AI RESEARCH
Agentic Video Generation: From Text to Executable Event Graphs via Tool-Constrained LLM Planning
arXiv CS.CV
•
ArXi:2604.10383v1 Announce Type: new Existing multi-agent video generation systems use LLM agents to orchestrate neural video generators, producing visually impressive but semantically unreliable outputs with no ground truth annotations. We present an agentic system that inverts this paradigm: instead of generating pixels, the LLM constructs a formal Graph of Events in Space and Time (GEST) -- a structured specification of actors, actions, objects, and temporal constraints -- which is then executed deterministically in a 3D game engine.