SPICEAssistant: LLM using SPICE Simulation Tools for Schematic Design of Switched-Mode Power Supplies

2025-07-14

AI Summary

This study investigates the applicability and limitations of large language models (LLMs) in switch-mode power supply (SMPS) printed circuit board (PCB) design, with particular focus on their ability to interpret SPICE simulation results and perform multi-step, closed-loop design optimization. Method: We propose SPICEAssistant—a tool-augmented LLM framework enabling active invocation of SPICE simulators, parsing of netlists and waveform outputs, and iterative parameter refinement guided by simulation feedback. The framework supports end-to-end automation from natural-language specifications to netlist generation, simulation-driven correction, and PCB-level design convergence. Contribution/Results: Evaluated on a 256-task benchmark, SPICEAssistant achieves a 38% accuracy improvement over the GPT-4o baseline. Results demonstrate that integrating simulation-based feedback into the LLM’s reasoning loop is critical for enhancing electronic design inference, decision-making, and physical implementation fidelity.

Technology Category

Machine Learning: Large Multimodal Models (LMMs)Natural Language Processing: (Large) Language ModelsSearch and Optimization: Sampling/Simulation-based Search

Application Category

Economics, Online Markets and Human Computation: Cost models of using LLMs in production systemsSearch and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved informationUser Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

State-of-the-art large language models (LLMs) show high performance across a wide range of tasks in many domains of science. In the field of electronic design automation (EDA), it is yet to be determined to what extent they are capable to understand, adapt, and dimension electronic circuits. This paper focuses on the application of LLMs to switched-mode power supply (SMPS) design on printed circuit boards (PCBs). Particular challenges for LLMs in this context include their limited ability to interpret results from key simulation tools like SPICE and the multi-step design process. To address these challenges, we suggest SPICEAssistant, a framework that provides a broad selection of tools to an LLM. The tools serve as an interface to SPICE, allowing the LLM to interact flexibly with the simulator to estimate the impact of its modifications to the circuit. To evaluate the performance of SPICEAssistant, we defined a benchmark consisting of 256 questions testing the ability to adapt circuit netlists to fulfil different SMPS design tasks. The benchmarking results show that simulation feedback effectively improves SMPS design capabilities of LLMs. An increasing number of simulation iterations leads to enhanced performance. The SPICEAssistant framework significantly outperforms the standalone LLM GPT-4o on the benchmark by approximately 38%.

Problem

• LLMs struggle with SPICE simulation interpretation in SMPS design
• Multi-step SMPS design challenges LLMs' circuit adaptation ability
• Standalone LLMs lack tools for iterative SPICE-based circuit optimization

Innovation

• LLM integrates SPICE for circuit simulation
• Framework enhances SMPS design via feedback
• Simulation iterations boost LLM performance significantly