Automating Monte Carlo simulations in nuclear engineering with domain knowledge-embedded large language model agents

Next-generation nuclear reactor technologies, such as molten salt and fast reactors present complex analytical challenges that require advanced modeling and simulation tools. Yet, traditional workflows for Monte Carlo simulations like FLUKA are labor-intensive and error-prone, relying on manual inpu...

Full description

Saved in:
Bibliographic Details
Main Authors: Zavier Ndum Ndum, Jian Tao, John Ford, Yang Liu
Format: Article
Language:English
Published: Elsevier 2025-09-01
Series:Energy and AI
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666546825000874
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849243020731351040
author Zavier Ndum Ndum
Jian Tao
John Ford
Yang Liu
author_facet Zavier Ndum Ndum
Jian Tao
John Ford
Yang Liu
author_sort Zavier Ndum Ndum
collection DOAJ
description Next-generation nuclear reactor technologies, such as molten salt and fast reactors present complex analytical challenges that require advanced modeling and simulation tools. Yet, traditional workflows for Monte Carlo simulations like FLUKA are labor-intensive and error-prone, relying on manual input file generation and post-processing. This limits scalability and efficiency. In this work, we present AutoFLUKA, a novel framework that leverages domain knowledge-embedded large language models (LLMs) and AI agents to automate the entire FLUKA simulation workflow from input file creation to execution management, and data analysis. AutoFLUKA also integrates Retrieval-Augmented Generation (RAG) and a web-based user-friendly graphical interface, enabling users to interact with the system in real time. Benchmarking against manual FLUKA simulations, AutoFLUKA demonstrated substantial improvements in resolving FLUKA error-related queries, particularly those arising from input file creation and execution. Traditionally, such issues are addressed through expert support on the FLUKA user forum, often resulting in significant delays. The resolution time for these queries was also reduced from several days to under one minute. Additionally, human-induced simulation errors were mitigated, and a high accuracy in key simulation metrics, such as neutron fluence and microdosimetric quantities, was achieved, with uncertainties below 0.001 % for large sample sizes. The flexibility of AutoFLUKA was demonstrated through successful application to both general and specialized nuclear scenarios, and its design allows for straightforward extension to other simulation platforms. These results highlight AutoFLUKA’s potential to transform nuclear engineering analysis by enhancing productivity, reliability, and accessibility through AI-driven automation.
format Article
id doaj-art-66792e6c070b44cab5c4554cb5f6d71f
institution Kabale University
issn 2666-5468
language English
publishDate 2025-09-01
publisher Elsevier
record_format Article
series Energy and AI
spelling doaj-art-66792e6c070b44cab5c4554cb5f6d71f2025-08-20T03:59:37ZengElsevierEnergy and AI2666-54682025-09-012110055510.1016/j.egyai.2025.100555Automating Monte Carlo simulations in nuclear engineering with domain knowledge-embedded large language model agentsZavier Ndum Ndum0Jian Tao1John Ford2Yang Liu3Department of Nuclear Engineering, Texas A&M University, United StatesCollege of Performance, Visualization & Fine Arts, Texas A&M University, United StatesDepartment of Nuclear Engineering, Texas A&M University, United StatesDepartment of Nuclear Engineering, Texas A&M University, United States; Corresponding author.Next-generation nuclear reactor technologies, such as molten salt and fast reactors present complex analytical challenges that require advanced modeling and simulation tools. Yet, traditional workflows for Monte Carlo simulations like FLUKA are labor-intensive and error-prone, relying on manual input file generation and post-processing. This limits scalability and efficiency. In this work, we present AutoFLUKA, a novel framework that leverages domain knowledge-embedded large language models (LLMs) and AI agents to automate the entire FLUKA simulation workflow from input file creation to execution management, and data analysis. AutoFLUKA also integrates Retrieval-Augmented Generation (RAG) and a web-based user-friendly graphical interface, enabling users to interact with the system in real time. Benchmarking against manual FLUKA simulations, AutoFLUKA demonstrated substantial improvements in resolving FLUKA error-related queries, particularly those arising from input file creation and execution. Traditionally, such issues are addressed through expert support on the FLUKA user forum, often resulting in significant delays. The resolution time for these queries was also reduced from several days to under one minute. Additionally, human-induced simulation errors were mitigated, and a high accuracy in key simulation metrics, such as neutron fluence and microdosimetric quantities, was achieved, with uncertainties below 0.001 % for large sample sizes. The flexibility of AutoFLUKA was demonstrated through successful application to both general and specialized nuclear scenarios, and its design allows for straightforward extension to other simulation platforms. These results highlight AutoFLUKA’s potential to transform nuclear engineering analysis by enhancing productivity, reliability, and accessibility through AI-driven automation.http://www.sciencedirect.com/science/article/pii/S2666546825000874Advanced nuclear energyMonte Carlo simulationsFLUKA codeLarge language model agentsRetrieval Augmented GenerationGenerative AI
spellingShingle Zavier Ndum Ndum
Jian Tao
John Ford
Yang Liu
Automating Monte Carlo simulations in nuclear engineering with domain knowledge-embedded large language model agents
Energy and AI
Advanced nuclear energy
Monte Carlo simulations
FLUKA code
Large language model agents
Retrieval Augmented Generation
Generative AI
title Automating Monte Carlo simulations in nuclear engineering with domain knowledge-embedded large language model agents
title_full Automating Monte Carlo simulations in nuclear engineering with domain knowledge-embedded large language model agents
title_fullStr Automating Monte Carlo simulations in nuclear engineering with domain knowledge-embedded large language model agents
title_full_unstemmed Automating Monte Carlo simulations in nuclear engineering with domain knowledge-embedded large language model agents
title_short Automating Monte Carlo simulations in nuclear engineering with domain knowledge-embedded large language model agents
title_sort automating monte carlo simulations in nuclear engineering with domain knowledge embedded large language model agents
topic Advanced nuclear energy
Monte Carlo simulations
FLUKA code
Large language model agents
Retrieval Augmented Generation
Generative AI
url http://www.sciencedirect.com/science/article/pii/S2666546825000874
work_keys_str_mv AT zavierndumndum automatingmontecarlosimulationsinnuclearengineeringwithdomainknowledgeembeddedlargelanguagemodelagents
AT jiantao automatingmontecarlosimulationsinnuclearengineeringwithdomainknowledgeembeddedlargelanguagemodelagents
AT johnford automatingmontecarlosimulationsinnuclearengineeringwithdomainknowledgeembeddedlargelanguagemodelagents
AT yangliu automatingmontecarlosimulationsinnuclearengineeringwithdomainknowledgeembeddedlargelanguagemodelagents