Metraipolis › archive › dc_5545f6d38398
Rethinking World Models for Safety-Critical Embodied Systems — arXiv:2609.03774
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.03774
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T01:11:15.896Z
- SHA-256 of the archived text
5f11f8084bebee44628c7847a408dfad879c5357b5f49a56d9dedabda6f87596- Stable URL of this page
https://metraipolis.com/documento/dc_5545f6d38398
How to cite
Rethinking World Models for Safety-Critical Embodied Systems — arXiv:2609.03774 — arXiv (en), https://arxiv.org/abs/2609.03774 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5545f6d38398 (Metraipolis archive dc_5545f6d38398, sha256 5f11f8084bebee44628c7847a408dfad879c5357b5f49a56d9dedabda6f87596)
BibTeX
@misc{dc5545f6d38398,
title = {Rethinking World Models for Safety-Critical Embodied Systems — arXiv:2609.03774},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.03774},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5545f6d38398; sha256 5f11f8084bebee44628c7847a408dfad879c5357b5f49a56d9dedabda6f87596},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03774. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
World models have progressed from compact latent dynamics to generative, controllable, and interactive simulators of embodied environments. However, high predictive likelihood and visual fidelity do not necessarily ensure that a model preserves the evidence required for safe decision-making. This perspective identifies three structural mismatches in current world modeling: likelihood versus risk, prediction versus intervention, and finite-horizon prediction versus accumulated consequences. We propose the Risk-Informed World Model (RIWM) as a decision-centric research direction for safety-critical embodied systems. RIWM organizes world modeling around consequences, intervention, epistemic uncertainty, and recoverability, and integrates four interdependent capabilities: decision-relevant representation, counterfactual reasoning, safety-critical episodic memory, and runtime safety assurance. It distinguishes physical, social, and operational consequences while using epistemic uncertainty to qualify the evidence supporting action. We further discuss open challenges in identifying consequential futures, validating counterfactual reasoning, maintaining revisable safety memories, translating learned consequences into executable constraints, and determining when evidence is sufficient to act. This perspective argues that future world models should move beyond predicting likely futures toward identifying which futures matter, revising judgments through experience, and recognizing when to act, revise, sense, defer, or abstain. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.03774 — 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 2026-10-17T00:28:02.874Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).