，提取出42个可在六步有限状态机框架内执行的电路技能。电路技能构建器实现了线性可扩展的技能自动化提取；代理技能RAG在不依赖嵌入模型的前提下实现亚毫秒级检索。在VerilogEval v2中41个高难度问题（GPT-5.2-Codex在极高推理成本下仍无法解决）上的实证评估显示，使用LEGO构建的单个电路技能使Pass@1从0提升至0.805，较基线提高80.5%。跨项目技能组合也达到0.805的Pass@1，优于Hierarchy-Verilog 14.6%，优于VerilogCoder 2.5%，并媲美MAGE。结果表明，模块化技能组合能有效支持灵活的RTL设计自动化。LEGO平台及所有电路技能已公开于GitHub：https://github.com/loujc/LEGO-An-LLM-Skill-Based-Front-End-Design-Generation-Platform。
原文摘要 · Abstract (English)
Existing LLM-based EDA agents are often isolated task-specific systems. This leads to repeated engineering effort and limited reuse of successful design and debugging strategies. We present LEGO, a unified skill-based platform for front-end design generation. It decomposes the digital front-end flow into six independent steps and represents every agent capability as a standardized composable circuit skill within a plug-and-play architecture. To build this skill library, we survey more than 100 papers, select 11 representative open-source projects, and extract 42 executable circuit skills within a six-step finite state machine formulation. Circuit Skill Builder automates skill extraction with linear scalability. Agent Skill RAG achieves submillisecond retrieval without relying on embedding models. Empirical evaluation on a hard subset of 41 VerilogEval v2 problems that gpt-5.2-codex fails to solve under extra-high reasoning effort shows that individual circuit skills constructed within LEGO raise Pass@1 from 0.000 to 0.805. This is an 80.5% gain over the baseline. Cross-project skill compositions also reach 0.805 Pass@1. They outperform hierarchy-verilog by 14.6% and VerilogCoder by 2.5%. They also match MAGE. These results show that modular skill composition supports both effective and flexible RTL design automation. The LEGO platform and all circuit skills are publicly available at GitHub: https://github.com/loujc/LEGO-An-LLM-Skill-Based-Front-End-Design-Generation-Platform
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。