# Seek-CAD: A Self-refined Generative Modeling for 3D Parametric CAD Using Local Inference via DeepSeek

arXiv: https://arxiv.org/abs/2505.17702 · HTML: https://mlsanity.com/paper/2505.17702/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 41 of its 67 references that are in the map.
- First posted on arXiv 23 May 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 30 of 41)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks](https://mlsanity.com/paper/2305.11175/) (2023)
- [LMDrive: Closed-Loop End-to-End Driving with Large Language Models](https://mlsanity.com/paper/2312.07488/) (2023)
- [DeepCAD: A Deep Generative Network for Computer-Aided Design Models](https://mlsanity.com/paper/2105.09492/) (2021)
- [VTimeLLM: Empower LLM to Grasp Video Moments](https://mlsanity.com/paper/2311.18445/) (2023)
- [SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebooks](https://mlsanity.com/paper/2207.04632/) (2022)
- [BrepGen: A B-rep Generative Diffusion Model with Structured Latent Geometry](https://mlsanity.com/paper/2401.15563/) (2024)
- [Hierarchical Neural Coding for Controllable CAD Model Generation](https://mlsanity.com/paper/2307.00149/) (2023)
- [Computer-Aided Design as Language](https://mlsanity.com/paper/2105.02769/) (2021)
- [CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLM](https://mlsanity.com/paper/2411.04954/) (2024)
- [JoinABLe: Learning Bottom-up Assembly of Parametric CAD Joints](https://mlsanity.com/paper/2111.12772/) (2021)
- [SketchGen: Generating Constrained CAD Sketches](https://mlsanity.com/paper/2106.02711/) (2021)
- [VELMA: Verbalization Embodiment of LLM Agents for Vision and Language Navigation in Street View](https://mlsanity.com/paper/2307.06082/) (2023)
- [CAD-Llama: Leveraging Large Language Models for Computer-Aided Design Parametric 3D Model Generation](https://mlsanity.com/paper/2505.04481/) (2025)
- [CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attention](https://mlsanity.com/paper/2402.17678/) (2024)
- [Generating CAD Code with Vision-Language Models for 3D Designs](https://mlsanity.com/paper/2410.05340/) (2024)
- [Koala: Key frame-conditioned long video-LLM](https://mlsanity.com/paper/2404.04346/) (2024)
- [I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification](https://mlsanity.com/paper/2212.02291/) (2022)
- [CAD-GPT: Synthesising CAD Construction Sequence with Spatial Reasoning-Enhanced Multimodal LLMs](https://mlsanity.com/paper/2412.19663/) (2024)
- [LLM-Seg: Bridging Image Segmentation and Large Language Model Reasoning](https://mlsanity.com/paper/2404.08767/) (2024)
- [Text-to-CAD Generation Through Infusing Visual Feedback in Large Language Models](https://mlsanity.com/paper/2501.19054/) (2025)
- [CLIPSyntel: CLIP and LLM Synergy for Multimodal Question Summarization in Healthcare](https://mlsanity.com/paper/2312.11541/) (2023)
- [CAD-Assistant: Tool-Augmented VLLMs as Generic CAD Task Solvers](https://mlsanity.com/paper/2412.13810/) (2024)

