CoAgent: Collaborative Planning and Consistency Agent for Coherent Video Generation
Qinglin Zeng, Kaitong Cai, Ruiqi Chen, Qinhan Lv, Keze Wang

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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsArtificial Intelligence in Games · Generative Adversarial Networks and Image Synthesis · Multimodal Machine Learning Applications
