CAD-HLLM: Generating Executable CAD from Text with Hierarchical LLM Planning

Zhuo Zuo, Yantao Gan, Junfeng Long, Xianggen Liu
Proceedings of the 17th Asian Conference on Machine Learning, PMLR 304:958-973, 2025.

Abstract

Translating natural language into precise and executable Computer-Aided Design (CAD) programs remains a challenging task, requiring both semantic understanding and geometric fidelity. In this paper, we present CAD-HLLM, a hierarchical LLM framework for structured CAD command generation. Our approach decomposes the task into two stages: a Plan Generator that infers high-level symbolic plans from text, and a Parameter Completor that generates detailed parametric commands conditioned on both the original description and the inferred plan. To enhance robustness, we introduce a lightweight ensemble selection mechanism that ranks and selects among multiple candidates based on model log-likelihoods. Experiments on benchmark datasets show that our method outperforms existing baselines in both parametric precision and 3D shape similarity, demonstrating the effectiveness of hierarchical reasoning and LLM-based planning in bridging the gap between human design intent and executable CAD sequences.

Cite this Paper

BibTeX
@InProceedings{pmlr-v304-zuo25a, title = {CAD-HLLM: Generating Executable CAD from Text with Hierarchical LLM Planning}, author = {Zuo, Zhuo and Gan, Yantao and Long, Junfeng and Liu, Xianggen}, booktitle = {Proceedings of the 17th Asian Conference on Machine Learning}, pages = {958--973}, year = {2025}, editor = {Lee, Hung-yi and Liu, Tongliang}, volume = {304}, series = {Proceedings of Machine Learning Research}, month = {09--12 Dec}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v304/main/assets/zuo25a/zuo25a.pdf}, url = {https://proceedings.mlr.press/v304/zuo25a.html}, abstract = {Translating natural language into precise and executable Computer-Aided Design (CAD) programs remains a challenging task, requiring both semantic understanding and geometric fidelity. In this paper, we present CAD-HLLM, a hierarchical LLM framework for structured CAD command generation. Our approach decomposes the task into two stages: a Plan Generator that infers high-level symbolic plans from text, and a Parameter Completor that generates detailed parametric commands conditioned on both the original description and the inferred plan. To enhance robustness, we introduce a lightweight ensemble selection mechanism that ranks and selects among multiple candidates based on model log-likelihoods. Experiments on benchmark datasets show that our method outperforms existing baselines in both parametric precision and 3D shape similarity, demonstrating the effectiveness of hierarchical reasoning and LLM-based planning in bridging the gap between human design intent and executable CAD sequences.} }
Endnote
%0 Conference Paper %T CAD-HLLM: Generating Executable CAD from Text with Hierarchical LLM Planning %A Zhuo Zuo %A Yantao Gan %A Junfeng Long %A Xianggen Liu %B Proceedings of the 17th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Hung-yi Lee %E Tongliang Liu %F pmlr-v304-zuo25a %I PMLR %P 958--973 %U https://proceedings.mlr.press/v304/zuo25a.html %V 304 %X Translating natural language into precise and executable Computer-Aided Design (CAD) programs remains a challenging task, requiring both semantic understanding and geometric fidelity. In this paper, we present CAD-HLLM, a hierarchical LLM framework for structured CAD command generation. Our approach decomposes the task into two stages: a Plan Generator that infers high-level symbolic plans from text, and a Parameter Completor that generates detailed parametric commands conditioned on both the original description and the inferred plan. To enhance robustness, we introduce a lightweight ensemble selection mechanism that ranks and selects among multiple candidates based on model log-likelihoods. Experiments on benchmark datasets show that our method outperforms existing baselines in both parametric precision and 3D shape similarity, demonstrating the effectiveness of hierarchical reasoning and LLM-based planning in bridging the gap between human design intent and executable CAD sequences.
APA
Zuo, Z., Gan, Y., Long, J. & Liu, X.. (2025). CAD-HLLM: Generating Executable CAD from Text with Hierarchical LLM Planning. Proceedings of the 17th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 304:958-973 Available from https://proceedings.mlr.press/v304/zuo25a.html.

Related Material