Papers for

industrial cad software developers

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

GOPR-CAD improves text to CAD model generation accuracy and structure

GOPR-CAD: Graph-of-Operations Progressive Reasoning for CAD Generation

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.

Sun 8 NovArtificial Intelligence
The gist
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.
Open → 2611.11470v1