Programmable world model keeps game states consistent for longer play
Programmable World Model
Computer Vision and Pattern Recognition
Summary
Video games and simulations often struggle to keep their worlds consistent and remember what happened earlier during long play sessions. This paper presents a method where the game’s rules and object states are controlled by computer programs, separate from how the images are created. The authors use a special system that tracks all objects and their changes over time, even if they are not visible on screen. They then connect these states to a video-generating part that shows the game visually. Their approach helps make games with clear rules and persistent worlds that can be played for longer without losing track of what’s going on.
world modelstate persistencenatural language programmingentity statestate-transition rules3D oriented bounding boxesspatiotemporal conditioningvideo generationinteractive gameplaybenchmark evaluation
Authors
Zheng-Hui Huang, Guixu Lin, Jiacheng Lin, Yi-Chuan Huang, Ruihan Yu, Muyao Niu, Siqi Yang, Yu-Lun Liu, Yung-Yu Chuang, Kaipeng Zhang, Zhixiang Wang
Abstract
Recent video world models generate increasingly realistic and interactive visual experiences, yet lack reliable mechanisms for maintaining persistent world state and enforcing programmable rules over extended interactions. We introduce Programmable World Model, a framework that decouples world-state evolution from visual observation generation. An agent translates natural-language instructions into executable programs that specify entity states and state-transition rules, enabling direct control over individual entities and their interactions. A lightweight engine executes these programs to update and maintain an explicit, persistent global world state, including off-screen entities and non-visual attributes. To connect world state with visual generation, we introduce state-augmented 3D oriented bounding boxes (OBBs) as an intermediate representation. This representation, together with the target camera trajectory, is deterministically compiled into pixel-aligned spatiotemporal conditioning signals for a pretrained video model serving as the generative renderer. This design allows users to create playable games with predefined mechanics, direct control over individual entities, and persistent world state throughout gameplay. We further introduce CombatStateBench, a benchmark for evaluating programmable world models. On CombatStateBench, our method achieves 94% Count Accuracy and 98% State Accuracy, substantially outperforming existing interactive video world models while supporting coherent long-horizon generation. These results demonstrate the effectiveness of separating explicit state evolution from generative rendering for building persistent, programmable worlds.