Wizard: Agentic game world model achieves real-time character control
What happened
Yuzhe Wu and others propose Wizard, an agentic game world model, claiming it can precisely control character actions in real time and achieve zero-shot generalization to new scenes, characters, and actions. The authors built a dataset covering 750 scenes and 178 characters, using skeleton and geometry information as structured representations to condition a video generation model, and introduced an adaptive masking mechanism to improve the consistency between the conditioning signal and the generated video. A companion agent framework explicitly maintains and updates game state, letting players configure virtual worlds and control character actions at fine granularity. The above results are all claims by the paper's authors.
AI-written from the coverage · updated 23 d ago
Coverage timeline
Follow the coverage to see the story from different sides.
- arXiv Game World Models & GenerationPickWizard: Manipulate any world in real time via agentic control
The paper proposes Wizard, an agentic game world model that can precisely control character actions in real time and achieve zero-shot generalization to new scenes, characters, and actions. The authors built a dataset covering 750 scenes and 178 characters, using skeleton and geometry information as structured representations to condition a video generation model, and introduced an adaptive masking mechanism to improve the consistency between the conditioning signal and the generated video. A companion agent framework explicitly maintains and updates game state, letting players freely configure virtual worlds and control character actions at fine granularity.