提出首个解耦游戏世界模型，让非玩家角色根据状态自主决策。
WorldMind: Decoupled Game World Model for State-Aware NPC Behavior
- 将游戏世界建模分为理解、决策、控制、生成四层，分离状态与行为
- 在自建数据集上实现90%以上状态重建准确率，70%对比中表现更优
- 适合游戏开发、智能体行为研究者，推动动态角色设计
游戏世界模型近年来在生成视觉连贯且可操作的游戏视频方面展现出潜力。然而，现有模型中的非玩家角色（NPC）行为要么隐式嵌入视频生成过程，要么通过外部控制信号显式指定，导致模型需同时理解状态、规划反应并渲染视觉结果，限制了其生成响应性强、状态感知的NPC行为能力。根本问题在于缺乏明确的状态驱动决策接口。为此，我们提出WorldMind，据知是首个面向游戏世界模型中状态感知型NPC行为的解耦框架。WorldMind将交互式世界建模分为四层：理解层从生成帧构建紧凑状态；决策层基于该状态推理并规划NPC下一步动作；控制层将动作转化为时间对齐的条件；生成层合成视觉结果。通过闭环重连各层，使NPC行为扎根于动态演变的游戏状态。我们还引入BOSS-140K，一个包含丰富内部状态的游戏视频数据集，并开发代理实现大规模自动化采集。在BOSS-140K上的实验表明，模型能可靠重建紧凑状态并进行机制驱动的规划，在70%的成对比较中被偏好，因其行为更具策略性与一致性。
原文摘要 · Abstract (English)
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/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。