arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.00906cs.MAcs.AIcs.MM
收藏

基于大语言模型的多智能体系统增强的面向多媒体物联网的复杂事件处理流水线

Large Language Model Based Multi-Agent System Augmented Complex Event Processing Pipeline for Internet of Multimedia Things

University of Oulu(奥卢大学);University of Helsinki(赫尔辛基大学)

Talha Zeeshan, Abhishek Kumar, Susanna Pirttikangas, Sasu Tarkoma

AI总结:

本文提出并评估了一种基于大语言模型的多智能体系统框架,结合Autogen与Kafka实现自主复杂事件处理流水线,用于视频查询处理,并通过实验揭示了智能体数量、视频复杂度与延迟及叙事一致性之间的权衡关系。

摘要:

本文介绍了一种基于大语言模型(LLM,也称为基础模型)的多智能体系统框架的开发和评估,该框架用于复杂事件处理(CEP),重点关注视频查询处理用例。主要目标是创建一个概念验证(POC),将最先进的LLM编排框架与发布/订阅(pub/sub)工具集成,以解决LLM与当前CEP系统的集成问题。该系统利用Autogen框架与Kafka消息代理相结合,展示了一个能够处理复杂工作流的自主CEP流水线。大量实验评估了该系统在不同配置、复杂度和视频分辨率下的性能,揭示了功能性与延迟之间的权衡。结果表明,虽然更高的智能体数量和视频复杂度会增加延迟,但系统在叙事连贯性方面保持了高度一致性。本研究建立在分布式AI系统的现有新颖方法之上并对其做出了贡献,为将此类系统集成到现有基础设施中提供了详细的见解。

英文摘要:

This paper presents the development and evaluation of a Large Language Model (LLM), also known as foundation models, based multi-agent system framework for complex event processing (CEP) with a focus on video query processing use cases. The primary goal is to create a proof-of-concept (POC) that integrates state-of-the-art LLM orchestration frameworks with publish/subscribe (pub/sub) tools to address the integration of LLMs with current CEP systems. Utilizing the Autogen framework in conjunction with Kafka message brokers, the system demonstrates an autonomous CEP pipeline capable of handling complex workflows. Extensive experiments evaluate the system's performance across varying configurations, complexities, and video resolutions, revealing the trade-offs between functionality and latency. The results show that while higher agent count and video complexities increase latency, the system maintains high consistency in narrative coherence. This research builds upon and contributes to, existing novel approaches to distributed AI systems, offering detailed insights into integrating such systems into existing infrastructures.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