Metraipolis › archive › dc_2f73f4773a37
MARC: Mechanism-Aware Reflective Correction for Articulated Object Code Generation — arXiv:2610.33060
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.33060
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-27T07:59:31.284Z
- SHA-256 of the archived text
6cf22dc2b3bf3cd6963a88ace7483f94418d2b771f18c385dddb611db778296f- Stable URL of this page
https://metraipolis.com/documento/dc_2f73f4773a37
How to cite
MARC: Mechanism-Aware Reflective Correction for Articulated Object Code Generation — arXiv:2610.33060 — arXiv (en), https://arxiv.org/abs/2610.33060 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2f73f4773a37 (Metraipolis archive dc_2f73f4773a37, sha256 6cf22dc2b3bf3cd6963a88ace7483f94418d2b771f18c385dddb611db778296f)
BibTeX
@misc{dc2f73f4773a37,
title = {MARC: Mechanism-Aware Reflective Correction for Articulated Object Code Generation — arXiv:2610.33060},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.33060},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2f73f4773a37; sha256 6cf22dc2b3bf3cd6963a88ace7483f94418d2b771f18c385dddb611db778296f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.33060. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Generating an articulated object from images and text requires more than plausible parts and movable joints: the assembled mechanism must execute the intended motion. This is particularly challenging for closed-chain and coupled mechanisms, where an error in one connection can block motion or separate connected parts. We introduce MARC, Mechanism-Aware Reflective Correction, which shares an executable kinematic graph across program construction, motion solving, and correction. The graph binds physical connections to local attachment frames and represents loop closures and joint-coordinate couplings. Given prescribed driver inputs, a numerical solver computes follower motion and associates errors with specific connections and configurations. The agent uses these diagnostics to probe possible causes, revise connections or geometry, and retest the mechanism along the original motion paths. On a 20-object test set, MARC with Kimi-K3 achieves 67.8% valid motion coverage and 60.0% overall success, outperforming six baselines. Starting from the same initial candidates, correction improves these scores by 13.7 and 20.0 percentage points, respectively. Ablations further show the benefits of graph-based mechanism support and graph-guided repair. Project homepage: this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.33060 — 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 2026-10-27T07:55:30.800Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).