MASS：具有权威共享状态的多玩家世界模型

摘要

当前的视频世界模型在多玩家环境中面临困难，因为它们将世界状态与视角相关的视觉潜变量纠缠在一起，导致计算冗余、视角不一致以及可扩展性差。我们提出MAS（基于权威共享状态的多玩家世界模型）来解决这一局限。受多玩家游戏架构启发，MAS将世界动态与视角渲染解耦。一个学习得到的逻辑引擎仅依据联合动作推进全局、权威的类型化状态，无需任何手写转移函数，并充当唯一的循环记忆与同步参考。基于这一共享状态，一个学习得到的渲染引擎能够按需为任意请求的视角生成独立且一致的视图。这种显式解耦使MAS在与最先进的多视角基线进行匹配多玩家贪吃蛇基准测试时，实现了更优的状态准确性和更低的跨视角不一致性。它能够以1，024个并发玩家推进预测世界10，000个循环步骤。我们的结果表明，显式的权威状态建模为可扩展且一致的多智能体世界模拟提供了实用基础。

English

Current video world models struggle in multiplayer environments because they entangle world state with view-dependent visual latents, leading to redundant compute, view inconsistencies, and poor scalability. We propose MAS (Multiplayer world models with Authoritative Shared State) to resolve this limitation. Inspired by multiplayer game architectures, MAS disentangles world dynamics and view rendering. A learned Logic Engine advances a global, authoritative typed state from joint actions without any hand-written transition function, acting as the sole recurrent memory and synchronization reference. From this shared state, a learned Rendering Engine generates independent and consistent views for any requested camera on demand. This explicit disentangling allows MAS to achieve superior state accuracy and lower cross-view inconsistency compared to state-of-the-art multi-view baselines on a matched multiplayer Snake benchmark. It advances predicted worlds with 1,024 concurrent players for 10,000 recurrent steps. Our results show that explicit, authoritative state modeling provides a practical foundation for scalable and consistent multi-agent world simulation.