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

2026-04-25

AI Summary

This work addresses the limited reusability of design and debugging strategies in existing large language model (LLM)-driven EDA agents, which are typically isolated and task-specific. To overcome this, the authors propose a modular circuit skill library that decouples the digital front-end design flow into six standardized steps, enabling flexible composition through a plug-and-play architecture. A key innovation is the introduction of an embedding-free Agent Skill RAG mechanism that achieves sub-millisecond skill retrieval, combined with an LLM for skill composition reasoning. Evaluated on 41 challenging tasks from VerilogEval v2, the approach attains a Pass@1 score of 0.805 for both single-skill and cross-project compositions, representing an 80.5% improvement over baseline methods and significantly outperforming Hierarchy-Verilog and VerilogCoder, with performance on par with MAGE.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Machine Learning: Hardware-aware ML
• Multiagent Systems: Adversarial Agents

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work

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 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

Problem

• LLM-based EDA
• task-specific systems
• design reuse
• debugging strategies
• front-end design automation

Innovation

• skill-based architecture
• circuit skill
• modular composition
• LLM for EDA
• front-end design automation