Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.09819 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913690659323904 |
|---|---|
| author | Jones, Benjamin T. Hähnlein, Felix Zhang, Zihan Ahmad, Maaz Kim, Vladimir Schulz, Adriana |
| author_facet | Jones, Benjamin T. Hähnlein, Felix Zhang, Zihan Ahmad, Maaz Kim, Vladimir Schulz, Adriana |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_09819 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Solver-Aided Hierarchical Language for LLM-Driven CAD Design Jones, Benjamin T. Hähnlein, Felix Zhang, Zihan Ahmad, Maaz Kim, Vladimir Schulz, Adriana Computer Vision and Pattern Recognition Artificial Intelligence Graphics Machine Learning Programming Languages 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. |
| title | A Solver-Aided Hierarchical Language for LLM-Driven CAD Design |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Graphics Machine Learning Programming Languages |
| url | https://arxiv.org/abs/2502.09819 |