WorldMind: Decoupled Game World Model for State-Aware NPC Behavior

Hugging Face Daily Papers Papers
game-ai npc-behavior world-models decoupled-architecture state-aware ai-research gaming

Summary

WorldMind introduces a decoupled framework for state-aware NPC behavior in game world models, separating world modeling into understanding, decision, control, and generation layers to enhance responsiveness.

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/
Original Article
View Cached Full Text

Cached at: 08/25/26, 04:35 AM

Paper page - WorldMind: Decoupled Game World Model for State-Aware NPC Behavior

Source: https://huggingface.co/papers/2608.21439

Abstract

WorldMind decouples game world modeling into state understanding, decision-making, control, and generation layers to enable explicit, state-aware NPC behavior.

Game world modelshave 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-awareNPC behavior. The challenge lies in the lack of an explicit interface forstate-grounded decision-making. To this end, we introduce WorldMind, to our knowledge the first decoupled framework for state-awareNPC behavioringame 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 aclosed interaction loop, WorldMind groundsNPC behaviorin 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 reliablecompact state reconstructionandmechanics-grounded planning, with WorldMind preferred over the baselines in approximately 70% of pairwise comparisons for its more tactically appropriate and coherentNPC behavior. Project page: https://teawhite.cn/worldmind_projectpage/

View arXiv pageView PDFProject pageGitHub0Add to collection

Get this paper in your agent:

hf papers read 2608\.21439

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2608.21439 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2608.21439 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.21439 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

ReactiveGWM: Steering NPC in Reactive Game World Models

Hugging Face Daily Papers

ReactiveGWM is a reactive game world model that enables dynamic player-NPC interactions by decoupling player controls from NPC behaviors using diffusion models and cross-attention modules, achieving zero-shot strategy transfer across different games.

Programmable World Model

Hugging Face Daily Papers

The Programmable World Model introduces a framework that decouples world-state evolution from visual generation, enabling persistent and controllable environments through executable programs and 3D bounding boxes.

MASS: Multiplayer World Models with Authoritative Shared State

Hugging Face Daily Papers

This paper introduces MASS, a method for multiplayer world models that disentangles world dynamics from view rendering using an authoritative shared state, enabling scalable and consistent multi-agent simulation with up to 1,024 concurrent players.