Evaluating LLM-based Workflows for Switched-Mode Power Supply Design

Large language models (LLMs) have great potential to enhance productivity in many disciplines, such as software engineering. However, it is unclear to what extent they can assist in the design process of electronic circuits. This paper focuses on the application of LLMs to switched-mode power supply (SMPS) design for printed circuit boards (PCBs). We present multiple LLM-based workflows that combine reasoning, retrieval-augmented generation (RAG), and a custom toolkit that enables the LLM to interact with the SPICE circuit simulator to receive physical feedback. Two benchmark experiments are presented to analyze the performance of LLM-based assistants on various design tasks. These include parameter tuning and topology adaption, as well as design optimization of SMPS circuits through optimal catalogue component selection to maximize circuit efficiency or balance multiple objectives like size, ripple, and component loss. Experiment results show that SPICE simulation feedback and current LLM advancements, such as reasoning, significantly increase the solve rate on 269 manually created benchmark tasks from 15% to 91%. Furthermore, our analysis reveals that most parameter tuning design tasks can be solved, while limits remain for certain topology adaption and multi-objective optimization tasks. Our experiments offer insights for improving current concepts, for example by adapting text-based circuit representations.