Recent advancements in video diffusion demonstrate remarkable high-fidelity generation, but transforming clips into coherent long storytelling engines remains challenging. Most existing agentic pipelines suffer from semantic drift and cascading failures due to independent, handcrafted prompting, often requiring exhaustive manual intervention. Existing methods also face feature drift and content collapse.

Today, we introduce our research on an AI video co-director, a unified, multi-agent framework that explicitly plans visual continuity in multi-shot narratives. Built as an orchestration layer on top of Gemini and Veo, this framework natively inherits safety mechanisms like Synth ID watermarking. We have developed frameworks — Co-Director (to appear at COLM 2026), CANVAS (to appear at EMNLP 2026), A²RD, and VQQA — that translate high-level human creative specification into execution.

These frameworks act as responsive creative partners that abstract away the burdens of maintaining visual continuity. Across comprehensive evaluations, our framework demonstrates substantial gains in multi-shot narrative consistency and character persistence, successfully generating minutes-long videos while mitigating visual drift and pipeline error propagation.

To ensure semantic coherence, we present AI video co-director, a hierarchical multi-agent framework formalizing video storytelling as a global optimization problem. This top-down steering guarantees the entire pipeline operates under a unified vision, feeding structured prompts into Gemini and Veo models.