Population-Scalable Multi-Agent World Modeling
Renjie Zhao, Yuxiang Wu, Mingyu Zhang, Jiaxin Li, Sisi Li, He Li, Yimin Sheng, Tianxi Tan, Zhenkai Zhang, Jiao Liang, Jianyi Zhu, Yong-Lu Li
cs.CV, cs.AI, cs.LG
Submitted: 2026-08-24
Updated: 2026-08-25
Comments: Technical report. Project page: https://rhos.ai/research/khora. Online demo: https://ophilus.ai/khora
Project page: https://rhos.ai/research/khora
License: http://creativecommons.org/licenses/by/4.0/
The gist: World models have recently achieved impressive progress in visual prediction and interactive generation, but extending them to multi-agent environments introduces a fundamental scalability challenge.
Terminology
Abstract
World models have recently achieved impressive progress in visual prediction and interactive generation, but extending them to multi-agent environments introduces a fundamental scalability challenge. Existing methods generally assume a fixed number of agents during training and inference, which ties the model to a pre-determined agent population and limits inference-time scalability. Our key insight is that cross-view consistency should arise from a shared world state whose evolution does not assume a predefined number of agents, while agent-specific observations should be generated by querying this state through a unified rendering interface. Based on this insight, we propose Khora, a scalable multi-agent world model that supports inference-time expansion to arbitrary numbers of agents without retraining. Our framework decouples world-state evolution from visual rendering and introduces a population-agnostic rendering mechanism for incorporating other agent information. This design maintains cross-view consistency through the shared world state rather than through dense interactions among observation streams inside the expensive video generator, enabling approximately linear practical scaling with the number of queried views. Qualitative experiments demonstrate that our approach generalizes to unseen numbers of agents while maintaining visual quality and multi-agent consistency. We further implement a real-time interactive system to demonstrate scalable open-world simulation.
Sources
- Diffusion for World Modeling: Visual Details Matter in Atari
- Genie: Generative Interactive Environments
- AdaWorld: Learning Adaptable World Models with Latent Actions
- World Models
- Mastering Diverse Domains through World Models
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Multiplayer Interactive World Models with Representation Autoencoders
- Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players
- MultiGen: Level-Design for Editable Multiplayer Worlds in Diffusion Game Engines
- Solaris: Building a Multiplayer Video World Model in Minecraft
- Towards Accurate Generative Models of Video: A New Metric & Challenges
- MultiWorld: Scalable Multi-Agent Multi-View Video World Models
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models