## Built on by (most cited first, 24 of 24)

- [IterCAD: An Iterative Multimodal Agent for Visually-Grounded CAD Generation and Editing](https://mlsanity.com/paper/2606.13368/) (2026)
- [ArtiCAD: Articulated CAD Assembly Design via Multi-Agent Code Generation](https://mlsanity.com/paper/2604.10992/) (2026)
- [Clarify Before You Draw: Proactive Agents for Robust Text-to-CAD Generation](https://mlsanity.com/paper/2602.03045/) (2026)
- [Towards High-Fidelity CAD Generation via LLM-Driven Program Generation and Text-Based B-Rep Primitive Grounding](https://mlsanity.com/paper/2603.11831/) (2026)
- [CADReasoner: Iterative Program Editing for CAD Reverse Engineering](https://mlsanity.com/paper/2603.29847/) (2026)
- [TOOLCAD: Exploring Tool-Using Large Language Models in Text-to-CAD Generation with Reinforcement Learning](https://mlsanity.com/paper/2604.07960/) (2026)
- [CADDesigner: Conceptual CAD Model Generation with a General-Purpose Agent](https://mlsanity.com/paper/2508.01031/) (2025)
- [PR-CAD: Progressive Refinement for Unified Controllable and Faithful Text-to-CAD Generation with Large Language Models](https://mlsanity.com/paper/2604.19773/) (2026)
- [UniCAD: A Unified Benchmark and Universal Model for Multi-Modal Multi-Task CAD](https://mlsanity.com/paper/2606.05058/) (2026)
- [GACO-CAD: Geometry-Augmented and Conciseness-Optimized CAD Model Generation from Single Image](https://mlsanity.com/paper/2510.17157/) (2025)
- [Self-Improving CAD Generation Agents with Finite Element Analysis as Feedback](https://mlsanity.com/paper/2605.17448/) (2026)
- [CADIR: A Cross-Backend Editable Intermediate Representation for Agentic CAD Generation](https://mlsanity.com/paper/2608.00891/) (2026)
- [Draw it like Euclid: Teaching transformer models to generate CAD profiles using ruler and compass construction steps](https://mlsanity.com/paper/2601.09428/) (2026)
- [Pointer-CAD v2: Plan-Then-Construct CAD Generation with Dimension-Aware Parametric Precision](https://mlsanity.com/paper/2606.29301/) (2026)
- [SOV-CAD: Stepwise Orthographic Views Guided CAD Modeling Sequence Reconstruction](https://mlsanity.com/paper/2607.04119/) (2026)
- [CADForge: Agentic Single-View CAD Reconstruction with Explicit Geometry Reasoning](https://mlsanity.com/paper/2610.04262/) (2026)
- [Agent-Aided Design for Dynamic CAD Models](https://mlsanity.com/paper/2604.15184/) (2026)
- [Memory-Augmented Reinforcement Learning Agent for CAD Generation](https://mlsanity.com/paper/2605.19748/) (2026)
- [TraceCAD: Trace-Guided Repair for Agentic CAD Generation](https://mlsanity.com/paper/2608.03062/) (2026)
- [RA-CAD: Learning Post-Execution Critique for State-Aware Text-to-CAD Generation](https://mlsanity.com/paper/2608.05714/) (2026)
- [Test-Time Scaling for CAD Generation via Verifier-Free Consensus Selection](https://mlsanity.com/paper/2608.09706/) (2026)
- [Language-Augmented Semantic Priors for B-Spline Surface Fitting](https://mlsanity.com/paper/2609.11708/) (2026)
- [Vision2CAD: A Visual Agent Harness for Explicit Geometry Referencing and Localization in Parametric CAD Modeling](https://mlsanity.com/paper/2609.22688/) (2026)
- [StepCAD: Mesh-to-CAD Code Generation via LLM Policy and Geometry-Guided Search](https://mlsanity.com/paper/2610.03799/) (2026)

## Abstract (arXiv)

The advent of Computer-Aided Design (CAD) generative modeling will significantly transform the design of industrial products. The recent research endeavor has extended into the realm of Large Language Models (LLMs). In contrast to fine-tuning methods, training-free approaches typically utilize the advanced closed-source LLMs, thereby offering enhanced flexibility and efficiency in the development of AI agents for generating CAD parametric models. However, the substantial cost and limitations of local deployment of the top-tier closed-source LLMs pose challenges in practical applications. The Seek-CAD is the pioneer exploration of locally deployed open-source inference LLM DeepSeek-R1 for CAD parametric model generation with a training-free methodology. This study is the first investigation to incorporate both visual and Chain-of-Thought (CoT) feedback within the self-refinement mechanism for generating CAD models. Specifically, the initial generated parametric CAD model is rendered into a sequence of step-wise perspective images, which are subsequently processed by a Vision Language Model (VLM) alongside the corresponding CoTs derived from DeepSeek-R1 to assess the CAD model generation. Then, the feedback is utilized by DeepSeek-R1 to refine the initial generated model for the next round of generation. Moreover, we present an innovative 3D CAD model dataset structured around the SSR (Sketch, Sketch-based feature, and Refinements) triple design paradigm. This dataset encompasses a wide range of CAD commands, thereby aligning effectively with industrial application requirements and proving suitable for the generation of LLMs. Extensive experiments validate the effectiveness of Seek-CAD under various metrics.