Iterative Diagnosis-Driven Augmented Generation (IDDAG) for Programmatic 3D CAD

Thomas Paviot, Virginie Fortineau, Samir Lamouri, Samir Lamouri

2025

Abstract

This paper presents a novel approach for automated generation of 3D CAD models using Large Language Models (LLMs) within Model-Based Systems Engineering workflows. We introduce Iterative Diagnosis-Driven Augmented Generation (IDDAG), a methodology combining programmatic geometry creation with systematic diagnostic feedback. The approach leverages a dedicated API for exact Boundary Representation (B-Rep) geometry generation, augmented by a closed-loop architecture that provides iterative refinement based on syntactic, runtime, and geometric analysis. Unlike existing methods requiring extensive training datasets or producing approximate geometries, our solution generates topologically valid, parameterized models while maintaining traceability to engineering requirements. Results demonstrate progressive geometric refinement across iterations, with the diagnostic feedback mechanism effectively identifying and correcting topological inconsistencies.

Paper Citation

in Harvard Style

Paviot T., Fortineau V. and Lamouri S. (2025). Iterative Diagnosis-Driven Augmented Generation (IDDAG) for Programmatic 3D CAD. 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 474-480. DOI: 10.5220/0013443500003896

in Bibtex Style

@conference{mbse-ai integration25,
author={Thomas Paviot and Virginie Fortineau and Samir Lamouri},
title={Iterative Diagnosis-Driven Augmented Generation (IDDAG) for Programmatic 3D CAD},
booktitle={Proceedings of the 13th International Conference on Model-Based Software and Systems Engineering - Volume 1: MBSE-AI Integration},
year={2025},
pages={474-480},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013443500003896},
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 - Iterative Diagnosis-Driven Augmented Generation (IDDAG) for Programmatic 3D CAD
SN - 978-989-758-729-0
AU - Paviot T.
AU - Fortineau V.
AU - Lamouri S.
PY - 2025
SP - 474
EP - 480
DO - 10.5220/0013443500003896
PB - SciTePress