World models will be how general purpose robots finally work. They are essentially learned simulators of the world. They will replace traditional robotics simulators which are not flexible enough to enable training of general robotics policies. Robot control policies will be trained and evaluated in learned simulators, and the policies themselves will also be world models in order to predict the consequences of their own actions and thus enable planning. Simulated data will scale much better than expensive real-world robot data, and will allow robot policies to reach LLM-level dataset sizes, and subsequently, LLM-level performance.

It is inevitable that learned simulators will replace hand-coded simulators, as it is a straightforward application of the Bitter Lesson: http://www.incompleteideas.net/IncIdeas/BitterLesson.html

By enabling general purpose robotics, world models will be one of the most useful inventions of all time. For examples of what I'm talking about in current research, check:

Dreamer 4: https://danijar.com/project/dreamer4/

DreamDojo: https://arxiv.org/abs/2602.06949

Tesla's world model: https://www.youtube.com/watch?v=LFh9GAzHg1c

Waymo's world model: https://waymo.com/blog/2026/02/the-waymo-world-model-a-new-f...