Pith. sign in

REVIEW 2 major objections 1 minor 38 references

IterCAD frames CAD generation and editing as closed-loop multi-turn interactions between a multimodal agent and an executable code sandbox.

Reviewed by Pith at T0; open to challenge. T0 means a machine referee read the full paper against a public rubric. the ladder, T0–T4 →

Challenge this review Re-run · record.json Download PDF Read on arXiv ↗

T0 review · grok-4.3

2026-07-01 07:31 UTC pith:P4ENQTEK

load-bearing objection IterCAD adds an iterative agent loop, synthetic data pipeline, and CD-TR metric to CAD generation, but the outperformance claims rest on unshown experiments and unvalidated data realism. the 2 major comments →

arxiv 2606.13368 v2 pith:P4ENQTEK submitted 2026-06-11 cs.AI cs.CV

IterCAD: An Iterative Multimodal Agent for Visually-Grounded CAD Generation and Editing

Tao Hu , Jiaxin Ai , Licheng Wen , Xueheng Li , Shu Zou , Siqi Li , Nianchen Deng , Xinyu Cai
show 7 more authors
Hongbin Zhou Pinlong Cai Daocheng Fu Yu Yang Hairong Zhang Botian Shi Xuemeng Yang
This is my paper
classification cs.AI cs.CV
keywords CAD generationmultimodal agentiterative refinementcode generationreinforcement learninggeometric precisiondata synthesis pipeline
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

The pith

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper establishes that open-loop one-shot methods mismatch real iterative CAD practice and proposes a unified agent that handles drawing-to-code, text-to-code, and interactive editing through repeated observation and code revision. It supplies a data pipeline that produces standard-compliant multi-view drawings and editing trajectories, then trains the agent first with progressive supervised fine-tuning and then with geometry-aware reinforcement learning that uses viable-prefix masking. The resulting system is evaluated on a new benchmark suite whose CD-TR curve and AUC-TR metric jointly measure code executability and geometric fidelity without survivor bias. Experiments indicate that this closed-loop procedure yields higher rates of valid, precise CAD code than prior approaches across the three tasks.

Core claim

IterCAD formulates CAD tasks as multi-turn agent-sandbox interactions, generates training trajectories via an industrial-feature data pipeline, and optimizes the agent through progressive SFT followed by geometry-aware RL with viable-prefix masking, producing measurable gains in code executability and geometric precision on the introduced IterCAD-Bench and CD-TR metric.

What carries the argument

The multimodal agent that performs closed-loop turns with an executable CAD sandbox, refined by progressive supervised fine-tuning and geometry-aware reinforcement learning using viable-prefix masking.

Load-bearing premise

The data synthesis pipeline that adds advanced industrial manufacturing features creates training and test distributions close enough to real CAD work for the measured gains to carry over.

What would settle it

Run the trained IterCAD agent on a collection of real industrial CAD drawings and models never produced by the synthesis pipeline and measure whether the reported improvements in code validity and Chamfer-distance precision remain.

Watch this falsifier — get emailed when new claim-graph text bears on it.

If this is right

  • The same agent architecture unifies three previously separate CAD tasks under one interactive loop.
  • Viable-prefix masking during RL directly raises the fraction of executable code outputs.
  • The CD-TR curve supplies a single scalar that trades off validity against geometric tolerance without discarding failed samples.
  • Iterative refinement produces larger gains on complex editing tasks than on single-pass generation.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • If the sandbox accurately reflects downstream manufacturing constraints, the agent could reduce the number of human revision cycles needed in production CAD workflows.
  • The same closed-loop pattern might transfer to other domains where code must satisfy geometric or physical constraints, such as procedural modeling or robotic task planning.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit.

Referee Report

2 major / 1 minor

Summary. The paper presents IterCAD, a multimodal agent framework for closed-loop, interactive CAD generation and editing formulated as multi-turn interactions in an executable sandbox across Drawing-to-Code, Text-to-Code, and Interactive Editing tasks. It introduces a data synthesis pipeline that adds industrial manufacturing features to produce multi-view drawings, editing tasks, and trajectories; trains the agent via progressive SFT followed by geometry-aware RL with viable-prefix masking; and proposes IterCAD-Bench with the CD-TR curve and AUC-TR metric as a survivor-bias-free evaluation standard. The central claim is that IterCAD achieves highly competitive performance, significantly outperforming prior methods in code executability and geometric precision while demonstrating superior closed-loop iterative refinement.

