Draw it like Euclid: Teaching transformer models to generate CAD profiles using ruler and compass construction steps
Not on the map. Why?
Abstract (arXiv)
We introduce a new method of generating Computer Aided Design (CAD) profiles via a sequence of simple geometric constructions including curve offsetting, rotations and intersections. These sequences start with geometry provided by a designer and build up the points and curves of the final profile step by step. We demonstrate that adding construction steps between the designer's input geometry and the final profile improves generation quality in a similar way to the introduction of a chain of thought in language models. Similar to the constraints in a parametric CAD model, the construction sequences reduce the degrees of freedom in the modeled shape to a small set of parameter values which can be adjusted by the designer, allowing parametric editing with the constructed geometry evaluated to floating point precision. In addition we show that applying reinforcement learning to the construction sequences gives further improvements over a wide range of metrics, including some which were not explicitly optimized.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 23 of its 36 references that are in the map. First posted on arXiv 14 Jan 2026.
Builds on
23 of 36 references.
References · 23
- 2017Proximal Policy Optimization Algorithmscited by 14,441
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
- 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
- 2015Pointer Networkscited by 882
- 2018ABC: A Big CAD Model Dataset For Geometric Deep Learningcited by 339
- 2021DeepCAD: A Deep Generative Network for Computer-Aided Design Modelscited by 266
- 2023ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Modelscited by 184
- 2022SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebookscited by 121
- 2024BrepGen: A B-rep Generative Diffusion Model with Structured Latent Geometrycited by 101
- 2024Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrappingcited by 89
- 2013The Optimal Reward Baseline for Gradient-Based Reinforcement Learningcited by 84
- 2021Computer-Aided Design as Languagecited by 82
11 more
- 2023IconShop: Text-Guided Vector Icon Synthesis with Autoregressive Transformerscited by 73
- 2020SketchGraphs: A Large-Scale Dataset for Modeling Relational Geometry in Computer-Aided Designcited by 72
- 2021SketchGen: Generating Constrained CAD Sketchescited by 68
- 2021Vitruvion: A Generative Model of Parametric CAD Sketchescited by 66
- 2021Engineering Sketch Generation for Computer-Aided Designcited by 49
- 2025CADCrafter: Generating Computer-Aided Design Models from Unconstrained Imagescited by 31
- 2022Chain of Thought Imitation with Procedure Cloningcited by 30
- 2025Seek-CAD: A Self-refined Generative Modeling for 3D Parametric CAD Using Local Inference via DeepSeekcited by 22
- 2025cadrille: Multi-modal CAD Reconstruction with Reinforcement Learningcited by 14
- 2024NeuroNURBS: Learning Efficient Surface Representations for 3D Solidscited by 8
- 2025Aligning Constraint Generation with Design Intent in Parametric CADcited by 8
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2025ReCAD: Reinforcement Learning Enhanced Parametric CAD Model Generation with Vision-Language Models
- 2025A Solver-Aided Hierarchical Language for LLM-Driven CAD Design
- 2024CadVLM: Bridging Language and Vision in the Generation of Parametric CAD Sketches
- 2025From Intent to Execution: Multimodal Chain-of-Thought Reinforcement Learning for Precise CAD Code Generation
- 2026Zero-to-CAD: Agentic Synthesis of Interpretable CAD Programs at Million-Scale Without Real Data
- 2025CADKnitter: Compositional CAD Generation from Text and Geometry Guidance
- 2025Text-to-CadQuery: A New Paradigm for CAD Generation with Scalable Large Model Capabilities
- 2026Memory-Augmented Reinforcement Learning Agent for CAD Generation