LiveAct: heterogeneous action interfaces for real-time multi-agent world models
LiveAct: Towards Real-Time Multi-Agent World Models with Heterogeneous Action Interfaces
LiveAct introduces a heterogeneous action interface that lets a multi-agent video world model generate joint visual futures for multiple controlled agents, handling control inputs ranging from game buttons to robot commands. The method reaches agent attribution accuracy of 0.898 on games and 0.942 on multi-robot manipulation, without relying on agent position or identity cropping. Its causal generator runs at 17.70 FPS at 512×448 resolution.
The work binds each action stream to its corresponding visual agent and reports streaming generation at 17.70 FPS, making it a useful comparison point for existing single-agent interactive world models.
Source: arXiv Game World Models & Generation · arxiv.org