SPICEPilot: Navigating SPICE Code Generation and Simulation with AI Guidance

Deepak Vungarala, Sakila Alam, Arnob Ghosh, Shaahin Angizi
10/27/2024
cs.ARcs.AI

Official code: ACADLab/SPICEPilot (45 stars, MIT, last commit 2026-04-02).

Abstract

Large Language Models (LLMs) have shown great potential in automating code generation; however, their ability to generate accurate circuit-level SPICE code remains limited due to a lack of hardware-specific knowledge. In this paper, we analyze and identify the typical limitations of existing LLMs in SPICE code generation. To address these limitations, we present SPICEPilot a novel Python-based dataset generated using PySpice, along with its accompanying framework. This marks a significant step forward in automating SPICE code generation across various circuit configurations. Our framework automates the creation of SPICE simulation scripts, introduces standardized benchmarking metrics to evaluate LLM's ability for circuit generation, and outlines a roadmap for integrating LLMs into the hardware design process. SPICEPilot is open-sourced under the permissive MIT license at https://github.com/ACADLab/SPICEPilot.git.

View on arXivView PDF

Code Implementations(1)

ACADLab/SPICEPilotOfficial100%
MIT

This repository hosts the information of SPICEPilot: a training free LLM data-augmentation, new bench marking and future road-map.

457PythonOct 22, 20246 months agoMIT
llmllm-frameworkpyspicespice

Similar Papers

NotSoTiny: A Large, Living Benchmark for RTL Code Generation

83% match2025

Classification-Based Automatic HDL Code Generation Using LLMs

83% match2024

EvoVerilog: Large Langugage Model Assisted Evolution of Verilog Code

82% match2025

CktGNN: Circuit Graph Neural Network for Electronic Design Automation

82% match1 repo962026

Automatically Improving LLM-based Verilog Generation using EDA Tool Feedback

81% match2024

Exploring Code Language Models for Automated HLS-based Hardware Generation: Benchmark, Infrastructure and Analysis

81% match2025

Cite this paper

@article{vungarala2024spicepilot,
  title  = {SPICEPilot: Navigating SPICE Code Generation and Simulation with AI Guidance},
  author = {Deepak Vungarala and Sakila Alam and Arnob Ghosh and Shaahin Angizi},
  year   = {2024},
  eprint = {2410.20553},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2410.20553v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2410.20553.svg)](https://codeofpaper.com/paper/2410.20553)

Discussion