Metraipolis › archive › dc_ccbea4e6edf1

AgenticCADedit: A Stateful, Tool-Mediated Agentic Approach to Multimodal 3D CAD Editing — arXiv:2609.29621

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.29621
License (as archived): CC0-1.0
Archived: 2026-10-08T06:44:32.616Z
SHA-256 of the archived text: 34023d9a8d0f756f66d7fd625203269734ab15781dfaca05eace397ca6271752
Stable URL of this page: https://metraipolis.com/documento/dc_ccbea4e6edf1

How to cite

AgenticCADedit: A Stateful, Tool-Mediated Agentic Approach to Multimodal 3D CAD Editing — arXiv:2609.29621 — arXiv (en), https://arxiv.org/abs/2609.29621 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ccbea4e6edf1 (Metraipolis archive dc_ccbea4e6edf1, sha256 34023d9a8d0f756f66d7fd625203269734ab15781dfaca05eace397ca6271752)

BibTeX

@misc{dcccbea4e6edf1,
  title = {AgenticCADedit: A Stateful, Tool-Mediated Agentic Approach to Multimodal 3D CAD Editing — arXiv:2609.29621},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.29621},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ccbea4e6edf1; sha256 34023d9a8d0f756f66d7fd625203269734ab15781dfaca05eace397ca6271752},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29621. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Computer-aided design is central to industrial manufacturing, and much of a designer's daily work consists of editing existing models from multimodal requests involving speech, sketches, and model interaction. Existing neural CAD approaches focus predominantly on unconditional or text-conditioned generation. The neuralCAD-Edit approach formalizes expert multimodal editing requests, but its iterative baseline refines a complete CAD program across attempts, executing each attempt from the original model in a stateless CAD environment. Every attempt must therefore reconstruct the entire edit from scratch, so partially correct progress is discarded rather than accumulated, and the model can neither inspect the geometry it has just produced nor selectively revert a single faulty operation. We present AgenticCADedit, which turns editing into a sequence of small, verifiable actions on a persistent CAD state instead of a single regenerated program. Rather than emitting one complete program, it applies incremental code steps that each commit to the session, inspects the resulting faces and edges, renders highlighted selections to verify that the intended region was addressed, and reverts individual operations when it was not. Subsequent actions therefore build on the geometry produced by earlier ones. Our approach improves on all metrics for all three evaluated LLMs (open-weight: qwen3.6-27b, gemma4-31b; proprietary: gpt-5.6-luna), with the largest gains for the weakest baseline model, qwen3.6-27b, whose validity rises from 51.0% to 94.8% and acceptance from 1.6% to 12.0%. A token-cost analysis with gpt-5.6-luna further shows $66.7$% fewer output tokens than neuralCAD-Edit, while $94.8$% of input tokens are served from the prompt cache.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-25 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Graphics (cs.GR).
Pagina del lavoro: https://arxiv.org/abs/2609.29621 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T06:09:29.868Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).