Significance. If the empirical claims hold, the work addresses a clear mismatch between one-shot CAD generation and iterative real-world practice, with the new benchmark and metric potentially serving as a useful standard for the community. The geometry-aware RL component with viable-prefix masking represents a concrete technical contribution for improving executability. The data synthesis approach incorporating industrial features is a positive step toward more realistic training data.

major comments (2)
  1. [Data synthesis pipeline] Data synthesis pipeline (described in the methods section following the task formulation): the central performance claims (outperformance in executability, geometric precision, and iterative refinement on IterCAD-Bench) rest on the assumption that the generated multi-view drawings and interaction trajectories match the feature complexity, tolerance variability, and editing patterns of real manufacturing workflows, yet no quantitative validation (distributional statistics, expert review, or comparison against external CAD corpora) is reported to support this match.
  2. [Experimental evaluation] Experimental evaluation section: the abstract and results claim significant outperformance across benchmarks with the new CD-TR/AUC-TR metric, but the provided description supplies no details on baseline implementations, number of runs, error bars, or full experimental protocol, preventing assessment of whether the reported gains are robust or benchmark-specific.
minor comments (1)
  1. [Evaluation metric definition] Notation for the CD-TR curve and AUC-TR metric should be defined with an explicit equation or pseudocode in the evaluation section to clarify how tolerance thresholds are applied and how survivor bias is avoided.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback and positive assessment of the work's significance. We address each major comment below and will revise the manuscript to incorporate the suggested improvements.

read point-by-point responses

  1. Referee: [Data synthesis pipeline] Data synthesis pipeline (described in the methods section following the task formulation): the central performance claims (outperformance in executability, geometric precision, and iterative refinement on IterCAD-Bench) rest on the assumption that the generated multi-view drawings and interaction trajectories match the feature complexity, tolerance variability, and editing patterns of real manufacturing workflows, yet no quantitative validation (distributional statistics, expert review, or comparison against external CAD corpora) is reported to support this match.

    Authors: We agree that explicit quantitative validation of the data synthesis pipeline against real manufacturing data would strengthen the central claims. In the revised manuscript we will add a dedicated subsection (or appendix) reporting distributional statistics (feature-type histograms, tolerance ranges, and editing-operation frequencies) comparing the synthesized data against external CAD corpora such as ABC and DeepCAD, together with a brief expert-review summary from two domain practitioners. This addition will be placed immediately after the data-pipeline description. revision: yes

  2. Referee: [Experimental evaluation] Experimental evaluation section: the abstract and results claim significant outperformance across benchmarks with the new CD-TR/AUC-TR metric, but the provided description supplies no details on baseline implementations, number of runs, error bars, or full experimental protocol, preventing assessment of whether the reported gains are robust or benchmark-specific.

    Authors: We acknowledge that the current experimental section lacks sufficient implementation and reproducibility details. In the revision we will expand the section to include: (i) complete descriptions and hyper-parameter settings for all baselines, (ii) results averaged over five independent runs with standard deviations shown as error bars in all tables and figures, and (iii) a full experimental protocol (including random seeds, hardware, and evaluation scripts) placed in the appendix. These changes will allow readers to assess robustness directly. revision: yes

Circularity Check

0 steps flagged

No circularity: empirical pipeline with independent experimental outcomes

full rationale

The paper describes a standard machine-learning pipeline: a data synthesis procedure generates training trajectories and a new benchmark (IterCAD-Bench), an agent is trained via SFT then geometry-aware RL, and performance is measured with CD-TR/AUC-TR on held-out tasks. No equations, predictions, or uniqueness claims are shown to reduce by construction to fitted parameters or self-citations. The central claims (outperformance in executability and refinement) are framed as measured experimental results on an externally defined benchmark, not quantities defined in terms of the model's own outputs. This matches the default expectation for non-circular empirical work.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

