CoAgent: Collaborative Planning and Consistency Agent for Coherent Video Generation

TL;DR

CoAgent introduces a collaborative, plan-based framework for open-domain video generation that enhances narrative coherence, visual consistency, and temporal flow through a structured, feedback-driven process.

Contribution

It presents a novel plan-synthesize-verify pipeline with entity memory and a pacing editor, advancing coherence and consistency in long-form video synthesis.

Findings

Significantly improves video coherence and visual consistency.

Enhances narrative quality in long-form video generation.

Demonstrates effectiveness through extensive experiments.

Abstract

Maintaining narrative coherence and visual consistency remains a central challenge in open-domain video generation. Existing text-to-video models often treat each shot independently, resulting in identity drift, scene inconsistency, and unstable temporal structure. We propose CoAgent, a collaborative and closed-loop framework for coherent video generation that formulates the process as a plan-synthesize-verify pipeline. Given a user prompt, style reference, and pacing constraints, a Storyboard Planner decomposes the input into structured shot-level plans with explicit entities, spatial relations, and temporal cues. A Global Context Manager maintains entity-level memory to preserve appearance and identity consistency across shots. Each shot is then generated by a Synthesis Module under the guidance of a Visual Consistency Controller, while a Verifier Agent evaluates intermediate results using vision-language reasoning and triggers selective regeneration when inconsistencies are detected. Finally, a pacing-aware editor refines temporal rhythm and transitions to match the desired narrative flow. Extensive experiments demonstrate that CoAgent significantly improves coherence, visual consistency, and narrative quality in long-form video generation.