AnalogCoder-Pro: Unifying Analog Circuit Generation and Optimization via Multi-modal LLMs
This addresses automation challenges in analog circuit design for engineers, though it appears incremental as it builds on existing LLM-based methods.
The paper tackled the problem of automating analog front-end design, which relies on expert intuition and iterative simulations, by presenting AnalogCoder-Pro, a multimodal LLM framework that generated and optimized circuits, successfully designing 28 circuits and outperforming existing LLM-based methods on a benchmark suite.
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.