AnalogCoder: Analog Circuit Design via Training-Free Code Generation

TL;DR

AnalogCoder is a novel training-free LLM-based tool that automates analog circuit design through Python code, incorporating feedback, modular design, and outperforming existing methods in diverse tasks.

Contribution

It introduces the first training-free LLM agent for analog circuit design, combining feedback, modular libraries, and extensive benchmarking to enhance efficiency and success rate.

Findings

Successfully designed 20 circuits, outperforming GPT-4o by 5 designs.

Outperforms other LLM-based methods on a comprehensive benchmark.

Enables non-experts to efficiently design analog circuits.

Abstract

Analog circuit design is a significant task in modern chip technology, focusing on the selection of component types, connectivity, and parameters to ensure proper circuit functionality. Despite advances made by Large Language Models (LLMs) in digital circuit design, the complexity and scarcity of data in analog circuitry pose significant challenges. To mitigate these issues, we introduce AnalogCoder, the first training-free LLM agent for designing analog circuits through Python code generation. Firstly, AnalogCoder incorporates a feedback-enhanced flow with tailored domain-specific prompts, enabling the automated and self-correcting design of analog circuits with a high success rate. Secondly, it proposes a circuit tool library to archive successful designs as reusable modular sub-circuits, simplifying composite circuit creation. Thirdly, extensive experiments on a benchmark designed to cover a wide range of analog circuit tasks show that AnalogCoder outperforms other LLM-based methods. It has successfully designed 20 circuits, 5 more than standard GPT-4o. We believe AnalogCoder can significantly improve the labor-intensive chip design process, enabling non-experts to design analog circuits efficiently.