Pith. sign in

REVIEW 7 cited by

Query2CAD: Generating CAD models using natural language queries

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2406.00144 v1 pith:MIQEGWTO submitted 2024-05-31 cs.LG cs.AIcs.CE

Query2CAD: Generating CAD models using natural language queries

classification cs.LG cs.AIcs.CE
keywords modelquery2caddesignsframeworklanguageratesuccessachieve
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Computer Aided Design (CAD) engineers typically do not achieve their best prototypes in a single attempt. Instead, they iterate and refine their designs to achieve an optimal solution through multiple revisions. This traditional approach, though effective, is time-consuming and relies heavily on the expertise of skilled engineers. To address these challenges, we introduce Query2CAD, a novel framework to generate CAD designs. The framework uses a large language model to generate executable CAD macros. Additionally, Query2CAD refines the generation of the CAD model with the help of its self-refinement loops. Query2CAD operates without supervised data or additional training, using the LLM as both a generator and a refiner. The refiner leverages feedback generated by the BLIP2 model, and to address false negatives, we have incorporated human-in-the-loop feedback into our system. Additionally, we have developed a dataset that encompasses most operations used in CAD model designing and have evaluated our framework using this dataset. Our findings reveal that when we used GPT-4 Turbo as our language model, the architecture achieved a success rate of 53.6\% on the first attempt. With subsequent refinements, the success rate increased by 23.1\%. In particular, the most significant improvement in the success rate was observed with the first iteration of the refinement. With subsequent refinements, the accuracy of the correct designs did not improve significantly. We have open-sourced our data, model, and code (github.com/akshay140601/Query2CAD).

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. neuralCAD-Edit: An Expert Benchmark for Multimodal-Instructed 3D CAD Model Editing

    cs.CV 2026-04 unverdicted novelty 8.0

    neuralCAD-Edit benchmark shows even the best foundation model (GPT 5.2) scores 53% lower than human CAD experts in acceptance trials for multimodal-instructed 3D model edits.

  2. PCBWorld: A Benchmark Environment for Engine-Grounded PCB Design Automation

    cs.AI 2026-07 conditional novelty 7.0

    An open-source KiCad-grounded PCB routing environment and benchmark where agents interactively route boards via engine-native operations, with a PPO policy trained on synthetic boards achieving zero-shot transfer to r...

  3. UniCAD: A Unified Benchmark and Universal Model for Multi-Modal Multi-Task CAD

    cs.CV 2026-06 unverdicted novelty 7.0

    UniCAD supplies a unified multi-modal benchmark and an end-to-end MLLM that performs reconstruction, generation, and QA on CAD data, reporting SOTA results on UniCAD and Fusion360.

  4. CAD-Coder: Text-to-CAD Generation with Chain-of-Thought and Geometric Reward

    cs.GR 2025-05 unverdicted novelty 7.0

    CAD-Coder generates valid CadQuery scripts from text via supervised fine-tuning followed by reinforcement learning with geometric Chamfer Distance rewards and chain-of-thought planning.

  5. Memory-Augmented Reinforcement Learning Agent for CAD Generation

    cs.AI 2026-05 unverdicted novelty 5.0

    Memory-augmented RL agent with case and skill libraries plus dynamic retrieval improves success rate and geometric consistency for complex CAD model generation.

  6. Enhancing Creativity in 3D Generative Design via a TRIZ-Inspired Text-to-CAD Framework

    cs.LG 2026-06 unverdicted novelty 4.0

    TRIZ-guided LLM prompting produces structurally diverse CAD chair variants with 4.0-14.7% mass reduction while preserving integrity in a two-stage pipeline.

  7. Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence

    cs.CL 2026-06 unverdicted novelty 3.0

    A structured survey of multimodal code intelligence that formulates the field by code roles and organizes work into four domains while proposing verification-centered research directions.