CORE:Toward Ubiquitous 6G Intelligence Through Collaborative Orchestration of Large Language Model Agents Over Hierarchical Edge

2026-01-29

AI Summary

This work addresses the challenge of fragmented heterogeneous edge resources in 6G networks, which hinder the execution of complex reasoning tasks by large language models (LLMs). To overcome this limitation, the paper proposes a hierarchical edge-based LLM agent collaborative inference framework that deploys multi-role LLM agents and integrates real-time environmental awareness, dynamic role orchestration, and pipeline parallelism to enable efficient cooperative reasoning. The key innovation lies in a role-affinity-aware scheduling algorithm that dynamically aligns computational demands with distributed edge resources, achieving the first hierarchical, 6G-oriented orchestration of edge LLM agents. Experimental results demonstrate significant improvements in system efficiency and task completion rates across diverse 6G scenarios, with deployment feasibility validated on a real-world edge computing platform.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Planning with Language Models
• Multiagent Systems: Coordination and Collaboration

Application Category

• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Rapid advancements in sixth-generation (6G) networks and large language models (LLMs) have paved the way for ubiquitous intelligence, wherein seamless connectivity and distributed artificial intelligence (AI) have revolutionized various aspects of our lives.However, realizing this vision faces significant challenges owing to the fragmented and heterogeneous computing resources across hierarchical networks, which are insufficient for individual LLM agents to perform complex reasoning tasks.To address this issue, we propose Collaborative Orchestration Role at Edge (CORE), an innovative framework that employs a collaborative learning system in which multiple LLMs, each assigned a distinct functional role, are distributed across mobile devices and tiered edge servers. The system integrates three optimization modules, encompassing real-time perception,dynamic role orchestration, and pipeline-parallel execution, to facilitate efficient and rapid collaboration among distributed agents. Furthermore, we introduce a novel role affinity scheduling algorithm for dynamically orchestrating LLM role assignments across the hierarchical edge infrastructure, intelligently matching computational demands with available dispersed resources.Finally, comprehensive case studies and performance evaluations across various 6G application scenarios demonstrated the efficacy of CORE, revealing significant enhancements in the system efficiency and task completion rates. Building on these promising outcomes, we further validated the practical applicability of CORE by deploying it on a real-world edge-computing platform,that exhibits robust performance in operational environments.

Problem

• 6G networks
• large language models
• edge computing
• heterogeneous resources
• ubiquitous intelligence

Innovation

• Collaborative Orchestration
• Large Language Model Agents
• Hierarchical Edge Computing
• Role Affinity Scheduling
• 6G Intelligence