The abstract provides no explicit free parameters, axioms, or invented entities; the framework applies standard supervised fine-tuning and reinforcement learning to a new application domain without introducing new mathematical primitives or postulated objects.

pith-pipeline@v0.9.1-grok · 5797 in / 1189 out tokens · 50411 ms · 2026-07-01T07:31:03.974026+00:00 · methodology

0 comments
read the original abstract

Computer-Aided Design is pivotal in modern manufacturing, yet existing automated methods predominantly rely on open-loop, one-shot generation, creating a mismatch with iterative real-world practices. In this paper, we present IterCAD, a unified multimodal agent framework for closed-loop, interactive CAD generation and editing. We formulate the task as a multi-turn interaction between a multimodal agent and an executable CAD sandbox, covering three tasks: Drawing-to-Code, Text-to-Code, and Interactive Editing. To support this, we develop a data synthesis pipeline incorporating advanced industrial manufacturing features to generate standard-compliant multi-view engineering drawings, complex code-editing tasks, and high-fidelity interaction trajectories. We optimize the agent via progressive SFT followed by geometry-aware reinforcement learning with viable-prefix masking to enhance code executability and geometric fidelity. Finally, we introduce the IterCAD-Bench evaluation suite and propose the Chamfer Distance Tolerance-Recall (CD-TR) curve alongside its AUC-TR metric, establishing a survivor-bias-free standard that unifies code validity and geometric precision. Extensive experiments demonstrate that IterCAD achieves highly competitive performance across multiple benchmarks, significantly outperforming existing approaches in both code executability and geometric precision, while exhibiting superior capabilities in closed-loop iterative refinement.

Figures

Figures reproduced from arXiv: 2606.13368 by Botian Shi, Daocheng Fu, Hairong Zhang, Hongbin Zhou, Jiaxin Ai, Licheng Wen, Nianchen Deng, Pinlong Cai, Shu Zou, Siqi Li, Tao Hu, Xinyu Cai, Xueheng Li, Xuemeng Yang, Yu Yang.

Figure 1
Figure 1. Figure 1: IterCAD mimics the human “generate–verify–refine” workflow. Guided by multi-view engineering [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Overview of the IterCAD framework. IterCAD formulates interactive CAD generation and editing as a [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Data curation pipeline for IterCAD. The pipeline first constructs three categories of high-quality CAD [PITH_FULL_IMAGE:figures/full_fig_p004_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: CD-TR Curve on IterCAD-Draw bench. Benchmarks. We evaluate multi-turn generation across: 1) IterCAD-Bench: Our proposed suite with 1K drawing and 200 editing tasks; 2) Text2CAD Bench [14]: 8, 046 multimodal parts with text speci￾fications; and 3) CADPrompt Bench [34]: 200 expert instructions for zero-shot text-to-CAD synthesis. Evaluation Metrics. Performance is assessed via a multi-dimensional metric suit… view at source ↗
Figure 5
Figure 5. Figure 5: Representative samples from the IterCAD-Draw benchmark across two difficulty levels, showcasing multi-view engineering drawings paired with ground-truth 3D geometries. Complexity increases from simple extruded profiles (Easy-level) to parts requiring advanced operations such as shells, fillets, and through-cuts (Hard-level). Csrc. For each corrupted instance, we pair it with a concise design-change instruc… view at source ↗
Figure 6
Figure 6. Figure 6: Representative samples from the IterCAD-Edit benchmark. Each pair shows the source code (left), the editing instruction (middle), and the target code after modification (right), illustrating diverse edit operations including feature addition, Boolean subtraction, and parametric adjustment [PITH_FULL_IMAGE:figures/full_fig_p015_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Top-20 CadQuery API operation distribution in the [PITH_FULL_IMAGE:figures/full_fig_p015_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Average number of interaction turns during RL training. GSPO alone (blue) rapidly [PITH_FULL_IMAGE:figures/full_fig_p017_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Qualitative comparison on representative [PITH_FULL_IMAGE:figures/full_fig_p018_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Drawing-to-code self-correction case. Starting from a dimensioned engineering drawing, [PITH_FULL_IMAGE:figures/full_fig_p019_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: Text-to-CAD self-correction case. The initial code creates an offset cylinder and misses the [PITH_FULL_IMAGE:figures/full_fig_p020_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: Instruction-based CAD editing case. Starting from an existing rounded base, IterCAD [PITH_FULL_IMAGE:figures/full_fig_p021_12.png] view at source ↗
Figure 13
Figure 13. Figure 13: Unified generation-and-editing example. IterCAD first reconstructs a base plate from [PITH_FULL_IMAGE:figures/full_fig_p021_13.png] view at source ↗
Figure 14
Figure 14. Figure 14: System prompt for IterCAD code generation and editing. [PITH_FULL_IMAGE:figures/full_fig_p022_14.png] view at source ↗

