| pipeline_tag: image-to-video | |
| base_model: nvidia/Cosmos-Predict2.5-2B | |
| tags: | |
| - World-Model | |
| - Multi-Agent | |
| # **Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players** | |
| [**Code**](https://github.com/nv-tlabs/Gamma-World) | [**Paper**](https://huggingface.co/papers/2605.28816) | [**Website**](https://research.nvidia.com/labs/sil/projects/gamma-world/) | |
| Gamma-World (γ-World) is a generative multi-agent world model that renders a single shared world in which several independently-controlled agents stay causally connected. It supports action-responsive streaming rollouts and generalizes from two-player training to four-player (and beyond) interaction without additional training. Gamma-World is built on the NVIDIA Cosmos stack ([Cosmos-Predict2.5](https://github.com/nvidia-cosmos/cosmos-predict2.5)). | |
| ## Citation | |
| ```bibtex | |
| @article{gammaworld2026, | |
| title={Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players}, | |
| author={Fangfu Liu and Kai He and Tianchang Shen and Tianshi Cao and | |
| Sanja Fidler and Yueqi Duan and Jun Gao and Igor Gilitschenski and | |
| Zian Wang and Xuanchi Ren}, | |
| journal={arXiv preprint arXiv:2605.28816}, | |
| year={2026} | |
| } | |
| ``` | |