cs.AINov 16, 2026

Multi-LLM Agentic AI at the Edge: Joint Agent Scheduling and Resource Allocation

Authors: Yuanyan Song, Kezhi Wang, Xinmian Xu, Yongmin Li

Organizations: Department of Computer Science, Brunel University of London, UB8 3PH, UK. · Key Laboratory of Broadband Wireless Communication and Sensor Network Technology, Nanjing University of Posts and Telecommunications, Nanjing 210003, China.

Abstract

In this paper, an edge-enabled multi-large language model (LLM) agentic AI architecture is proposed, where one supervisor AI agent and multiple worker AI agents cooperatively execute users' requests at the edge. The supervisor AI agent decouples the user request into a series of sub-tasks and dynamically dispatches them to LLM-equipped worker AI agents via two agentic workflows, i.e., parallel and serial workflows, with a two-level retry mechanism to enhance execution reliability. To prolong the service duration of worker AI agents, the energy minimization problems are formulated by jointly considering AI agent selection and resource allocation, subject to task execution latency and quality of service (QoS) constraints. A resource allocation scheme based on alternating optimization (AO) is proposed. Specifically, for the parallel workflow, the scheme decouples the original problem into bandwidth allocation, retrieval selection and AI agent selection sub-problems, which are iteratively solved by the proposed successive convex approximation (SCA), Lagrangian relaxation (LR), and Gale-Shapley (GS) or LLM-based algorithms, respectively. For the serial workflow, the problem is similarly decoupled into service time allocation, retrieval selection and AI agent selection sub-problems; the optimal service time allocation is obtained via Karush-Kuhn-Tucker (KKT) conditions, while the latter two sub-problems are addressed by extending the proposed algorithms to the serial scenario. Simulation results show that the proposed resource allocation scheme can reduce system energy consumption compared with other benchmarks, while experiments on a multi-LLM agentic AI system based on Qwen and Llama demonstrate improved task execution success rates.

Figures & tables

Explore similar work

CardsList
  1. End-to-End Latency-Minimizing and Load-Balanced Request Scheduling for Edge LLM Inference in Agentic AI Services

    Sep 15, 2026Zhen Li, Jun Cai, Haoran Gao +2LLM Inference SchedulingLLM Request Scheduling

  2. RAGAM-AI: A Hybrid Reinforcement Learning based Agentic approach powered by Generative AI for Edge Resource Management

    Nov 4, 2026Shreya K. Chari, John S. Vardakas, Kostas Ramantas +1Edge ComputingMulti-Agent Resource Allocation

  3. Conflict-Aware Autonomous Resource Orchestration for 5G Edge Slicing Using Multi-Agent Systems and LLMs

    Oct 10, 2026Nathan R. Prediger, Rodrigo Moreira, Juliano Araujo Wickboldt +4Network SlicingEdge Computing