cs.RONov 11, 2026

Does Your World Model Know Actions Have Consequences?

Authors: Ayush Gaggar, Jared Berry, Todd D. Murphey

Organizations: Department of Mechanical Engineering Northwestern University, Evanston, IL, USA

Abstract

Embodied world models (WMs) are implicit learning systems that predict the next future latent state directly from observations and actions. Unique from other end-to-end learning systems, the dynamics predictor of WMs can simulate the environment's response to alternative actions without physical deployment nor pre-specifying states of the dynamical system. Current metrics focus on the quality of model outputs, e.g., clarity of reconstructions or task success, but fail to assess the fidelity of modeling consequences of counterfactual actions. Inspecting the forced response to action perturbations through sensitivity analysis is one way to audit how well WMs can predict the consequences of counterfactual actions. Deploying WMs on hardware will require new evaluation frameworks to analyze the tradeoffs between state error and accurate sensitivity prediction.

Figures & tables

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Counterfactual Action Evaluation, Observation Bottlenecks, and Representation Geometry in Joint-Embedding Predictive World Models

    Oct 2, 2026Arjun SubramanianWorld Model EvaluationAction-Conditioned World Models

  2. Rethinking World Models for Safety-Critical Embodied Systems

    Sep 3, 2026Kailang Ma, Heye Huang, Inhi Kim +1Runtime AssuranceEmbodied World Models