Review history (2 revisions) →

discussion (0)

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

Reference graph

Works this paper leans on

38 extracted references · 19 canonical work pages · 6 internal anchors

  1. [1]

    Comparing 3d cad models: uses, methods, tools and perspectives.Computer-Aided Design and Applications, 9(6):771–794, 2012

    Antoine Brière-Côté, Louis Rivest, and Roland Maranzana. Comparing 3d cad models: uses, methods, tools and perspectives.Computer-Aided Design and Applications, 9(6):771–794, 2012

    2012

  2. [2]

    Penev, Bryan Weissinger, M

    AU, Jeremy Wright, thebluedirt, Marcus Boyd, Lorenz, Innovations Technology Solutions, Hasan Yavuz ÖZDERYA, Bruno Agostini, Jojain, Michael Greminger, Seth Fischer, Justin Buchanan, cactrot, huskier, Ruben, iulianOnofrei (U-lee aan), Miguel Sánchez de León Peque, Martin Budden, Hecatron, Peter Boin, Wink Saville, Pavel M. Penev, Bryan Weissinger, M. Greys...

    work page doi:10.5281/zenodo.10513848 2024

  3. [3]

    Text-to-cadquery: A new paradigm for cad generation with scalable large model capabilities.arXiv preprint arXiv:2505.06507, 2025

    Haoyang Xie and Feng Ju. Text-to-cadquery: A new paradigm for cad generation with scalable large model capabilities.arXiv preprint arXiv:2505.06507, 2025

    work page arXiv 2025

  4. [4]

    Cad translator: An effective drive for text to 3d parametric computer-aided design generative modeling

    Xueyang Li, Yu Song, Yunzhong Lou, and Xiangdong Zhou. Cad translator: An effective drive for text to 3d parametric computer-aided design generative modeling. InProceedings of the 32nd ACM International Conference on Multimedia, pages 8461–8470, 2024

    2024

  5. [5]

    Clarify Before You Draw: Proactive Agents for Robust Text-to-CAD Generation

    Bo Yuan, Zelin Zhao, Petr Molodyk, Bin Hu, and Yongxin Chen. Clarify before you draw: Proactive agents for robust text-to-cad generation.arXiv preprint arXiv:2602.03045, 2026

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  6. [6]

    Skexgen: Autoregressive generation of cad construction sequences with disentangled codebooks

    Xiang Xu, Karl DD Willis, Joseph G Lambourne, Chin-Yi Cheng, Pradeep Kumar Jayaraman, and Yasutaka Furukawa. Skexgen: Autoregressive generation of cad construction sequences with disentangled codebooks. arXiv preprint arXiv:2207.04632, 2022

    work page arXiv 2022

  7. [7]

    Cadsmith: Multi-agent cad generation with programmatic geometric validation.arXiv preprint arXiv:2603.26512, 2026

    Jesse Barkley, Rumi Loghmani, and Amir Barati Farimani. Cadsmith: Multi-agent cad generation with programmatic geometric validation.arXiv preprint arXiv:2603.26512, 2026

    work page arXiv 2026

  8. [8]

    Cme-cad: Heterogeneous collaborative multi-expert reinforcement learning for cad code generation.arXiv preprint arXiv:2512.23333, 2025

    Ke Niu, Haiyang Yu, Zhuofan Chen, Zhengtao Yao, Weitao Jia, Xiaodong Ge, Jingqun Tang, Benlei Cui, Bin Li, and Xiangyang Xue. Cme-cad: Heterogeneous collaborative multi-expert reinforcement learning for cad code generation.arXiv preprint arXiv:2512.23333, 2025

    work page arXiv 2025

  9. [9]

