AnalogCoder-Pro: Unifying Analog Circuit Generation and Optimization via Multi-modal LLMs

TL;DR

AnalogCoder-Pro introduces a multimodal LLM framework that automates analog circuit design and optimization by integrating simulation feedback, reusable components, and Bayesian optimization, significantly advancing automation in analog front-end design.

Contribution

It presents a novel multimodal LLM framework that unifies circuit generation, error correction, and optimization, outperforming existing methods on diverse circuit benchmarks.

Findings

Designed 28 circuits across 13 types with high success rate.

Outperformed existing LLM-based methods in key performance metrics.

Enabled end-to-end automation from specifications to optimized designs.

Abstract

Despite recent advances, analog front-end design still relies heavily on expert intuition and iterative simulations, which limits the potential for automation. We present AnalogCoder-Pro, a multimodal large language model (LLM) framework that integrates generative and optimization techniques. The framework features a multimodal diagnosis-and-repair feedback loop that uses simulation error messages and waveform images to autonomously correct design errors. It also builds a reusable circuit tool library by archiving successful designs as modular subcircuits, accelerating the development of complex systems. Furthermore, it enables end-to-end automation by generating circuit topologies from target specifications, extracting key parameters, and applying Bayesian optimization for device sizing. On a curated benchmark suite covering 13 circuit types, AnalogCoder-Pro successfully designed 28 circuits and consistently outperformed existing LLM-based methods in figures of merit.