Metraipolis › archive › dc_d2dfd00b1ab2

AgiWorld: An Agentic Video World Model for Building Persistent Worlds — arXiv:2611.02341

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.02341
License (as archived): CC0-1.0
Archived: 2026-11-03T11:07:37.832Z
SHA-256 of the archived text: 312c2469850f4590b05e7b37bfef35d1156e9659a6b87a428f03ba73afbfc77e
Stable URL of this page: https://metraipolis.com/documento/dc_d2dfd00b1ab2

How to cite

AgiWorld: An Agentic Video World Model for Building Persistent Worlds — arXiv:2611.02341 — arXiv (en), https://arxiv.org/abs/2611.02341 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d2dfd00b1ab2 (Metraipolis archive dc_d2dfd00b1ab2, sha256 312c2469850f4590b05e7b37bfef35d1156e9659a6b87a428f03ba73afbfc77e)

BibTeX

@misc{dcd2dfd00b1ab2,
  title = {AgiWorld: An Agentic Video World Model for Building Persistent Worlds — arXiv:2611.02341},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02341},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d2dfd00b1ab2; sha256 312c2469850f4590b05e7b37bfef35d1156e9659a6b87a428f03ba73afbfc77e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02341. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent interactive video world models generate visually compelling videos from a single image, following user-provided camera motion and text prompts. However, such low-level control demands substantial user effort to realize a high-level intent, and the generated world struggles to remain persistent as the exploration proceeds. In this work, we present AgiWorld, an agentic video world model that explores and builds a persistent world from a single image and a free-form instruction. For high-level planning, our agent AgiWorld-Agent designs the world and the journey through it in a world state and directs the exploration. For low-level realization, our video world model AgiWorld-WM generates the video chunk by chunk and stores it with its geometry in a spatial memory, from which the agent updates its world state. This closed loop keeps the world faithful to the user's intent and keeps the agent's world state consistent with the generated content throughout the exploration. We co-design the two levels around the shared spatial memory and an interface of metric camera trajectories and structured prompts. In AgiWorld-WM, to handle occlusion and accumulated geometric errors in the spatial memory over long rollouts, we propose occlusion-aware history selection, which retrieves past views by surface visibility, and reliability-based memory maintenance, which prefers reliable geometry and earlier observations. AgiWorld-WM achieves state-of-the-art overall performance on world revisiting and exploration benchmarks, and qualitative results and ablations show that AgiWorld builds persistent worlds from free-form instructions over minute-long journeys. Persistence thus arises not from the video model alone but from its closed loop with the agent.

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/2611.02341 — 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 2026-11-03T10:59:46.092Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).