Metraipolis › archive › dc_e79936f375fc

3DCodeVerse: Exploring 3D Worlds as Code — arXiv:2610.22341

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.22341
License (as archived)
CC0-1.0
Archived
2026-10-16T09:50:58.939Z
SHA-256 of the archived text
a879eec7ee60b14bc02fa95f49c9a5d056afc3069b562b9f942cd182b6ccc744
Stable URL of this page
https://metraipolis.com/documento/dc_e79936f375fc

How to cite

3DCodeVerse: Exploring 3D Worlds as Code — arXiv:2610.22341 — arXiv (en), https://arxiv.org/abs/2610.22341 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e79936f375fc (Metraipolis archive dc_e79936f375fc, sha256 a879eec7ee60b14bc02fa95f49c9a5d056afc3069b562b9f942cd182b6ccc744)
BibTeX
@misc{dce79936f375fc,
  title = {3DCodeVerse: Exploring 3D Worlds as Code — arXiv:2610.22341},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.22341},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e79936f375fc; sha256 a879eec7ee60b14bc02fa95f49c9a5d056afc3069b562b9f942cd182b6ccc744},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22341. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We introduce 3DCodeVerse, a research ecosystem that enables coding agents to create editable and verifiable 3D content at scale. 3DCodeVerse comprises large-scale, high-quality datasets of executable 3D code, a coding harness for spatial reasoning and automated verification, and practical guidance for 3D coding. First, we construct 3DCodeVerse-2M, a large-scale curated dataset of standalone 3D executable code. We build this corpus by collecting open-source data, converting specialized representations, and generating new programs with coding agents. Each program is packaged with the source files and associated assets required for execution in its declared environment, along with available descriptions and verification records. Second, we develop the 3DCodeVerse Harness, a multi-agent directed acyclic graph framework for generating and refining 3D content. It uses execution checks, spatial measurements, and visual feedback to automatically evaluate and revise generated programs without human feedback during generation. Third, we conduct systematic empirical studies of 3D coding, establishing baselines with fine-tuned open models and deriving practical guidance through component-level analyses of our harness. Extensive experiments demonstrate that fine-tuning on our dataset significantly improves the 3D coding capabilities of open-source models. Notably, our 3DCodeVerse harness achieves a 90% win rate against Claude Design (3D Object) in pairwise human evaluations, when both are utilized by Claude Opus 5.5.

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/2610.22341 — 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 2026-10-16T08:44:18.063Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).