# From Intent to Execution: Multimodal Chain-of-Thought Reinforcement Learning for Precise CAD Code Generation arXiv: https://arxiv.org/abs/2508.10118 ยท HTML: https://mlsanity.com/paper/2508.10118/ ## Key facts - Cited by 12 papers in the map (data through 14 Oct 2026). - Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. - Builds on 18 of its 31 references that are in the map. - First posted on arXiv 13 Aug 2025. ## Placed in - LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/) ## Builds on (most cited first, 18 of 18) - [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023) - [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017) - [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024) - [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024) - [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025) - [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024) - [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024) - [SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution](https://mlsanity.com/paper/2502.18449/) (2025) - [CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLM](https://mlsanity.com/paper/2411.04954/) (2024) - [SolidGen: An Autoregressive Model for Direct B-rep Synthesis](https://mlsanity.com/paper/2203.13944/) (2022) - [StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback](https://mlsanity.com/paper/2402.01391/) (2024) - [CAD-Coder: Text-to-CAD Generation with Chain-of-Thought and Geometric Reward](https://mlsanity.com/paper/2505.19713/) (2025) - [CAD-Coder: An Open-Source Vision-Language Model for Computer-Aided Design Code Generation](https://mlsanity.com/paper/2505.14646/) (2025) - [GenCAD: Image-Conditioned Computer-Aided Design Generation with Transformer-Based Contrastive Representation and Diffusion Priors](https://mlsanity.com/paper/2409.16294/) (2024) - [Img2CAD: Reverse Engineering 3D CAD Models from Images through VLM-Assisted Conditional Factorization](https://mlsanity.com/paper/2408.01437/) (2024) - [CAD-Coder:Text-Guided CAD Files Code Generation](https://mlsanity.com/paper/2505.08686/) (2025) - [CReFT-CAD: Boosting Orthographic Projection Reasoning for CAD via Reinforcement Fine-Tuning](https://mlsanity.com/paper/2506.00568/) (2025) - [PHT-CAD: Efficient CAD Parametric Primitive Analysis with Progressive Hierarchical Tuning](https://mlsanity.com/paper/2503.18147/) (2025) ## Built on by (most cited first, 12 of 12) - [CME-CAD: Heterogeneous Collaborative Multi-Expert Reinforcement Learning for CAD Code Generation](https://mlsanity.com/paper/2512.23333/) (2025) - [IterCAD: An Iterative Multimodal Agent for Visually-Grounded CAD Generation and Editing](https://mlsanity.com/paper/2606.13368/) (2026) - [Clarify Before You Draw: Proactive Agents for Robust Text-to-CAD Generation](https://mlsanity.com/paper/2602.03045/) (2026) - [Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence](https://mlsanity.com/paper/2606.15932/) (2026) - [GIFT: Bootstrapping Image-to-CAD Program Synthesis via Geometric Feedback](https://mlsanity.com/paper/2603.27448/) (2026) - [Pointer-CAD v2: Plan-Then-Construct CAD Generation with Dimension-Aware Parametric Precision](https://mlsanity.com/paper/2606.29301/) (2026) - [Design-Specification Tiling for ICL-based CAD Code Generation](https://mlsanity.com/paper/2603.12712/) (2026) - [Arko-T: A Foundation Model for Text-to-Structured 3D Generation](https://mlsanity.com/paper/2606.30429/) (2026) - [PCBWorld: A Benchmark Environment for Engine-Grounded PCB Design Automation](https://mlsanity.com/paper/2607.05915/) (2026) - [IterCAD: Iterative Program Repair for CAD Code Generation from Orthographic Views](https://mlsanity.com/paper/2608.24020/) (2026) - [CIT-CAD: Constraint Intent Tree-based CAD Code Generation and Verification](https://mlsanity.com/paper/2609.07434/) (2026) - [Rethinking Human Intent-to-CAD: Parametric CAD Model Generation via Cooperative Multi-Task Alignment and Spatial-Aware Reinforcement Learning](https://mlsanity.com/paper/2610.15681/) (2026) ## Abstract (arXiv) Computer-Aided Design (CAD) plays a vital role in engineering and manufacturing, yet current CAD workflows require extensive domain expertise and manual modeling effort. Recent advances in large language models (LLMs) have made it possible to generate code from natural language, opening new opportunities for automating parametric 3D modeling. However, directly translating human design intent into executable CAD code remains highly challenging, due to the need for logical reasoning, syntactic correctness, and numerical precision. In this work, we propose CAD-RL, a multimodal Chain-of-Thought (CoT) guided reinforcement learning post training framework for CAD modeling code generation. Our method combines CoT-based Cold Start with goal-driven reinforcement learning post training using three task-specific rewards: executability reward, geometric accuracy reward, and external evaluation reward. To ensure stable policy learning under sparse and high-variance reward conditions, we introduce three targeted optimization strategies: Trust Region Stretch for improved exploration, Precision Token Loss for enhanced dimensions parameter accuracy, and Overlong Filtering to reduce noisy supervision. To support training and benchmarking, we release ExeCAD, a noval dataset comprising 16,540 real-world CAD examples with paired natural language and structured design language descriptions, executable CADQuery scripts, and rendered 3D models. Experiments demonstrate that CAD-RL achieves significant improvements in reasoning quality, output precision, and code executability over existing VLMs.