SOURCE-LINKED INTELLIGENCE

Code World Model: Coding Agent as World Brain

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

World models aim to simulate how complex environments evolve under actions and events, yet existing video-based world models primarily learn dynamics from visual observations, which reveal outcomes rather than the underlying knowledge, rules, and mechanisms governing world evolution. This makes it difficult to maintain persistent consequences and support coherent, open-ended evolution. We introduce Code World Model, a framework that separates world evolution from visual realization by combining the reasoning and coding capabilities of language models with the generative priors of video models.

Read original source ↗ Open in workspace

recordType

paper

region

Global