Abstract
Current video world models struggle in multiplayer environments because they entangle world state with view-dependent visual latents, leading to redundant compute, view inconsistencies, and poor scalability. We propose MAS (Multiplayer world models with Authoritative Shared State) to resolve this limitation. Inspired by multiplayer game architectures, MAS disentangles world dynamics and view rendering. A learned Logic Engine advances a global, authoritative typed state from joint actions without any hand-written transition function, acting as the sole recurrent memory and synchronization reference. From this shared state, a learned Rendering Engine generates independent and consistent views for any requested camera on demand. This explicit disentangling allows MAS to achieve superior state accuracy and lower cross-view inconsistency compared to state-of-the-art multi-view baselines on a matched multiplayer Snake benchmark. It advances predicted worlds with 1,024 concurrent players for 10,000 recurrent steps. Our results show that explicit, authoritative state modeling provides a practical foundation for scalable and consistent multi-agent world simulation.
Community
Stop making a world model dream 1,024 separate videos. MASS learns one authoritative world state, advances it once, and renders every player’s view on demand, scaling to 1,024 players for 10,000 recurrent steps.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Walking in the Implicit: Interactive World Exploration via Neural Scene Representation (2026)
- From Pixels to States: Rethinking Interactive World Models as Game Engines (2026)
- Current World Models Lack a Persistent State Core (2026)
- AlayaWorld: Long-Horizon and Playable Video World Generation (2026)
- AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Report (2026)
- ActWorld: From Explorable to Interactive World Model via Action-Aware Memory (2026)
- MoVerse: Real-Time Video World Modeling with Panoramic Gaussian Scaffold (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend
Get this paper in your agent:
hf papers read 2608.06257 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper