Bridges the gap between parametric CAD and direct B-Rep synthesis using LLMs and primitive grounding.
arXiv · March 13, 2026 · 2603.11831
Why it matters
It enables high-fidelity, executable CAD generation for industrial design by allowing LLMs to ground natural language selections to geometric primitives. This overcomes the paradigm gap that previously limited AI-driven CAD to simple shapes or non-parametric models.
From the abstract
The field of Computer-Aided Design (CAD) generation has made significant progress in recent years. Existing methods typically fall into two separate categorie: parametric CAD modeling and direct boundary representation (B-Rep) synthesis. In modern feature-based CAD systems, parametric modeling and B-Rep are inherently intertwined, as advanced parametric operations (e.g., fillet and chamfer) require explicit selection of B-Rep geometric primitives, and the B-Rep itself is derived from parametric