MASS：具有權威共享狀態的多人世界模型

摘要

當前的視頻世界模型在多人遊戲環境中表現不佳，因為它們將世界狀態與依賴視角的視覺潛在表示糾纏在一起，導致冗餘計算、視角不一致以及較差的可擴展性。我們提出具有權威共享狀態的多人世界模型（MAS，Multiplayer world models with Authoritative Shared State）來解決這個限制。受多人遊戲架構的啟發，MAS 將世界動力學與視角渲染解耦。一個學習的邏輯引擎根據聯合動作推進全局、權威的類型化狀態，無需任何手寫轉換函數，同時作為唯一的循環記憶和同步參考。基於這個共享狀態，一個學習的渲染引擎按需為任何請求的攝像機生成獨立且一致的視角。這種顯式解耦使得 MAS 在匹配的多人貪吃蛇基準測試中，與最先進的多視角基線相比，能夠實現更優的狀態準確性和更低的跨視角不一致性。它可推進具有 1,024 個並發玩家的預測世界，持續 10,000 個循環步驟。我們的結果表明，顯式、權威的狀態建模為可擴展且一致的多智能體世界模擬提供了實用基礎。

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.