arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.23355cs.AI
收藏

LEGO: 一个基于LLM技能的前端设计生成平台

LEGO: An LLM Skill-Based Front-End Design Generation Platform

School of IC, Peking University(北京大学集成电路学院);School of EECS, Peking University(北京大学电子信息技术学院);School of Microelectronics, Xidian University(西安电子科技大学微电子学院);Institute of EDA, Peking University(北京大学EDA研究院);Beijing Advanced Innovation Center for IC(北京集成电路先进创新中心)

Jincheng Lou, Ruohan Xu, Jiecheng Ma, Runzhe Tao, Xinyu Qu, Yibo Lin

AI总结:

本文提出LEGO平台,通过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标准化的可组合电路技能,实现了高效的前端设计生成,显著提升了RTL设计自动化的效果。

摘要:

现有的基于LLM的EDA代理往往都是特定任务的孤立系统。这导致了重复的工程努力和成功设计和调试策略的有限重用。我们提出了LEGO,一个统一的基于技能的前端设计生成平台。它将数字前端流程分解为六个独立的步骤,并将每个代理的能力表示为标准化的可组合电路技能,以在即插即用的架构中进行表示。为了构建这个技能库,我们调查了超过100篇论文,选择了11个具有代表性的开源项目,并在六步有限状态机的公式中提取了42个可执行的电路技能。电路技能构建器通过线性可扩展性自动化技能提取。代理技能RAG实现了亚毫秒级检索,而无需依赖嵌入模型。在41个VerilogEval v2问题的严格子集上的实证评估显示,LEGO内构建的单个电路技能将Pass@1从0.000提升到0.805。这比基线提高了80.5%。跨项目技能组合也达到了0.805的Pass@1。它们在层次Verilog上表现更优14.6%,在VerilogCoder上表现更优2.5%。它们还与MAGE相匹配。这些结果表明,模块化技能组合支持有效且灵活的RTL设计自动化。LEGO平台和所有电路技能都在GitHub上公开:https://github.com/loujc/LEGO-An-LLM-Skill-Based-Front-End-Design-Generation-Platform

英文摘要:

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

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