发表机构
Tencent（腾讯）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对现有游戏世界模型中NPC行为与视频生成绑定的问题，提出首个解耦框架WorldMind，构建BOSS-140K数据集，实验显示其NPC行为更优。
AI 中文摘要
游戏世界模型近期在生成视觉连贯、动作可控的游戏视频方面展现出良好能力。然而，现有模型中的非玩家角色（NPC）行为要么与视频生成隐式绑定，要么通过外部控制信号显式指定，导致游戏世界模型需同时理解状态、规划NPC响应并渲染视觉结果，限制了其生成响应迅速且状态感知的NPC行为的能力。核心挑战在于缺乏基于状态的显式决策接口。为此，我们提出WorldMind，据我们所知，这是首个用于游戏世界模型中状态感知NPC行为的解耦框架。WorldMind将交互式世界建模分为四层：理解层（从生成的帧中构建紧凑状态）、决策层（对紧凑状态推理以规划NPC的下一个动作）、控制层（将动作转换为时间对齐的条件）、生成层（合成其视觉结果）。通过在闭环交互循环中重新连接各层，WorldMind将NPC行为与不断变化的游戏状态关联。我们还推出BOSS-140K，这是一个包含游戏视频及丰富内部游戏状态的数据集，以及一个可大规模自动收集数据的智能体。在BOSS-140K上的实验表明，该模型可实现可靠的紧凑状态重建和基于机制的规划，在约70%的成对比较中，WorldMind因NPC行为更符合战术需求且更连贯，优于基线模型。项目页面：this https URL
英文摘要
Game world models have recently demonstrated promising capabilities in generating visually coherent and action-controllable gameplay videos. However, non-player character (NPC) behavior in existing models is either implicitly entangled with video generation or explicitly prescribed through external control signals. Consequently, a game world model has to jointly understand the state, plan the NPC's response and render its visual outcome, limiting its ability to produce responsive and state-aware NPC behavior. The challenge lies in the lack of an explicit interface for state-grounded decision-making. To this end, we introduce WorldMind, to our knowledge the first decoupled framework for state-aware NPC behavior in game world models. WorldMind separates interactive world modeling into four layers: an Understanding Layer that constructs a compact state from generated frames; a Decision Layer that reasons over the compact state to plan the NPC's next action; a Control Layer that translates the actions into temporally aligned conditions; and a Generation Layer that synthesizes their visual outcomes. By reconnecting layers in a closed interaction loop, WorldMind grounds NPC behavior in the evolving game state. We further introduce BOSS-140K, a dataset of gameplay videos paired with rich internal game states, together with an agent that automates the collection at scale. Experiments on BOSS-140K demonstrate reliable compact state reconstruction and mechanics-grounded planning, with WorldMind preferred over the baselines in approximately 70% of pairwise comparisons for its more tactically appropriate and coherent NPC behavior. Project page: https://teawhite.cn/worldmind_projectpage/
CommentsProject page: https://teawhite.cn/worldmind_projectpage/
