CME-CAD: Heterogeneous Collaborative Multi-Expert Reinforcement Learning for CAD Code Generation

TL;DR

This paper introduces CME-CAD, a novel reinforcement learning paradigm that enhances CAD code generation by integrating multiple expert models, improving accuracy, editability, and scalability in industrial design automation.

Contribution

The paper proposes a new multi-expert reinforcement learning framework for CAD code generation, including a two-stage training process and an open-source benchmark dataset.

Findings

Improved accuracy in CAD model generation.

Enhanced editability and constraint compliance.

Benchmark dataset with 17,299 instances for training and evaluation.

Abstract

Computer-Aided Design (CAD) is essential in industrial design, but the complexity of traditional CAD modeling and workflows presents significant challenges for automating the generation of high-precision, editable CAD models. Existing methods that reconstruct 3D models from sketches often produce non-editable and approximate models that fall short of meeting the stringent requirements for precision and editability in industrial design. Moreover, the reliance on text or image-based inputs often requires significant manual annotation, limiting their scalability and applicability in industrial settings. To overcome these challenges, we propose the Heterogeneous Collaborative Multi-Expert Reinforcement Learning (CME-CAD) paradigm, a novel training paradigm for CAD code generation. Our approach integrates the complementary strengths of these models, facilitating collaborative learning and improving the model's ability to generate accurate, constraint-compatible, and fully editable CAD models. We introduce a two-stage training process: Multi-Expert Fine-Tuning (MEFT), and Multi-Expert Reinforcement Learning (MERL). Additionally, we present CADExpert, an open-source benchmark consisting of 17,299 instances, including orthographic projections with precise dimension annotations, expert-generated Chain-of-Thought (CoT) processes, executable CADQuery code, and rendered 3D models.