What changes when a video world model must represent several agents? This survey follows six questions: learning separate action representations, applying controls to the correct agents, generating others' behavior, planning with imagined futures, maintaining shared facts across viewpoints, and handling more agents than seen during training.
The Chinese slides include concrete illustrated examples for all six questions and simplified diagrams for the seven core methods. Teaching schematics are labeled separately from reproduced paper evidence.
The discussion emphasizes the actual inputs, outputs, and information assumptions of each method. Fifteen papers provide seven core readings, five supporting comparisons, two brief latent-action backgrounds, and one distributed-generation perspective.
Reading route
- Action learning: FLAM, with PlaySlot and LPWM; OTF-LAM and GDLAM as background.
- Control binding: ActionParty, with Incantation.
- Other-agent behavior: COMBAT followed by WorldMind.
- Cooperative planning: COMBO.
- Shared worlds and persistence: ME-World, with OverSeer and a brief WorldCast perspective.
- Agent-count generalization: Gamma-World, with Multics.
These are connected research questions, not components of an already integrated system. Objects, particles, active agents, and camera views are distinguished throughout.
Problem map and open questions · Meeting note · Figure sources
Materials cover literature checked through 2026-10-23. The meeting has not yet taken place; no discussion conclusions or follow-up assignments are recorded.