Metraipolis › archive › dc_a204e5da4a68

AssemblyWorld: Rethinking 3D Assembly with General-Purpose Agents — arXiv:2609.40353

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.40353
License (as archived)
CC0-1.0
Archived
2026-10-07T14:46:41.734Z
SHA-256 of the archived text
bd38357144661cc5fca6986a89f3e376fba19f8c47bc21f21cfa49d65cf5646c
Stable URL of this page
https://metraipolis.com/documento/dc_a204e5da4a68

How to cite

AssemblyWorld: Rethinking 3D Assembly with General-Purpose Agents — arXiv:2609.40353 — arXiv (en), https://arxiv.org/abs/2609.40353 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a204e5da4a68 (Metraipolis archive dc_a204e5da4a68, sha256 bd38357144661cc5fca6986a89f3e376fba19f8c47bc21f21cfa49d65cf5646c)
BibTeX
@misc{dca204e5da4a68,
  title = {AssemblyWorld: Rethinking 3D Assembly with General-Purpose Agents — arXiv:2609.40353},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.40353},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a204e5da4a68; sha256 bd38357144661cc5fca6986a89f3e376fba19f8c47bc21f21cfa49d65cf5646c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.40353. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The task of 3D assembly requires translating an understanding of parts and their relationships into precise spatial arrangements. Can pretrained general-purpose agents assemble objects through visual interaction without additional assembly-specific fine-tuning? To investigate this question, we introduce AssemblyWorld, an interactive 3D environment in which agents inspect rendered views and manipulate supplied rigid parts, guided by images or assembly manuals when available. Agents perceive part geometry through 2D views rather than direct access to mesh vertices or faces, while their resulting assemblies are evaluated geometrically. Building on this environment, we construct AssemblyWorldBench, comprising 100 assembly tasks across 80 objects spanning furniture, industrial assembly, and fracture reassembly. Evaluating eight agent systems reveals substantial differences in their capabilities. The strongest system achieves 80.9% part accuracy but 59.4% complete-assembly success. The evaluated open-source systems lag substantially behind their stronger closed-source peers in both execution reliability and assembly accuracy. Analyses of visual references, interaction trajectories, and failures show how agents revise assemblies while leaving residual positioning errors. AssemblyWorld provides a common setting for both assessing the capabilities of interactive assembly agents and characterizing the gap between approximate structure recovery and precise reconstruction.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-01 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.40353 — 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 2026-10-07T14:19:00.867Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).