Metraipolis › archive › dc_615337f4f45a

WorldMind: Test-Time Scaling for Visual Spatial Reasoning through Latent World Simulation — arXiv:2611.10151

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.10151
License (as archived)
CC0-1.0
Archived
2026-11-10T18:40:45.425Z
SHA-256 of the archived text
7c3fbaa3bffa5a3f7b433ebcdd79d2761ab1edef81466c5006dd4685d131bff1
Stable URL of this page
https://metraipolis.com/documento/dc_615337f4f45a

How to cite

WorldMind: Test-Time Scaling for Visual Spatial Reasoning through Latent World Simulation — arXiv:2611.10151 — arXiv (en), https://arxiv.org/abs/2611.10151 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_615337f4f45a (Metraipolis archive dc_615337f4f45a, sha256 7c3fbaa3bffa5a3f7b433ebcdd79d2761ab1edef81466c5006dd4685d131bff1)
BibTeX
@misc{dc615337f4f45a,
  title = {WorldMind: Test-Time Scaling for Visual Spatial Reasoning through Latent World Simulation — arXiv:2611.10151},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.10151},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_615337f4f45a; sha256 7c3fbaa3bffa5a3f7b433ebcdd79d2761ab1edef81466c5006dd4685d131bff1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.10151. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-Language Models (VLMs) have continuous deficiency in spatial reasoning tasks that require \emph{mental spatial transformation}, such as reasoning under hypothetical changes in viewpoint or position, known as perspective-taking tasks. Existing approaches either scale linguistic reasoning or augment VLMs with static geometric representations, but neither directly enables active transformation of the represented scene. World models offer this capability, yet existing systems typically communicate through synthesized RGB images, introducing a latent-to-pixel-to-latent bottleneck. We introduce \emph{WorldMind}, a framework for test-time scaling of spatial reasoning through latent world simulation. Given a query and observation, the VLM selects useful spatial transformations, while a world model executes them and exposes aligned intermediate latent features directly to the VLM. The resulting latent evidence is incorporated into subsequent reasoning steps, enabling iterative spatial simulation without repeatedly decoding imagined states into pixels. To optimize this interaction, WorldMind further employs process-verifiable reinforcement learning that rewards reasoning progress only when the associated action and latent transition are valid. WorldMind thus scales spatial reasoning by allocating additional inference-time computation to active world simulation rather than generating more language or pixels. Across VSI-Bench, MMSI-Bench, and MindCube-Tiny, WorldMind achieves an average improvement of 16.0% over the base VLM and 8.3% over the strongest RGB-based world simulation.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.10151 — 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 2026-11-10T18:37:37.479Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).