ReactiveGWM: Steering NPC in Reactive Game World Models

Hugging Face Daily Papers Papers
game-ai npc-behavior diffusion-models cross-attention zero-shot-transfer game-world-models player-npc-interaction

Summary

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.

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.
Original Article
View Cached Full Text

Cached at: 05/18/26, 02:23 AM

Paper page - ReactiveGWM: Steering NPC in Reactive Game World Models

Source: https://huggingface.co/papers/2605.15256

Abstract

ReactiveGWM enables dynamic player-NPC interactions in game worlds by decoupling player controls from NPC behaviors through diffusion models with cross-attention modules for game-agnostic strategy transfer.

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, areactive game world modelthat synthesizes dynamic interactions between the player and NPC. Instead of entangling all interaction dynamics, ReactiveGWM explicitly decouplesplayer controlsfromNPC 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 throughcross-attention modules. Crucially, these modules learn agame-agnostic representationofinteractive logic. This enableszero-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 interactionwith the NPC.

View arXiv pageView PDFProject pageGitHub9Add to collection

Get this paper in your agent:

hf papers read 2605\.15256

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/2605.15256 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2605.15256 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.15256 in a Space README.md to link it from this page.

Collections including this paper1

Similar Articles

Multi-Agent World Models (3 minute read)

TLDR AI

γ-World is a generative multi-agent world model that supports independently controllable, permutation-symmetric agents using Simplex Rotary Agent Encoding and Sparse Hub Attention, achieving real-time 24 FPS rollouts and zero-shot generalization from two to four players.

PROWL: Prioritized Regret-Driven Optimization for World Model Learning

arXiv cs.LG

Introduces PROWL, a prioritized regret-driven optimization framework that uses an adversarial curriculum to improve diffusion-based world model robustness by focusing on high-error trajectories, achieving better performance on out-of-distribution scenarios in MineRL.