World Action Models: A Survey

Key points

The survey defines WAM as a model that predicts actionable futures from observation and action history together with task context, and then uses those predictions to generate action.
It organizes WAMs along two classification axes: what should be generated, such as rendered, latent, or free, and how the system is decomposed into substrate, backbone, coupling, and deployment.
It identifies five core properties: interactability, causality, persistence, physical plausibility, and generalization.
It systematically categorizes more than 200 studies into five backbone families: diffusion, autoregressive, joint, optional-future, and related variants.
Its core insight is that WAMs are evolving toward a 'generate less, preserve only what is needed for control' design philosophy.

External research summaries. These are not HDATF publications or measured product results.