Artificial intelligence orchestration for text-based ultrasonic simulation via self-review by multi-large language model agents

Abstract Widely used ultrasonic simulation systems often rely on complex graphical user interfaces (GUIs) or scripting, resulting in substantial time investments and reduced accessibility for new users. In this study, we propose a novel text-based simulation control architecture, which leverages a l...

Full description

Saved in:
Bibliographic Details
Main Authors: Soyeon Kim, Yonggyun Yu, Hogeon Seo
Format: Article
Language:English
Published: Nature Portfolio 2025-04-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-97498-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850202769050304512
author Soyeon Kim
Yonggyun Yu
Hogeon Seo
author_facet Soyeon Kim
Yonggyun Yu
Hogeon Seo
author_sort Soyeon Kim
collection DOAJ
description Abstract Widely used ultrasonic simulation systems often rely on complex graphical user interfaces (GUIs) or scripting, resulting in substantial time investments and reduced accessibility for new users. In this study, we propose a novel text-based simulation control architecture, which leverages a large language model (LLM) and the ground artificial intelligence (AI) approach to streamline the control of ultrasonic simulation systems. By modularizing the functionalities of the SimNDT program into discrete functions and enabling natural language-based command interpretation, the proposed method reduces the average simulation configuration time by approximately 75%. To further mitigate task failures in scenario generation using the LLM, we introduce the ground AI approach, which employs self-review mechanisms and multi-agent collaboration to improve task completion rates. In particular, when vectorized output lengths deviate from the standard, we regenerate outputs using multiple LLM agents, reducing the scenario generation error rate from 23.89 to 1.48% and enhancing reliability significantly. These advancements underscore the potential of AI-driven methods in reducing operational costs and enhancing reliability in simulation frameworks. By integrating text-based control and Ground AI mechanisms, the proposed approach provides an efficient and scalable alternative to traditional GUI-based control methods, particularly in time-sensitive applications such as digital twin systems.
format Article
id doaj-art-e392358ccb754c5cbaaa0aa731e343c2
institution OA Journals
issn 2045-2322
language English
publishDate 2025-04-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-e392358ccb754c5cbaaa0aa731e343c22025-08-20T02:11:41ZengNature PortfolioScientific Reports2045-23222025-04-0115111410.1038/s41598-025-97498-yArtificial intelligence orchestration for text-based ultrasonic simulation via self-review by multi-large language model agentsSoyeon Kim0Yonggyun Yu1Hogeon Seo2Korea Atomic Energy Research InstituteKorea Atomic Energy Research InstituteKorea Atomic Energy Research InstituteAbstract Widely used ultrasonic simulation systems often rely on complex graphical user interfaces (GUIs) or scripting, resulting in substantial time investments and reduced accessibility for new users. In this study, we propose a novel text-based simulation control architecture, which leverages a large language model (LLM) and the ground artificial intelligence (AI) approach to streamline the control of ultrasonic simulation systems. By modularizing the functionalities of the SimNDT program into discrete functions and enabling natural language-based command interpretation, the proposed method reduces the average simulation configuration time by approximately 75%. To further mitigate task failures in scenario generation using the LLM, we introduce the ground AI approach, which employs self-review mechanisms and multi-agent collaboration to improve task completion rates. In particular, when vectorized output lengths deviate from the standard, we regenerate outputs using multiple LLM agents, reducing the scenario generation error rate from 23.89 to 1.48% and enhancing reliability significantly. These advancements underscore the potential of AI-driven methods in reducing operational costs and enhancing reliability in simulation frameworks. By integrating text-based control and Ground AI mechanisms, the proposed approach provides an efficient and scalable alternative to traditional GUI-based control methods, particularly in time-sensitive applications such as digital twin systems.https://doi.org/10.1038/s41598-025-97498-ySimulationLarge language modelsMulti-agentsNatural language commandsText-based controlAutomation
spellingShingle Soyeon Kim
Yonggyun Yu
Hogeon Seo
Artificial intelligence orchestration for text-based ultrasonic simulation via self-review by multi-large language model agents
Scientific Reports
Simulation
Large language models
Multi-agents
Natural language commands
Text-based control
Automation
title Artificial intelligence orchestration for text-based ultrasonic simulation via self-review by multi-large language model agents
title_full Artificial intelligence orchestration for text-based ultrasonic simulation via self-review by multi-large language model agents
title_fullStr Artificial intelligence orchestration for text-based ultrasonic simulation via self-review by multi-large language model agents
title_full_unstemmed Artificial intelligence orchestration for text-based ultrasonic simulation via self-review by multi-large language model agents
title_short Artificial intelligence orchestration for text-based ultrasonic simulation via self-review by multi-large language model agents
title_sort artificial intelligence orchestration for text based ultrasonic simulation via self review by multi large language model agents
topic Simulation
Large language models
Multi-agents
Natural language commands
Text-based control
Automation
url https://doi.org/10.1038/s41598-025-97498-y
work_keys_str_mv AT soyeonkim artificialintelligenceorchestrationfortextbasedultrasonicsimulationviaselfreviewbymultilargelanguagemodelagents
AT yonggyunyu artificialintelligenceorchestrationfortextbasedultrasonicsimulationviaselfreviewbymultilargelanguagemodelagents
AT hogeonseo artificialintelligenceorchestrationfortextbasedultrasonicsimulationviaselfreviewbymultilargelanguagemodelagents