Metraipolis › archive › dc_044ff09afb62

Hierarchical World Models with Implicit Dynamics — arXiv:2610.42146

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.42146
License (as archived): CC0-1.0
Archived: 2026-11-03T07:33:36.791Z
SHA-256 of the archived text: 95337fbc360113f1e77fc48192b1ff12ffb2a22981b63fd69ce8b9f7e8ba08fd
Stable URL of this page: https://metraipolis.com/documento/dc_044ff09afb62

How to cite

Hierarchical World Models with Implicit Dynamics — arXiv:2610.42146 — arXiv (en), https://arxiv.org/abs/2610.42146 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_044ff09afb62 (Metraipolis archive dc_044ff09afb62, sha256 95337fbc360113f1e77fc48192b1ff12ffb2a22981b63fd69ce8b9f7e8ba08fd)

BibTeX

@misc{dc044ff09afb62,
  title = {Hierarchical World Models with Implicit Dynamics — arXiv:2610.42146},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.42146},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_044ff09afb62; sha256 95337fbc360113f1e77fc48192b1ff12ffb2a22981b63fd69ce8b9f7e8ba08fd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.42146. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Planning with world models enables test-time adaptation for embodied agents, offering superior generalization over direct policy learning. However, long-horizon tasks remain hindered by cumulative errors and search complexity. Existing hierarchical methods often use rigid macro-actions or latent skills, leading to brittle representations and limited fine-grained control. We introduce ID-WM (Implicit Dynamics World Models), a hierarchical world model that decouples state-space reachability from local control. Our framework utilizes a high-level model to sample feasible transitions across the state manifold and a low-level world model as an inverse dynamics solver to ground these transitions into precise actions. This allows the planner to identify reachable subgoals without being constrained by low-level execution details. By prioritizing local physical feasibility over global behavioral patterns, ID-WM synthesizes novel long-horizon plans from short segments, transcending the specific behavioral modes seen during training. We demonstrate its effectiveness across three navigation and manipulation suites, achieving a 38.5% improvement over state-of-the-art policy and diffusion-based planners. Crucially, by leveraging this hierarchical structure to mitigate compounding errors, our approach yields a 135% performance gain over single-level world model MPC, particularly in complex, unseen configurations for long-horizon tasks. Videos can be viewed at this https URL

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.42146 — 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 2026-11-03T07:29:33.756Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).