Redirecting to original paper in 30 seconds...
Click below to go immediately or wait for automatic redirect
📄 Abstract
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.
Authors (9)
Zheng Wei
Mingchen Li
Zeqian Zhang
Ruibin Yuan
Pan Hui
Huamin Qu
+3 more
Submitted
October 25, 2025
Key Contributions
Introduces OmniAgent, a hierarchical multi-agent framework for long video generation inspired by film production. It uses hypergraph nodes for agent discussions and directed cyclic graphs for iterative refinement, improving collaboration and output quality.
Business Value
Enables the automated generation of high-quality, long-form video content, potentially revolutionizing media production, advertising, and entertainment industries.