# Rethinking World Models for Safety-Critical Embodied Systems

arXiv: https://arxiv.org/abs/2609.03774 · HTML: https://mlsanity.com/paper/2609.03774/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in World models for navigation, one of 11 directions in World models.
- Builds on 5 of its 34 references that are in the map.
- First posted on arXiv 3 Sep 2026.

## Placed in

- World models / [World models for navigation](https://mlsanity.com/wm/world-models-for-navigation/)

## Builds on (most cited first, 5 of 5)

- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2503.20523/) (2025)
- [Learning Humanoid Locomotion with World Model Reconstruction](https://mlsanity.com/paper/2502.16230/) (2025)
- [RISE: Adaptive Imagination for World Action Models](https://mlsanity.com/paper/2608.20430/) (2026)
- [A knowledge-augmented dataset of high-risk driving scenarios with LLM annotations for autonomous driving](https://mlsanity.com/paper/2607.07103/) (2026)

## Abstract (arXiv)

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.