MultiGen：可编辑多人世界在扩散式游戏引擎中的关卡设计

MultiGen: Level-Design for Editable Multiplayer Worlds in Diffusion Game Engines

March 30, 2026

作者: Ryan Po, David Junhao Zhang, Amir Hertz, Gordon Wetzstein, Neal Wadhwa, Nataniel Ruiz

cs.AI

摘要

视频世界模型在交互式仿真与娱乐领域展现出巨大潜力，但现有系统仍面临两大交互性挑战：用户对环境可控性以实现可复现、可编辑的体验，以及支持多玩家对共享世界施加影响的协同推理。为突破这些局限，我们在系统中引入了显式外部记忆机制——一种独立于模型上下文窗口的持久化状态，该状态通过用户行为持续更新并在生成推演过程中被实时查询。与传统扩散式游戏引擎采用下一帧预测的模式不同，我们的方法将生成过程解构为记忆、观测与动态三大模块。这一设计通过可编辑的记忆表征赋予用户对环境结构的直接控制权，并能自然扩展至实时多玩家推演场景，确保视角连贯性与跨玩家交互的一致性。

English

Video world models have shown immense promise for interactive simulation and entertainment, but current systems still struggle with two important aspects of interactivity: user control over the environment for reproducible, editable experiences, and shared inference where players hold influence over a common world. To address these limitations, we introduce an explicit external memory into the system, a persistent state operating independent of the model's context window, that is continually updated by user actions and queried throughout the generation roll-out. Unlike conventional diffusion game engines that operate as next-frame predictors, our approach decomposes generation into Memory, Observation, and Dynamics modules. This design gives users direct, editable control over environment structure via an editable memory representation, and it naturally extends to real-time multiplayer rollouts with coherent viewpoints and consistent cross-player interactions.