Ontology-Driven LLM Assistance for Task-Oriented Systems Engineering

Jean-Marie Gauthier, Eric Jenn, Ramon Conejo

2025

Abstract

This paper presents an LLM-based assistant integrated within an experimental modelling platform to support Systems Engineering tasks. Leveraging an ontology-driven approach, the assistant guides engineers through Systems Engineering tasks using an iterative prompting technique that builds task-specific context from prior steps. Our approach combines prompt engineering, few-shot learning, Chain of Thought reasoning, and Retrieval-Augmented Generation to generate accurate and relevant outputs without fine-tuning. A dual-chatbot system aids in task completion. The evaluation of the assistant’s effectiveness in the development of a robotic system demonstrates its potential to enhance Systems Engineering process efficiency and support decision-making.

Paper Citation

in Harvard Style

Gauthier J., Jenn E. and Conejo R. (2025). Ontology-Driven LLM Assistance for Task-Oriented Systems Engineering. In Proceedings of the 13th International Conference on Model-Based Software and Systems Engineering - Volume 1: MBSE-AI Integration; ISBN 978-989-758-729-0, SciTePress, pages 383-394. DOI: 10.5220/0013441100003896

in Bibtex Style

@conference{mbse-ai integration25,
author={Jean-Marie Gauthier and Eric Jenn and Ramon Conejo},
title={Ontology-Driven LLM Assistance for Task-Oriented Systems Engineering},
booktitle={Proceedings of the 13th International Conference on Model-Based Software and Systems Engineering - Volume 1: MBSE-AI Integration},
year={2025},
pages={383-394},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013441100003896},
isbn={978-989-758-729-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Model-Based Software and Systems Engineering - Volume 1: MBSE-AI Integration
TI - Ontology-Driven LLM Assistance for Task-Oriented Systems Engineering
SN - 978-989-758-729-0
AU - Gauthier J.
AU - Jenn E.
AU - Conejo R.
PY - 2025
SP - 383
EP - 394
DO - 10.5220/0013441100003896
PB - SciTePress