CAD-Coder: Text-to-CAD Generation with Chain-of-Thought and Geometric Reward

Yandong Guan, Xilin Wang, XiMing Xing, Jing Zhang, Dong Xu, Qian Yu

Keywords: CAD generation, text-to-CAD, LLM

Abstract:

In this work, we introduce CAD-Coder, a novel framework that reformulates text-to-CAD as the generation of CadQuery scripts—a Python-based, parametric CAD language.
This representation enables direct geometric validation, a richer modeling vocabulary, and seamless integration with existing LLMs.
To further enhance code validity and geometric fidelity, we propose a two-stage learning pipeline: (1) supervised fine-tuning on paired text–CadQuery data, and (2) reinforcement learning with Group Reward Policy Optimization (GRPO), guided by a CAD-specific reward comprising both a geometric reward (Chamfer Distance) and a format reward.
We also introduce a chain-of-thought (CoT) planning process to improve model reasoning, and construct a large-scale, high-quality dataset of 110K text–CadQuery–3D model triplets and 1.5K CoT samples via an automated pipeline. Extensive experiments demonstrate that CAD-Coder enables LLMs to generate diverse, valid, and complex CAD models directly from natural language, advancing the state of the art of text-to-CAD generation and geometric reasoning.

Primary Area: Applications (e.g., vision, language, speech and audio, Creative AI)

Submission Number: 7645