ReliCAD: From Uncertain LLM Generation to Reliable Parametric CAD Modeling

Large language models have shown considerable potential for natural-language-driven parametric CAD modeling. However, a fundamental contradiction exists between their probabilistic generation and the deterministic requirements of CAD modeling, resulting in limitations in reliability, design-intent preservation, and geometric validity. Existing methods typically rely on large-scale annotated datasets, lack explicit modeling of design intent, and underutilize the deterministic capabilities of CAD kernels. To address these limitations, we propose ReliCAD, a unified framework that transforms uncertain LLM generation into reliable parametric CAD modeling. Through explicit design-intent modeling, ReliCAD converts user instructions into structured design specifications and explicitly models geometric relations, topological dependencies, and feature construction order. It then generates constraint-aware parametric instructions and invokes the CAD kernel through an Agent-ready API to perform geometric construction, design iteration, and solving. ReliCAD further records runtime evidence and employs reinforcement-feedback mechanisms to ensure consistency between CAD generation and design specifications, thereby enhancing error localization and iterative repair. Experiments on the public HiStCAD generation dataset and our fine-granularity CAD editing dataset demonstrate that ReliCAD significantly outperforms baseline methods, achieving 99.8% validity rate and 0.8753 ground truth recall. ReliCAD provides a verifiable, repeatable, and generalizable approach to natural-language-interactive CAD modeling.