TL;DR
LEGO is a modular platform that decomposes front-end design into skills, enabling effective LLM-based RTL automation with significant performance improvements demonstrated on challenging problems.
Contribution
It introduces a unified, skill-based platform for front-end design generation, with automated skill extraction and high-performance LLM-based design automation.
Findings
Pass@1 increased from 0.000 to 0.805 using LEGO skills
Outperforms hierarchy-verilog and VerilogCoder in benchmarks
Achieves submillisecond retrieval without embedding models
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
