ReactiveGWM: Steering NPC in Reactive Game World Models
Quick Take
ReactiveGWM enables dynamic player-NPC interactions by decoupling controls and behaviors for scalable gameplay.
Key Points
- Introduces a reactive game world model for NPC interactions.
- Decouples player controls from NPC behaviors using cross-attention.
- Enables zero-shot strategy transfer across different games.
📖 Reader Mode
~2 min readAbstract: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.
| Comments: | The code is available at this https URL |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2605.15256 [cs.CV] |
| (or arXiv:2605.15256v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2605.15256 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zeqing Wang [view email]
[v1]
Thu, 14 May 2026 17:52:03 UTC (4,117 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →GeoSym127K: Scalable Symbolically-verifiable Synthesis for Multimodal Geometric Reasoning
GeoSym127K introduces a scalable neuro-symbolic framework for enhanced geometric reasoning in multimodal models.