arXiv cs.AI· 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·· 11 小时前AI 评分38
Khora：支持推理时任意数量智能体的可扩展多智能体世界模型
Population-Scalable Multi-Agent World Modeling across Scene Geometries
AI 导读
研究者提出 Khora，一个可扩展多智能体世界模型，支持在推理时扩展到任意数量智能体而无需重新训练。该框架将世界状态演化与视觉渲染解耦，通过共享世界状态而非视频生成器内的密集交互维持跨视角一致性，实际扩展随查询视角数近似线性。定性实验显示其可泛化到未见过的智能体数量，并已实现实时交互系统演示开放世界模拟。
正文 · 原文
Authors: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
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.
| Comments: | Technical report. Project page: this https URL. Online demo: this https URL |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2608.08600 [cs.CV] |
| (or arXiv:2608.08600v4 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2608.08600 arXiv-issued DOI via DataCite |
Submission history
From: Mingyu Zhang [view email]
[v1]
Sun, 9 Aug 2026 09:26:15 UTC (20,021 KB)
[v2]
Mon, 17 Aug 2026 08:23:48 UTC (20,103 KB)
[v3]
Mon, 24 Aug 2026 03:33:59 UTC (20,103 KB)
[v4]
Thu, 5 Nov 2026 13:13:10 UTC (32,870 KB)
来源：arXiv cs.AI · arxiv.org