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.
@article{arxiv.2508.02518,
title = {AnalogCoder-Pro: Unifying Analog Circuit Generation and Optimization via Multi-modal LLMs},
author = {Yao Lai and Souradip Poddar and Sungyoung Lee and Guojin Chen and Mengkang Hu and Bei Yu and Ping Luo and David Z. Pan},
journal= {arXiv preprint arXiv:2508.02518},
year = {2025}
}