Tool-validated LLM agents author formal event-graph story specifications that a deterministic game engine executes into multi-actor videos with perfect annotations, reaching 80% seeded end-to-end success versus 0% for a staged LLM pipeline.
From vision to language through graph of events in space and time: An explainable self-supervised approach
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Authoring for Living Worlds: Tool-Constrained LLM Agents for Executable Multi-Actor Scenarios
Tool-validated LLM agents author formal event-graph story specifications that a deterministic game engine executes into multi-actor videos with perfect annotations, reaching 80% seeded end-to-end success versus 0% for a staged LLM pipeline.