    Cad-coder: Text-to-cad generation with chain-of-thought and geometric reward.Advances in Neural Information Processing Systems, 38:59765–59789, 2026

    Yandong Guan, Xilin Wang, Ximing Xing, Jing Zhang, Dong Xu, and Qian Yu. Cad-coder: Text-to-cad generation with chain-of-thought and geometric reward.Advances in Neural Information Processing Systems, 38:59765–59789, 2026

    2026

  10. [10]

    cadrille: Multi-modal cad recon- struction with online reinforcement learning.arXiv preprint arXiv:2505.22914, 2025

    Maksim Kolodiazhnyi, Denis Tarasov, Dmitrii Zhemchuzhnikov, Alexander Nikulin, Ilya Zisman, Anna V orontsova, Anton Konushin, Vladislav Kurenkov, and Danila Rukhovich. cadrille: Multi-modal cad recon- struction with online reinforcement learning.arXiv preprint arXiv:2505.22914, 2025

    work page arXiv 2025

  11. [11]

    Cadreasoner: Iterative program editing for cad reverse engineering.arXiv preprint arXiv:2603.29847, 2026

    Soslan Kabisov, Vsevolod Kirichuk, Andrey V olkov, Gennadii Savrasov, Marina Barannikov, Anton Konushin, Andrey Kuznetsov, and Dmitrii Zhemchuzhnikov. Cadreasoner: Iterative program editing for cad reverse engineering.arXiv preprint arXiv:2603.29847, 2026

    work page arXiv 2026

  12. [12]

    Cad-judge: Toward efficient morphological grading and verification for text-to-cad generation

    Zheyuan Zhou, Jiayi Han, Liang Du, Naiyu Fang, Lemiao Qiu, and Shuyou Zhang. Cad-judge: Toward efficient morphological grading and verification for text-to-cad generation. InICASSP 2026-2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 1021–1025. IEEE, 2026

    2026

  13. [13]

    GIFT: Bootstrapping image-to-cad program synthesis via geometric feedback

    Giorgio Giannone, Anna Clare Doris, Amin Heyrani Nobari, Kai Xu, Akash Srivastava, and Faez Ahmed. Gift: Bootstrapping image-to-cad program synthesis via geometric feedback.arXiv preprint arXiv:2603.27448, 2026

    work page arXiv 2026

  14. [14]

    Text2cad: Generating sequential cad designs from beginner-to-expert level text prompts.Advances in Neural Information Processing Systems, 37:7552–7579, 2024

    Mohammad S Khan, Sankalp Sinha, Talha U Sheikh, Didier Stricker, Sk A Ali, and Muhammad Z Afzal. Text2cad: Generating sequential cad designs from beginner-to-expert level text prompts.Advances in Neural Information Processing Systems, 37:7552–7579, 2024

    2024

  15. [15]

    Deepcad: A deep generative network for computer-aided design models

    Rundi Wu, Chang Xiao, and Changxi Zheng. Deepcad: A deep generative network for computer-aided design models. InProceedings of the IEEE/CVF international conference on computer vision, pages 6772–6782, 2021

    2021

  16. [16]

    Secad-net: Self-supervised cad reconstruction by learning sketch-extrude operations

    Pu Li, Jianwei Guo, Xiaopeng Zhang, and Dong-Ming Yan. Secad-net: Self-supervised cad reconstruction by learning sketch-extrude operations. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 16816–16826, 2023. 10

    2023

  17. [17]

    Inversecsg: Automatic conversion of 3d models to csg trees.ACM Transac- tions on Graphics (TOG), 37(6):1–16, 2018

    Tao Du, Jeevana Priya Inala, Yewen Pu, Andrew Spielberg, Adriana Schulz, Daniela Rus, Armando Solar- Lezama, and Wojciech Matusik. Inversecsg: Automatic conversion of 3d models to csg trees.ACM Transac- tions on Graphics (TOG), 37(6):1–16, 2018

    2018

  18. [18]

    Capri-net: Learning compact cad shapes with adaptive primitive assembly

    Fenggen Yu, Zhiqin Chen, Manyi Li, Aditya Sanghi, Hooman Shayani, Ali Mahdavi-Amiri, and Hao Zhang. Capri-net: Learning compact cad shapes with adaptive primitive assembly. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 11768–11778, 2022

