ReactiveGWM：在反應式遊戲世界模型中引導NPC

摘要

當前的遊戲世界模型是從主觀且以玩家為中心的視角來模擬環境。然而，這類模型將非玩家角色（NPC）僅視為背景像素，因而無法捕捉玩家與NPC之間的互動。就此而論，它們更像是被動的影像渲染器，而非真正的模擬引擎，缺乏理解動作所引發的NPC反應所需的物理常識。我們提出ReactiveGWM，這是一種反應式遊戲世界模型，能夠合成玩家與NPC之間的動態互動。不同於將所有互動動態糾纏在一起，ReactiveGWM明確地將玩家控制與NPC行為解耦。玩家動作透過輕量化的加性偏置注入到擴散主幹網路中，而高階的NPC反應（例如：攻擊、控制、防禦）則透過交叉注意力模組來落實。關鍵在於，這些模組學會了一種與遊戲無關的互動邏輯表徵。這使得零樣本策略遷移成為可能：我們學習到的模組可以直接插入不同遊戲中現成的、未經標註的世界模型，無需任何領域特定的重新訓練，便能立即啟用可操控的NPC互動。在兩款《快打旋風》遊戲上的評估顯示，ReactiveGWM在維持精細的玩家可控性的同時，也實現了穩健且符合提示引導的NPC策略遵從，為可擴展且富含策略的NPC互動開闢了道路。

English

Current game world models simulate environments from a subjective, player-centric perspective. However, by treating the Non-Player Character (NPC) merely as background pixels, these models cannot capture interactions between the player and NPC. In that sense, they act as passive video renderers rather than real simulation engines, lacking the physical understanding needed to model action-induced NPC reactivities. We introduce ReactiveGWM, a reactive game world model that synthesizes dynamic interactions between the player and NPC. Instead of entangling all interaction dynamics, ReactiveGWM explicitly decouples player controls from NPC behaviors. Player actions are injected into the diffusion backbone via a lightweight additive bias, while high-level NPC responses (e.g., Offense, Control, Defense) are grounded through cross-attention modules. Crucially, these modules learn a game-agnostic representation of interactive logic. This enables zero-shot strategy transfer: our learned modules can be plugged directly into off-the-shelf, unannotated world models of different games. This instantly unlocks steerable NPC interactions without any domain-specific retraining. Evaluated on two Street Fighter games, ReactiveGWM maintains fine-grain player controllability while achieving robust, prompt-aligned NPC strategy adherence, paving the way for scalable, strategy-rich interaction with the NPC.