Metraipolis › archive › dc_6a37f62863be

Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction — arXiv:2610.12299

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.12299
License (as archived)
CC0-1.0
Archived
2026-10-09T06:03:52.996Z
SHA-256 of the archived text
287d53f07c73b84b91a1f6050e21a5ebb932d4213af3116414bfca5a3853e414
Stable URL of this page
https://metraipolis.com/documento/dc_6a37f62863be

How to cite

Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction — arXiv:2610.12299 — arXiv (en), https://arxiv.org/abs/2610.12299 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6a37f62863be (Metraipolis archive dc_6a37f62863be, sha256 287d53f07c73b84b91a1f6050e21a5ebb932d4213af3116414bfca5a3853e414)
BibTeX
@misc{dc6a37f62863be,
  title = {Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction — arXiv:2610.12299},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.12299},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6a37f62863be; sha256 287d53f07c73b84b91a1f6050e21a5ebb932d4213af3116414bfca5a3853e414},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.12299. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Egocentric world models predict first-person observations conditioned on an agent's actions, but most focus on a single agent. Real embodied settings often involve multiple agents that act and interact within a shared environment. Existing multi-agent world models rely on coarse actions like locomotion, camera control, or discrete commands, leaving fine-grained embodied interactions underexplored. We formulate multi-agent egocentric world modeling as synchronized ego-stream generation for multiple agents interacting through fine-grained actions in a shared world. This requires cross-view action consistency, shared-environment consistency, and consistent propagation of interaction-induced state updates. We propose Multi-agent Egocentric World Model (ME-World), which jointly denoises multiple ego streams in a shared token sequence, conditions each stream on all agents' target-view poses, and grounds generation with shared environment memory. We train and evaluate on real and synthetic multi-agent data and introduce shared-world consistency metrics for environment, update, and identity consistency. Experiments show ME-World improves shared-world consistency, action control, identity preservation, and video quality over existing methods.

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/2610.12299 — 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 2026-10-09T05:47:02.188Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).