A Solver-Aided Hierarchical Language for LLM-Driven CAD Design
This work addresses the challenge of CAD design for users of large language models, particularly those working in fields requiring precise geometric modeling.
The authors tackled the problem of generating procedural geometry in CAD design using large language models, achieving better results than existing methods, particularly in the few-shot regime. AIDL, their proposed domain-specific language, outperformed OpenSCAD in generating visual results closer to the prompt.
Large language models (LLMs) have been enormously successful in solving a wide variety of structured and unstructured generative tasks, but they struggle to generate procedural geometry in Computer Aided Design (CAD). These difficulties arise from an inability to do spatial reasoning and the necessity to guide a model through complex, long range planning to generate complex geometry. We enable generative CAD Design with LLMs through the introduction of a solver-aided, hierarchical domain specific language (DSL) called AIDL, which offloads the spatial reasoning requirements to a geometric constraint solver. Additionally, we show that in the few-shot regime, AIDL outperforms even a language with in-training data (OpenSCAD), both in terms of generating visual results closer to the prompt and creating objects that are easier to post-process and reason about.