From Generative Engines to Actionable Simulators: The Imperative of Physical Grounding in World Models
This addresses the issue of unreliable world models for AI researchers and practitioners, particularly in safety-critical domains like healthcare, but it is incremental as it builds on existing critiques and proposes a reframing rather than a new method.
The paper tackles the problem of world models in AI, which currently prioritize visual realism over physical and causal understanding, leading to failures in safety-critical decision-making. It argues for reframing world models as actionable simulators that encode causal structure and respect constraints, demonstrated through medical decision-making scenarios where errors are irreversible.
A world model is an AI system that simulates how an environment evolves under actions, enabling planning through imagined futures rather than reactive perception. Current world models, however, suffer from visual conflation: the mistaken assumption that high-fidelity video generation implies an understanding of physical and causal dynamics. We show that while modern models excel at predicting pixels, they frequently violate invariant constraints, fail under intervention, and break down in safety-critical decision-making. This survey argues that visual realism is an unreliable proxy for world understanding. Instead, effective world models must encode causal structure, respect domain-specific constraints, and remain stable over long horizons. We propose a reframing of world models as actionable simulators rather than visual engines, emphasizing structured 4D interfaces, constraint-aware dynamics, and closed-loop evaluation. Using medical decision-making as an epistemic stress test, where trial-and-error is impossible and errors are irreversible, we demonstrate that a world model's value is determined not by how realistic its rollouts appear, but by its ability to support counterfactual reasoning, intervention planning, and robust long-horizon foresight.