Zero-to-CAD: Agentic Synthesis of Interpretable CAD Programs at Million-Scale Without Real Data

TL;DR

Zero-to-CAD introduces a scalable method to synthesize and validate millions of CAD construction sequences using a language model within a feedback loop, enabling large-scale, interpretable CAD data generation without real data.

Contribution

It presents a novel agentic search framework embedding LLMs in CAD environments to generate diverse, executable CAD sequences at scale, surpassing existing datasets.

Findings

Synthesized approximately one million CAD sequences.

Fine-tuned a vision-language model to reconstruct CAD from images.

Outperformed strong baselines including GPT-5.2 in CAD reconstruction.

Abstract

Computer-Aided Design (CAD) models are defined by their construction history: a parametric recipe that encodes design intent. However, existing large-scale 3D datasets predominantly consist of boundary representations (B-Reps) or meshes, stripping away this critical procedural information. To address this scarcity, we introduce Zero-to-CAD, a scalable framework for synthesizing executable CAD construction sequences. We frame synthesis as an agentic search problem: by embedding a large language model (LLM) within a feedback-driven CAD environment, our system iteratively generates, executes, and validates code using tools and documentation lookup to promote geometric validity and operation diversity. This agentic approach enables the synthesis of approximately one million executable, readable, editable CAD sequences, covering a rich vocabulary of operations beyond sketch-and-extrude workflows. We also release a curated subset of 100,000 high-quality models selected for geometric diversity. To demonstrate the dataset's utility, we fine-tune a vision-language model on our synthetic data to reconstruct editable CAD programs from multi-view images, outperforming strong baselines, including GPT-5.2, and effectively bootstrapping sequence generation capabilities without real construction-history training data. Zero-to-CAD bridges the gap between geometric scale and parametric interpretability, offering a vital resource for the next generation of CAD AI.