GOPR-CAD improves text to CAD model generation accuracy and structure
GOPR-CAD: Graph-of-Operations Progressive Reasoning for CAD Generation
Artificial Intelligence
Summary
Creating precise 3D models for machines requires expert knowledge and careful design. Writing computer code to make these models from text is tricky because errors can appear in complex details but may not be obvious in the final image. The authors developed GOPR-CAD, a method that builds CAD models step-by-step using a graph of operations, reducing mistakes. They tested it on a benchmark of mechanical parts and showed it produces structurally correct models more often than previous methods.
What this means in practice
- •For mechanical design engineers: Generate reliable CAD models from textual descriptions while ensuring structural correctness in standard mechanical parts.
- •For industrial cad software developers: Integrate a modular pipeline that progressively builds and verifies CAD operations to improve program reliability without retraining models.
Authors
Yitian Pang, Yifan Li, Xiaowei Yue, Li Zheng
Abstract
Generating accurate CAD models requires substantial engineering expertise and careful control of geometry, topology, and mechanical constraints. Text-to-CAD aims to simplify this process, but current LLM-based methods often generate CAD programs directly. Language models remain unreliable when producing long code while coordinating coupled geometric, topological, and dimensional constraints. Consequently, executable programs may still produce structurally incorrect models, which execution rate and rendered appearance may fail to reveal. To address these limitations, we propose GOPR-CAD, an agentic Text-to-CAD pipeline based on Graph-of-Operations Progressive Reasoning. A language model acts as a decision agent over encapsulated CAD operations and progressively constructs an executable operation graph, which a deterministic compiler converts into the final CAD model. This separation requires no additional training and supports different language models. To evaluate structural fidelity, we construct MHCAD, a benchmark of 300 standard mechanical part requirements derived from Machinery's Handbook. Their explicit structures enable reference-free STEP/B-rep evaluation. GOPR-CAD achieves 82.7% Structural Yield on MHCAD, and 87.2% Structural Yield on an external CADPrompt subset.