Metraipolis › archive › dc_09778a32f7dd

ConsistWorld: Evidence Routing for Consistent Multi-Agent World Models — arXiv:2609.22641

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.22641
License (as archived)
CC0-1.0
Archived
2026-10-09T21:59:13.860Z
SHA-256 of the archived text
86ac5037a1ff19cda236c014a37e6765427d2a7567fb162e7fe4997f0c4a66a8
Stable URL of this page
https://metraipolis.com/documento/dc_09778a32f7dd

How to cite

ConsistWorld: Evidence Routing for Consistent Multi-Agent World Models — arXiv:2609.22641 — arXiv (en), https://arxiv.org/abs/2609.22641 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_09778a32f7dd (Metraipolis archive dc_09778a32f7dd, sha256 86ac5037a1ff19cda236c014a37e6765427d2a7567fb162e7fe4997f0c4a66a8)
BibTeX
@misc{dc09778a32f7dd,
  title = {ConsistWorld: Evidence Routing for Consistent Multi-Agent World Models — arXiv:2609.22641},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.22641},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_09778a32f7dd; sha256 86ac5037a1ff19cda236c014a37e6765427d2a7567fb162e7fe4997f0c4a66a8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22641. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Autoregressive video world models enable temporally coherent generation for a single observer. Extending them to multiple agents requires consistency across independently controlled views and temporal gaps under causal streaming. We present ConsistWorld, a multi-agent world model that generates camera-controlled video streams of a static scene from one shared image. We formulate consistency as routing evidence from committed multi-agent history and concurrently generated peer views to the tokens being generated. Pose Conditioned Memory Retrieval selects relevant historical observations from all agents, recovering evidence beyond the recent context window. Visibility-Gated Peer Sharing regulates current peer information according to estimated historical coverage and current-view overlap. Together, they determine which historical observations enter the context and where concurrent peer information contributes, supporting long-term recall and coordinated exploration. Both mechanisms use camera geometry and maintain a bounded active context for a fixed agent count and retrieval budget. Experiments on evidence sharing cases and video length and agent number generalizations show that ConsistWorld achieves a strong cross-time and cross-agent consistency while preserving competitive generation quality.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.22641 — 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 2026-10-09T21:45:20.802Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).