Metraipolis › archive › dc_8fea3bd4ae14
TraceCAD: Trace-Guided Repair for Agentic CAD Generation — arXiv:2608.03062
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.03062
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T12:15:32.931Z
- SHA-256 of the archived text
b51400da34789e63645378fe192ae8cc69e94d4725da614e107b8477027b1612- Stable URL of this page
https://metraipolis.com/documento/dc_8fea3bd4ae14
How to cite
TraceCAD: Trace-Guided Repair for Agentic CAD Generation — arXiv:2608.03062 — arXiv (en), https://arxiv.org/abs/2608.03062 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8fea3bd4ae14 (Metraipolis archive dc_8fea3bd4ae14, sha256 b51400da34789e63645378fe192ae8cc69e94d4725da614e107b8477027b1612)
BibTeX
@misc{dc8fea3bd4ae14,
title = {TraceCAD: Trace-Guided Repair for Agentic CAD Generation — arXiv:2608.03062},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.03062},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8fea3bd4ae14; sha256 b51400da34789e63645378fe192ae8cc69e94d4725da614e107b8477027b1612},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03062. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
LLM-based CAD agents produce executable parametric programs, but their correction loops may lose evidence about satisfied requirements, faulty operations, and prior repairs. We introduce TraceCAD, a recovery layer that links requested features, modeling steps, failure evidence, and candidate outcomes as persistent state. TraceCAD diagnoses likely faulty operations, searches bounded edits in their dependency regions, validates candidates through execution and preservation checks, and retains successful and failed repair outcomes in reusable skill memory. On DeepCAD-derived benchmarks with 200-model ablations and a 1K-model comparison, TraceCAD achieves competitive geometric quality in terms of IoU, Chamfer distance, and Hausdorff distance. Removing persistent state nearly halves recovery score; removing localized search more than doubles geometric regression and doubles code-agent invocations. Initializing the skill store on disjoint training models further reduces retries, token cost, and latency. These results demonstrate that persistent, localized, and reusable recovery improves final CAD quality and repair reliability. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Graphics (cs.GR); Software Engineering (cs.SE). Pagina del lavoro: https://arxiv.org/abs/2608.03062 — 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 2026-10-31T12:05:52.748Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).