Optimization through In-Context Learning and Iterative LLM Prompting for Nuclear Engineering Design Problems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Oktavian, M. Rizki, Tunga, Anirudh, Bakshi, Amandeep, Mueterthies, Michael J., Gruenwald, J. Thomas, Nistor, Jonathan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912293239914496
author Oktavian, M. Rizki
Tunga, Anirudh
Bakshi, Amandeep
Mueterthies, Michael J.
Gruenwald, J. Thomas
Nistor, Jonathan
author_facet Oktavian, M. Rizki
Tunga, Anirudh
Bakshi, Amandeep
Mueterthies, Michael J.
Gruenwald, J. Thomas
Nistor, Jonathan
contents The optimization of nuclear engineering designs, such as nuclear fuel assembly configurations, involves managing competing objectives like reactivity control and power distribution. This study explores the use of Optimization by Prompting, an iterative approach utilizing large language models (LLMs), to address these challenges. The method is straightforward to implement, requiring no hyperparameter tuning or complex mathematical formulations. Optimization problems can be described in plain English, with only an evaluator and a parsing script needed for execution. The in-context learning capabilities of LLMs enable them to understand problem nuances, therefore, they have the potential to surpass traditional metaheuristic optimization methods. This study demonstrates the application of LLMs as optimizers to Boiling Water Reactor (BWR) fuel lattice design, showing the capability of commercial LLMs to achieve superior optimization results compared to traditional methods.
format Preprint
id arxiv_https___arxiv_org_abs_2503_19620
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Optimization through In-Context Learning and Iterative LLM Prompting for Nuclear Engineering Design Problems
Oktavian, M. Rizki
Tunga, Anirudh
Bakshi, Amandeep
Mueterthies, Michael J.
Gruenwald, J. Thomas
Nistor, Jonathan
Machine Learning
Computational Physics
The optimization of nuclear engineering designs, such as nuclear fuel assembly configurations, involves managing competing objectives like reactivity control and power distribution. This study explores the use of Optimization by Prompting, an iterative approach utilizing large language models (LLMs), to address these challenges. The method is straightforward to implement, requiring no hyperparameter tuning or complex mathematical formulations. Optimization problems can be described in plain English, with only an evaluator and a parsing script needed for execution. The in-context learning capabilities of LLMs enable them to understand problem nuances, therefore, they have the potential to surpass traditional metaheuristic optimization methods. This study demonstrates the application of LLMs as optimizers to Boiling Water Reactor (BWR) fuel lattice design, showing the capability of commercial LLMs to achieve superior optimization results compared to traditional methods.
title Optimization through In-Context Learning and Iterative LLM Prompting for Nuclear Engineering Design Problems
topic Machine Learning
Computational Physics
url https://arxiv.org/abs/2503.19620