AI游戏引擎：像素背后藏着状态
现在的AI生成游戏画面，本质是“猜下一帧”——它不知道游戏里发生了什么，只是根据你的操作预测画面。但真正的游戏引擎需要记住：你捡了钥匙、门开了、怪物血量变了。这篇论文把问题拆成四个维度：操作控制、状态更新、长期记忆、实时生成，并指出当前AI模型在“状态持久性”上几乎为零。他们用《黑神话：悟空》90小时的真实游戏数据（含玩家操作、游戏状态、画面帧）作为基准，让AI学会“看状态”而非“猜像素”。这不是你明天能玩的游戏，但它划清了“视频生成”和“游戏引擎”的界限——前者是幻觉，后者是规则。
📄 原文摘要(英文)
Building interactive worlds that respond coherently to player actions has long been a shared goal of computer graphics, games, and artificial intelligence. Recent video generative models provide a data-driven route toward this goal by predicting future observations conditioned on user actions, and are increasingly regarded as potential next-generation game engines. Realizing a genuinely interactive game world, however, requires interaction outcomes that follow rules over evolving game conditions, consequences that persist over long horizons, and a generation loop that operates in real time. Conventional game engines realize these properties through a recurrent action-state-observation loop, in which player actions update an explicit game state according to predefined rules and observations are rendered from the resulting state. Taking this loop as an organizing lens, this paper examines interactive game world modeling along four dimensions: player action control, game state dynamics, state-observation persistence, and real-time interactive generation. For each dimension, we start from the capabilities required by an interactive game world, group existing approaches into representative families, and discuss the strengths and trade-offs of each family. Complementing this analysis, we present a scalable data engine for Black Myth: Wukong that collects over 90 hours of gameplay with frame-aligned player actions, ground-truth game states, and visual observations, together with structured and semantic annotations, as a resource for state-aware game world modeling. We hope this paper offers a clear picture of where the field stands and fosters progress toward interactive game worlds.