Large Language Models (LLMs) have demonstrated impressive capabilities in a wide range of code generation tasks. However, generating code for certain domains remains challenging. One such domain is Computer-Aided Design (CAD) program, where the goal is to produce scripted parametric models that define object geometry for precise design and manufacturing applications. A key challenge in LLM-based CAD program generation is the limited geometric complexity of generated shapes compared to those found in real-world industrial designs. This shortfall is in part due to the lack of diversity in the available CAD program training data. To address this, we propose a novel data augmentation paradigm that prompts an LLM to generate CAD programs conditioned on a reference surface program and a modeling procedure - an idea inspired by practices in industrial design. By varying the reference surface using a collection of organic shapes, our method enriches the geometric distribution of generated CAD models. In particular, it introduces edges and faces defined by spline-based curvature, which are typically missing or underrepresented in existing open-source CAD program datasets. Experiments show that our method produces CAD samples with significantly greater geometric diversity and a higher resemblance to industry-grade CAD designs in terms of the proportion of organic shape primitives. This enhancement makes our CAD data augmentation approach a useful tool for training LLMs and other deep learning models in CAD generation.
Figures & tables
Figure 1: It is common to use a reference surface to guide CAD creation for specific design intent, e.g., compatibility to other component. Motivated by this idea, we propose to a new design procedure prompting to guide the CAD program generation toward more organic shapes.
Figure 2: System overview: (1) Design procedure prompting takes a design description and a reference surface program as an input to formulate the design procedure. (2) The design prompt then condition an LLM to generate a CAD program. (3) Program validation executes the generated program to visualize a CAD Brep. (4) Structure validation checks the validity of the CAD Brep.
Bracket Data
Industry
DeepCAD-b
GenCAD*
CAD-MLLM*
Ours
avg. #lines (STEP)
10099
1783
991
2402
4494
avg. #faces
82.91
21.48
12.55
28.65
26.57
avg. #curves
259.4
50.30
27.86
69.26
67.57
w/ B-Spline faces
100%
0%
0%
0%
77%
w/ B-Spline curves
100%
1%
1%
1%
89%
B-Spline Ratio
0.5352
0.0004
0.0009
0.0008
0.2217
Table 1: A comparison of geometric properties with a commercial industry bracket dataset and baseline CAD program datasets DeepCAD-b, GenCAD and CAD-MLLM. (*) indicates that the data also include non-bracket objects.
Figure 3: Distribution of B-Spline ratio over data samples: Industry, DeepCAD-b and ours only contain bracket data. ABC, GenCAD and CAD-MLLM include brackets and other objects.
Figure 4: Examples of CAD B-rep visualization of our approach using reference surfaces, and the alternatives (-RT) and (-R) excluding reference surfaces. (-R) include a text guidance to prompt smooth and organic shapes. Ours with reference surfaces can generate more B-Spline shapes.
Approach
Ours(-RT)
Ours(-R)
Ours
avg. #lines (STEP)
1225
2992
4494
avg. #faces
14.86
34.56
26.57
avg. #curves
35.17
75.89
67.57
w/ B-Spline faces
2%
18%
77%
w/ B-Spline curves
6%
27%
89%
B-Spline Ratio
0.0085
0.0478
0.2217
Table 2: An ablation study of our approach, testing the alternative prompts (-RT) and (-R) without using reference surfaces.
Figure 5: Visualization of the generated program modules. The left side of each column is a generated bracket with its reference surface, and the right side is the bracket after the reference surface is removed.
Figure 6: Examples of generated wheels. The top row are the program visualization. The bottom row are the CAD Breps. Reference surfaces are used to generate the two wheels in the bottom right.
Approach
Ours(-RT)
Ours(-R)
Ours
require > 5 iterations
12%
18%
21%
Table 3: The proportion of generated data that requires more than 5 iterations of re-generation due to program execution errors or structure validation failures.
Automatic generation of computer-aided design (CAD) models is a core technology for enabling intelligence in advanced manufacturing. Existing generation methods based on large language models (LLMs) often fall short when handling complex CAD models characterized by long operation sequences, diverse operation types, and strong geometric constraints, primarily because reasoning chains break and effective error-correction mechanisms are lacking. To address this problem, this paper proposes a memory-augmented reinforcement learning framework for CAD generation agents. The framework encapsulates the underlying geometric kernel into a structured toolchain callable by the agent and builds a closed-loop mechanism of design intent understanding, global planning, execution, and multi-dimensional verification. It also designs a dual-track memory module consisting of a case library and a skill library, and proposes a dynamic utility retrieval algorithm. By introducing reinforcement learning into retrieval and policy optimization, the agent can effectively avoid retrieval traps in which examples are semantically similar but geometrically infeasible, enabling online self-correction and continual evolution without additional large-scale annotated data. Experiments show that the proposed method significantly improves both the success rate and geometric consistency on complex CAD model generation tasks.
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.
Mohammadmehdi Ataei, Farzaneh Askari, Kamal Rahimi Malekshan +1
The field of Computer-Aided Design (CAD) generation has made significant progress in recent years. Existing methods typically fall into two separate categories: parametric CAD modeling and direct boundary representation (B-Rep) synthesis. In modern feature-based CAD systems, parametric modeling and B-Rep are inherently intertwined, as advanced parametric operations (e.g., fillet and chamfer) require explicit selection of B-Rep geometric primitives, and the B-Rep itself is derived from parametric operations. Consequently, this paradigm gap remains a critical factor limiting AI-driven CAD modeling for complex industrial product design. This paper presents FutureCAD, a novel text-to-CAD framework that leverages large language models (LLMs) and a B-Rep grounding transformer (BRepGround) for high-fidelity CAD generation. Our method generates executable CadQuery scripts, and introduces a text-based query mechanism that enables the LLM to specify geometric selections via natural language, which BRepGround then grounds to the target primitives. To train our framework, we construct a new dataset comprising real-world CAD models. For the LLM, we apply supervised fine-tuning (SFT) to establish fundamental CAD generation capabilities, followed by reinforcement learning (RL) to improve generalization. Experiments show that FutureCAD achieves state-of-the-art CAD generation performance. Code and dataset are available at: https://github.com/JohanStackk/FutureCAD