From World Action Models to Embodied Brains: A Roadmap for Open-World Physical Intelligence

Key points

It defines WAMs as action-conditioned predictive models and classifies them as models that explicitly predict the results of interventions.
It identifies three structural limitations: the model-representation gap, the objective-standardization gap, and the ecosystem-system gap.
An embodied brain is the central model that integrates physical observations and compares interventions to output intended state transitions.
A physical harness converts the brain's outputs into execution tools and controllers, validates them, and records traces.
Shared contracts make heterogeneous data, tasks, and components mutually comparable.
Closed-loop post-training turns verified interactions into reusable experience.

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