arXiv cs.MA· Meryem Koksal, Yunzhe Wang, Volkan Ustun·· 12 小时前AI 评分31
FlockWorld：基于人工生命模拟的种群级多智能体视频世界模型
FlockWorld: Toward Population-Scale Multi-Agent Video World Models through Artificial Life Simulation
AI 导读
FlockWorld 是基于 Reynolds Boids 算法构建的人工生命环境，用于研究种群级多智能体视频世界模型，可渲染同步的自我中心视角裁剪画面并独立配置相机智能体数量。
正文
Abstract:Most action-conditioned video world models remain limited to a single player, while existing multiplayer models support only small, fixed groups of agents. We introduce FlockWorld, an artificial-life environment built on Reynolds's Boids algorithm for studying population-scale multi-agent video world models. Specifically, FlockWorld renders synchronized egocentric crops, assigns distinct colors to preserve camera-agent identity across views, exposes rule-derived accelerations as actions, and lets the number of camera agents be configured independently of the size of the surrounding population. We further introduce FlockDiT, an action-conditioned latent diffusion transformer trained with flow matching on FlockWorld data to jointly generate synchronized egocentric videos for multiple agents. Our results suggest that joint generation benefits agent detection at density-matched settings and that diffusion forcing improves rollout fidelity. Together, FlockWorld and FlockDiT provide a controlled testbed for multi-agent video generation.
| Comments: | Accepted to NeurIPS 2026, Creative AI Track |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2610.34564 [cs.CV] |
| (or arXiv:2610.34564v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.34564 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yunzhe Wang [view email]
[v1]
Sun, 25 Oct 2026 21:07:26 UTC (613 KB)
来源：arXiv cs.MA · arxiv.org