Metraipolis › archive › dc_eccba9a88bd6
The Planning Limits of Latent World Models — arXiv:2609.39235
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.39235
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T14:46:49.858Z
- SHA-256 of the archived text
75d6a1656994a45a9f24ba7c1b4b4fb398850f296e4f654a292ddad741a5078e- Stable URL of this page
https://metraipolis.com/documento/dc_eccba9a88bd6
How to cite
The Planning Limits of Latent World Models — arXiv:2609.39235 — arXiv (en), https://arxiv.org/abs/2609.39235 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eccba9a88bd6 (Metraipolis archive dc_eccba9a88bd6, sha256 75d6a1656994a45a9f24ba7c1b4b4fb398850f296e4f654a292ddad741a5078e)
BibTeX
@misc{dceccba9a88bd6,
title = {The Planning Limits of Latent World Models — arXiv:2609.39235},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.39235},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eccba9a88bd6; sha256 75d6a1656994a45a9f24ba7c1b4b4fb398850f296e4f654a292ddad741a5078e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39235. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
World models offer a promising way to help robots understand how the physical world evolves and plan complex behaviours through imagination. Yet existing studies mainly demonstrate what these models can accomplish, leaving unclear when their predictions remain useful for planning and where they fail. We study this question using action-conditioned predictors built on five frozen self-supervised visual backbones: V-JEPA 2, V-JEPA 2.1, VideoMAEv2, VideoPrism, and DINOv2. We use frozen backbones to test representations intended to transfer across environments. We evaluate these models on diverse Meta-World manipulation tasks and real-robot interactions from BridgeData V2. We find that a world model guides action selection reliably only when the goal lies within, or slightly beyond, the trajectory it imagines during planning. With five-step rollouts, the length the predictor was trained on, the world model ranks actions reliably only for targets five to ten control steps ahead, whereas task goals lie 16 to 53 steps away. Neither an 81-fold larger predictor nor longer-rollout training extends this range; the encoder affects both range and closed-loop success, with V-JEPA 2.1 performing most consistently. More fundamentally, the limit persists under perfect prediction: using the real simulator, success falls from 92% to 41% as the target moves from five to twenty steps ahead of a five-step rollout. Planning therefore requires either longer imagined trajectories or closer subgoals. For distant goals, pure imagination succeeds in 23% of episodes, planning with feedback (MPC) raises success to 30%, imagining as far as the goal to 47%, and nearby expert subgoals to 76%. Used within its plannable range, a world model can also improve a vision-language-action (VLA) policy: choosing among eight actions the VLA proposes raises its success from 65% to 77% across 16 different tasks. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-01 in cs.CV). Categorie arXiv: Robotics (cs.RO) ; Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.39235 — 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 2026-10-07T14:19:00.901Z 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).