LLM Agent for Fire Dynamics Simulations

TL;DR

This paper introduces FoamPilot, an LLM agent that enhances FireFOAM simulations by providing code insight, case configuration, and simulation evaluation, aiming to streamline fire dynamics modeling for engineers and scientists.

Contribution

The paper presents FoamPilot, a novel LLM-based agent that integrates multiple functionalities to improve usability and efficiency of FireFOAM simulations, especially for less experienced users.

Findings

Effective code insight and summarization for FireFOAM source code.

Successful natural language interpretation for case configuration.

Promising preliminary results in simulation management and analysis.

Abstract

Significant advances have been achieved in leveraging foundation models, such as large language models (LLMs), to accelerate complex scientific workflows. In this work we introduce FoamPilot, a proof-of-concept LLM agent designed to enhance the usability of FireFOAM, a specialized solver for fire dynamics and fire suppression simulations built using OpenFOAM, a popular open-source toolbox for computational fluid dynamics (CFD). FoamPilot provides three core functionalities: code insight, case configuration and simulation evaluation. Code insight is an alternative to traditional keyword searching leveraging retrieval-augmented generation (RAG) and aims to enable efficient navigation and summarization of the FireFOAM source code for developers and experienced users. For case configuration, the agent interprets user requests in natural language and aims to modify existing simulation setups accordingly to support intermediate users. FoamPilot's job execution functionality seeks to manage the submission and execution of simulations in high-performance computing (HPC) environments and provide preliminary analysis of simulation results to support less experienced users. Promising results were achieved for each functionality, particularly for simple tasks, and opportunities were identified for significant further improvement for more complex tasks. The integration of these functionalities into a single LLM agent is a step aimed at accelerating the simulation workflow for engineers and scientists employing FireFOAM for complex simulations critical for improving fire safety.