Automated Generation of Microfluidic Netlists using Large Language Models

TL;DR

This paper demonstrates the use of large language models to automatically generate microfluidic device netlists from natural language descriptions, aiming to make microfluidic design more accessible and automated.

Contribution

It introduces the first practical application of LLMs for converting natural language microfluidic specifications into structural Verilog netlists, bridging a gap in design automation.

Findings

Achieved an average syntactical accuracy of 88% in netlist generation.

Successfully generated netlists for practical microfluidic benchmarks.

Demonstrated feasibility of LLM-based microfluidic design automation.

Abstract

Microfluidic devices have emerged as powerful tools in various laboratory applications, but the complexity of their design limits accessibility for many practitioners. While progress has been made in microfluidic design automation (MFDA), a practical and intuitive solution is still needed to connect microfluidic practitioners with MFDA techniques. This work introduces the first practical application of large language models (LLMs) in this context, providing a preliminary demonstration. Building on prior research in hardware description language (HDL) code generation with LLMs, we propose an initial methodology to convert natural language microfluidic device specifications into system-level structural Verilog netlists. We demonstrate the feasibility of our approach by generating structural netlists for practical benchmarks representative of typical microfluidic designs with correct functional flow and an average syntactical accuracy of 88%.