The game engine rule that generative models keep forgetting

For a decade, tech has promised that generative AI would eventually replace the game engine. Feed a model a few frames of a player running through a forest, let it extrapolate the next frames, and ta-da: infinite, reactive worlds without a polygon in sight. It's a seductive vision, and video generative models have gotten good enough that the hype has started to sound plausible.

But any developer who has built an interactive system knows the problem. A generative model trained to predict pixels has no concept of a health bar, that a door opened three minutes ago should stay open, or that a player's inventory persists across scenes. It only sees frames. And when you only have frames, the world resets every time the player blinks. This blind spot matters beyond games: it's the same reason small vision-language models struggle to act in the real world.

A new paper from AlayaLab, posted on arXiv in July 2026 under the title From Pixels to States: Rethinking Interactive World Models as Game Engines, takes this tension seriously. Instead of asking how to make video generation more realistic, the authors ask a more fundamental question: what do game engines actually do that generative models don't, and how do we bridge that gap?

The loop that keeps a world alive

The paper's central move is to take the conventional game engine loop as its organizing lens. In a traditional engine, the flow is: the