Automated Movie Generation via Multi-Agent CoT Planning

Weijia Wu, Zeyu Zhu, Mike Zheng Shou

Keywords: Multi-Agent; Video Generation;

Abstract: Existing long-form video generation frameworks lack automated planning and often rely on manual intervention for storyline development, scene composition, cinematography design, and character interaction coordination, leading to high production costs and inefficiencies. To address these challenges, we present MovieAgent, an automated movie generation via multi-agent Chain of Thought (CoT) planning. MovieAgent offers two key advantages: 1) We firstly explore and define the paradigm of automated movie/long-video generation. Given a script and character bank, our MovieAgent can generates multi-scene, multi-shot long-form videos with a coherent narrative, while ensuring character consistency, synchronized subtitles, and stable audio throughout the film. 2) MovieAgent introduces a hierarchical CoT-based reasoning process to automatically structure scenes, camera settings, and cinematography, significantly reducing human effort. By employing multiple LLM agents to simulate the roles of a director, screenwriter, storyboard artist, and location manager, MovieAgent streamlines the production pipeline. Our framework represents a significant step toward fully automated movie production, bridging the gap between AI-driven video generation and high-quality, narrative-consistent filmmaking.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 7572