    2022

  19. [19]

    SolidGen: An autoregressive model for direct B-rep synthesis[J]

    Pradeep Kumar Jayaraman, Joseph G Lambourne, Nishkrit Desai, Karl DD Willis, Aditya Sanghi, and Nigel JW Morris. Solidgen: An autoregressive model for direct b-rep synthesis.arXiv preprint arXiv:2203.13944, 2022

    work page arXiv 2022

  20. [20]

    Brepgen: A b-rep generative diffusion model with structured latent geometry.ACM Transactions on Graphics (TOG), 43(4):1–14, 2024

    Xiang Xu, Joseph Lambourne, Pradeep Jayaraman, Zhengqing Wang, Karl Willis, and Yasutaka Furukawa. Brepgen: A b-rep generative diffusion model with structured latent geometry.ACM Transactions on Graphics (TOG), 43(4):1–14, 2024

    2024

  21. [21]

    Cad-llama: leveraging large language models for computer-aided design parametric 3d model generation

    Jiahao Li, Weijian Ma, Xueyang Li, Yunzhong Lou, Guichun Zhou, and Xiangdong Zhou. Cad-llama: leveraging large language models for computer-aided design parametric 3d model generation. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 18563–18573, 2025

    2025

  22. [22]

    Seek-cad: A self-refined generative modeling for 3d parametric cad using local inference via deepseek.arXiv preprint arXiv:2505.17702, 2025

    Xueyang Li, Jiahao Li, Yu Song, Yunzhong Lou, and Xiangdong Zhou. Seek-cad: A self-refined generative modeling for 3d parametric cad using local inference via deepseek.arXiv preprint arXiv:2505.17702, 2025

    work page arXiv 2025

  23. [23]

    From intent to execution: Multimodal chain-of-thought reinforcement learning for precise cad code generation

    Ke Niu, Haiyang Yu, Zhuofan Chen, Mengyang Zhao, Teng Fu, Bin Li, and Xiangyang Xue. From intent to execution: Multimodal chain-of-thought reinforcement learning for precise cad code generation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 40, pages 8160–8167, 2026

    2026

  24. [24]

    Fusion 360 gallery: A dataset and environment for programmatic cad construction from human design sequences.ACM Transactions on Graphics (TOG), 40(4):1–24, 2021

    Karl DD Willis, Yewen Pu, Jieliang Luo, Hang Chu, Tao Du, Joseph G Lambourne, Armando Solar-Lezama, and Wojciech Matusik. Fusion 360 gallery: A dataset and environment for programmatic cad construction from human design sequences.ACM Transactions on Graphics (TOG), 40(4):1–24, 2021

    2021

  25. [25]

    CAD-Editor: A locate-then-infill framework with automated training data synthesis for text-based cad editing.arXiv preprint arXiv:2502.03997, 2025

    Yu Yuan, Shizhao Sun, Qi Liu, and Jiang Bian. Cad-editor: A locate-then-infill framework with automated training data synthesis for text-based cad editing.arXiv preprint arXiv:2502.03997, 2025

    work page arXiv 2025

  26. [26]

    PR-CAD: Progressive Refinement for Unified Controllable and Faithful Text-to-CAD Generation with Large Language Models

    Jiyuan An, Jiachen Zhao, Fan Chen, Liner Yang, Zhenghao Liu, Hongyan Wang, Weihua An, Meishan Zhang, and Erhong Yang. Pr-cad: Progressive refinement for unified controllable and faithful text-to-cad generation with large language models.arXiv preprint arXiv:2604.19773, 2026

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  27. [27]

    CADDesigner: Conceptual CAD Model Generation with a General-Purpose Agent

    Fengxiao Fan, Jingzhe Ni, Xiaolong Yin, Sirui Wang, Xingyu Lu, Qiang Zou, Ruofeng Tong, Min Tang, and Peng Du. Caddesigner: Conceptual design of cad models based on general-purpose agent.arXiv preprint arXiv:2508.01031, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  28. [28]

