KAOS: Large Model Multi-Agent Operating System

TL;DR

KAOS introduces a multi-agent operating system leveraging large models to improve cross-platform user experience, resource sharing, and collaboration, validated through real application scenarios showing significant advantages.

Contribution

The paper presents KAOS, a novel multi-agent OS based on large models, with new management roles, collaboration strategies, and resource scheduling for improved multi-agent system performance.

Findings

Enhanced multi-agent collaboration efficiency

Improved resource utilization and scheduling

Validated system performance through real applications

Abstract

The intelligent interaction model based on large models reduces the differences in user experience across various system platforms but faces challenges in multi-agent collaboration and resource sharing. To demonstrate a uniform user experience across different foundational software platforms and address resource coordination management challenges, this paper proposes KAOS, a multi-agent operating system based on the open-source Kylin. The research method involves empowering agents with large models to serve applications. First, by introducing management role agents and vertical multi-agent collaboration to construct or replace typical application software. Second, by studying system-level shared resource scheduling strategies to enhance user experience and optimize resource utilization. And finally, by validating the efficiency and superiority of the large model multi-agent operating system through real applications and scoring intelligence. The feasibility of this system is demonstrated, providing a new perspective for the development of multi-agent operating systems. Experimental results show significant advantages of multi-agent collaboration in various application scenarios.