arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.07215eess.SYcs.AIcs.DCcs.SY
收藏

多智能体AI用于现实世界移动边缘网络中公平性感知和加速的多模态大模型推理

Multi-Agentic AI for Fairness-Aware and Accelerated Multi-modal Large Model Inference in Real-world Mobile Edge Networks

Smart Internet Lab, Department of Electrical and Electronic Engineering, University of Bristol(布里斯托大学电子与电气工程系智能互联网实验室)

Haiyuan Li, Hari Madhukumar, Shuangyi Yan, Yulei Wu, Dimitra Simeonidou

AI总结:

本文提出多智能体AI框架,通过优化提示路由和模型部署,实现移动边缘网络中多模态大模型推理的低延迟与高公平性。

摘要:

生成式人工智能(GenAI)已改变了自然语言处理和内容创作的应用,但集中式推理仍受到高延迟、定制性有限和隐私问题的阻碍。在移动边缘网络中部署大模型(LMs)成为一种有前途的解决方案。然而,这也带来了新的挑战,包括异构的多模态LMs具有不同的资源需求和推理速度,以及各种提示/输出模态使协调复杂化,以及资源有限的基础设施不适合同时执行LM。为此,我们提出了一种多智能体AI框架,用于移动边缘网络中公平性和延迟感知的多模态LM推理。我们的解决方案包括一个长期规划代理、一个短期提示调度代理以及多个节点上的LM部署代理,均由基础语言模型驱动。这些代理通过运行时遥测和历史经验上的自然语言推理,协同优化提示路由和LM部署。为了评估其性能,我们进一步开发了一个全市范围的测试床,支持网络监控、容器化LM部署、服务器内资源管理和服务器间通信。实验表明,我们的解决方案将平均延迟降低了超过80%,并且公平性(归一化Jain指数)提高到0.90,优于其他基线。此外,我们的解决方案能够快速适应,无需微调,为优化边缘环境中的GenAI服务提供了一种可推广的解决方案。

英文摘要:

Generative AI (GenAI) has transformed applications in natural language processing and content creation, yet centralized inference remains hindered by high latency, limited customizability, and privacy concerns. Deploying large models (LMs) in mobile edge networks emerges as a promising solution. However, it also poses new challenges, including heterogeneous multi-modal LMs with diverse resource demands and inference speeds, varied prompt/output modalities that complicate orchestration, and resource-limited infrastructure ill-suited for concurrent LM execution. In response, we propose a Multi-Agentic AI framework for latency- and fairness-aware multi-modal LM inference in mobile edge networks. Our solution includes a long-term Global Planning Agent, a short-term Prompt Scheduling Agent, and multiple on-node LM Deployment Agents, all powered by foundation language models. These agents cooperatively optimize prompt routing and LM deployment through natural language reasoning over runtime telemetry and historical experience. To evaluate its performance, we further develop a city-wide testbed that supports network monitoring, containerized LM deployment, intra-server resource management, and inter-server communications. Experiments demonstrate that our solution reduces average end-to-end latency by 42.9% compared with a state-of-the-art online-learning baseline and by 80.6% compared with the full-activation baseline, while maintaining a mean service-type Jain's index of 0.925. Moreover, our solution adapts quickly without fine-tuning, offering a generalizable solution for optimizing GenAI services in edge environments.

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。

↑