    TOOLCAD: Exploring Tool-Using Large Language Models in Text-to-CAD Generation with Reinforcement Learning

    Yifei Gong, Xing Wu, Wenda Liu, and Kang Tu. Toolcad: Exploring tool-using large language models in text-to-cad generation with reinforcement learning.arXiv preprint arXiv:2604.07960, 2026

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  29. [29]

    Qwen3-VL Technical Report

    Shuai Bai, Yuxuan Cai, Ruizhe Chen, Keqin Chen, Xionghui Chen, Zesen Cheng, Lianghao Deng, Wei Ding, Chang Gao, Chunjiang Ge, et al. Qwen3-vl technical report.arXiv preprint arXiv:2511.21631, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  30. [30]

    Group Sequence Policy Optimization

    Chujie Zheng, Shixuan Liu, Mingze Li, Xiong-Hui Chen, Bowen Yu, Chang Gao, Kai Dang, Yuqiong Liu, Rui Men, An Yang, et al. Group sequence policy optimization.arXiv preprint arXiv:2507.18071, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  31. [31]

    2026 , bdsk-url-1 =

    Yong Xien Chng, Tao Hu, Wenwen Tong, Xueheng Li, Jiandong Chen, Haojia Yu, Jiefan Lu, Hewei Guo, Hanming Deng, Chengjun Xie, et al. Sensenova-mars: Empowering multimodal agentic reasoning and search via reinforcement learning.arXiv preprint arXiv:2512.24330, 2025

    work page arXiv 2025

  32. [32]

    Swift: a scalable lightweight infrastructure for fine-tuning

    Yuze Zhao, Jintao Huang, Jinghan Hu, Xingjun Wang, Yunlin Mao, Daoze Zhang, Zeyinzi Jiang, Zhikai Wu, Baole Ai, Ang Wang, et al. Swift: a scalable lightweight infrastructure for fine-tuning. InProceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 29733–29735, 2025

    2025

  33. [33]

    Qwen3.5: Accelerating productivity with native multimodal agents, February 2026

    Qwen Team. Qwen3.5: Accelerating productivity with native multimodal agents, February 2026. URL https://qwen.ai/blog?id=qwen3.5

    2026

  34. [34]

    Generating cad code with vision-language models for 3d designs

    Kamel Alrashedy, Pradyumna Tambwekar, Zulfiqar Haider Zaidi, Megan Langwasser, Wei Xu, and Matthew Gombolay. Generating cad code with vision-language models for 3d designs. InInternational Conference on Learning Representations, volume 2025, pages 52236–52262, 2025

    2025

  35. [35]

    sketch-and-extrude

    OpenAI. Gpt-5.https://openai.com/gpt-5, 2025. 11 Appendix Contents A Related Work 12 A.1 CAD Representations and Generation . . . . . . . . . . . . . . . . . . . . . . . . 12 A.2 Multi-Turn CAD Agents . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 B CAD Pairs Construction 13 B.1 Drawing-Code Pairs. . . . . . . . . . . . . . . . . . . . ....

    work page arXiv 2025

  36. [36]

    2.Text: modeling instructions, dimensional constraints, or edit requests

    Technical Drawing Image: orthographic projections such as Front, Top, Side, and ISO views with dimensions. 2.Text: modeling instructions, dimensional constraints, or edit requests. 3.Existing Code: a CadQuery script that should be preserved or modified when possible. Objective.Create or edit a 3D model that satisfies the user request. Output Format.Always...

  37. [37]

    – Plan: define the origin, workplanes, sketch sequence, Boolean operations, and key dimen- sions

    Structure the<thinking>process strictly based on the provided inputs: •If no feedback is provided, such as initial generation or completely new instructions: – Requirement Analysis: break down visual or textual inputs into CadQuery features. – Plan: define the origin, workplanes, sketch sequence, Boolean operations, and key dimen- sions. •If feedback or e...

  38. [38]

    Code Implementation Rules

    If feedback explicitly confirms that the 3D model is correct with no remaining issues, briefly state the assessment in<thinking></thinking>, then output<DONE>. Code Implementation Rules. • Use Python as the programming language. • Use CadQuery withimport cadquery as cq. • Assign the final result to variabler. • If scaling is needed, define scale_factor an...