面向公平与低延迟多模态大模型推理的多智能体 AI 框架
Multi-Agentic AI for Fairness-Aware and Accelerated Multi-modal Large Model Inference in Real-world Mobile Edge Networks
AI 导读
研究者提出一个多智能体 AI 框架，用于移动边缘网络中兼顾延迟与公平性的多模态大模型推理，由全局规划 Agent、提示词调度 Agent 和多个节点级部署 Agent 组成，基于基础语言模型协同优化提示词路由与 LM 部署。
正文 · 原文
Abstract: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.
| Subjects: | Systems and Control (eess.SY); Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC) |
| Cite as: | arXiv:2602.07215 [eess.SY] |
| (or arXiv:2602.07215v2 [eess.SY] for this version) | |
| https://doi.org/10.48550/arXiv.2602.07215 arXiv-issued DOI via DataCite |
Submission history
From: Haiyuan Li [view email]
[v1]
Fri, 6 Feb 2026 21:52:49 UTC (5,720 KB)
[v2]
Sun, 25 Oct 2026 21:30:46 UTC (7,686 KB)
来源：arXiv cs.AI · arxiv.org