多人世界模型：把世界状态和画面分开算
现在的视频世界模型一进多人场景就乱套：它把“世界本身”和“每个玩家看到的画面”搅在一起算，人一多就重复计算、画面互相矛盾。这篇论文学的是多人游戏服务器的做法——把“世界状态”和“画面渲染”彻底拆开：一个逻辑引擎只负责推进全局状态（谁在哪、发生了什么），一个渲染引擎再按需给每个玩家生成各自视角的画面。结果在多人贪吃蛇基准上，状态更准、视角更一致，还能同时模拟1024个玩家跑1万步。它不是你明天能用上的东西，但给“AI模拟多人世界”指了一条更省力、更靠谱的路。
📄 原文摘要(英文)
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.