SOURCE-LINKED INTELLIGENCE

Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning

arXiv · AI, language, vision and robotics · article · Aug 27, 2026 · UTC

Physical understanding and reasoning depend on forming compact and generalizable representations of the world. While modern vision-language models can recognize and explain diverse physical events, they often lack explicit representations of the underlying mechanisms-such as object states, physical parameters, and governing dynamics-needed for reliably reasoning how the world evolves and responds to interventions. In this work, we introduce Code-as-World, a paradigm that represents physical worlds through executable world representations. By expressing physical composition, dynamic evolution,

Read original source ↗ Open in workspace

recordType

paper

region

Global