ReactiveGWM：在反应式游戏世界模型中引导NPC

摘要

当前游戏世界模型从主观的玩家中心视角模拟环境。然而，由于将非玩家角色（NPC）仅视为背景像素，这些模型无法捕捉玩家与NPC之间的交互。在此意义上，它们充当被动的视频渲染器而非真正的模拟引擎，缺乏对动作引发NPC反应所需的物理理解。我们提出ReactiveGWM——一种反应式游戏世界模型，能够合成玩家与NPC之间的动态交互。ReactiveGWM并非将所有交互动力学纠缠在一起，而是明确地将玩家控制与NPC行为解耦。玩家动作通过轻量级加性偏置注入扩散骨干网络，而高层NPC响应（如攻击、控制、防御）则通过交叉注意力模块进行锚定。关键在于，这些模块学习了一种与具体游戏无关的交互逻辑表示，从而实现了零样本策略迁移：我们的学习模块可直接插入不同游戏现成的、无标注的世界模型中，立即解锁可控的NPC交互，无需任何领域特定重训练。在《街头霸王》两款游戏上的评估表明，ReactiveGWM在保持精细玩家可控性的同时，实现了稳健的、与提示对齐的NPC策略遵循，为可扩展的、富含策略的NPC交互铺平了道路。

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.