Co-Director introduces a hierarchical multi-agent framework that treats video storytelling as global optimization, using multi-armed bandits for creative exploration and multimodal self-refinement to reduce semantic drift, outperforming baselines on a new 400-scenario advertising benchmark.
The system is not searching 36 distinct paths, but rather evaluating 10 independent parameters
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Co-Director: Agentic Generative Video Storytelling
Co-Director introduces a hierarchical multi-agent framework that treats video storytelling as global optimization, using multi-armed bandits for creative exploration and multimodal self-refinement to reduce semantic drift, outperforming baselines on a new 400-scenario advertising benchmark.