Hollywood Town: Long-Video Generation via Cross-Modal Multi-Agent Orchestration

TL;DR

This paper presents OmniAgent, a hierarchical multi-agent framework with hypergraph nodes and cyclic graphs for improved long video generation, enabling scalable, collaborative, and iterative creative content creation.

Contribution

Introduces OmniAgent, a novel hierarchical, graph-based multi-agent system with hypergraph nodes and cyclic graphs for enhanced collaboration in long video generation.

Findings

Enhanced collaboration through hypergraph nodes

Iterative refinement via cyclic graphs

Scalable multi-agent architecture for long videos

Abstract

Recent advancements in multi-agent systems have demonstrated significant potential for enhancing creative task performance, such as long video generation. This study introduces three innovations to improve multi-agent collaboration. First, we propose OmniAgent, a hierarchical, graph-based multi-agent framework for long video generation that leverages a film-production-inspired architecture to enable modular specialization and scalable inter-agent collaboration. Second, inspired by context engineering, we propose hypergraph nodes that enable temporary group discussions among agents lacking sufficient context, reducing individual memory requirements while ensuring adequate contextual information. Third, we transition from directed acyclic graphs (DAGs) to directed cyclic graphs with limited retries, allowing agents to reflect and refine outputs iteratively, thereby improving earlier stages through feedback from subsequent nodes. These contributions lay the groundwork for developing more robust multi-agent systems in creative tasks.