Coding Agent Is Good As World Simulator

ArXi:2605.14398v1 Announce Type: new World models have emerged as a powerful paradigm for building interactive simulation environments, with recent video-based approaches nstrating impressive progress in generating visually plausible dynamics. However, because these models typically infer dynamics from video and represent them in latent states, they do not explicitly enforce physical constraints. As a result, the generated video rollouts are not physically plausible, exhibiting unstable contacts, distorted shapes, or inconsistent motion.