提出可支持千人并发的多玩家世界模型，解决视图不一致问题。
MASS: Multiplayer World Models with Authoritative Shared State
- 分离全局状态与视角渲染，用逻辑引擎统一更新世界状态。
- 在蛇类多人游戏上实现1024玩家并发运行1万步，状态更准、视图更一致。
- 适合需要高并发、强一致性模拟的多智能体系统研究者。
当前视频世界模型在多玩家环境中表现不佳，因其将世界状态与依赖视角的视觉隐变量纠缠，导致计算冗余、视图不一致且难以扩展。本文提出MASS（Multiplayer world models with Authoritative Shared State），受多人游戏架构启发，显式解耦世界动态与视图渲染。一个学习得到的逻辑引擎基于联合动作推进全局、权威的类型化状态，无需人工编写转移函数，作为唯一的循环记忆与同步参考。由此共享状态出发，一个学习得到的渲染引擎可按需生成任意视角的独立且一致的视图。该显式解耦使MASS在匹配的多人贪吃蛇基准测试中，相比现有最先进多视角基线，在状态准确性与跨视角一致性上均取得提升。模型成功推进了包含1024名并发玩家的世界，持续10,000个递归步。结果表明，显式的权威状态建模为可扩展、一致的多智能体世界模拟提供了切实可行的基础。
原文摘要 · Abstract (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 MASS (Multiplayer world models with Authoritative Shared State) to resolve this limitation. Inspired by multiplayer game architectures, MASS 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 MASS 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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。