ComAgent: Multi-LLM based Agentic AI Empowered Intelligent Wireless Networks

2026-01-27

AI Summary

This work addresses the challenge of automatically translating high-level design intents into executable optimization models in 6G networks by proposing the first multi-agent large language model (LLM) framework tailored for wireless network design. The architecture employs a closed-loop mechanism—comprising perception, planning, action, and reflection—to coordinate specialized agents responsible for literature retrieval, code generation, and validation. This enables automatic problem decomposition, self-correction of errors, and end-to-end transformation of abstract intents into solvable optimization models. Evaluated on complex tasks such as beamforming, the system achieves expert-level performance, significantly outperforming monolithic LLM approaches and demonstrating a highly efficient, reproducible capability for automated network design.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Emerging 6G networks rely on complex cross-layer optimization, yet manually translating high-level intents into mathematical formulations remains a bottleneck. While Large Language Models (LLMs) offer promise, monolithic approaches often lack sufficient domain grounding, constraint awareness, and verification capabilities. To address this, we present ComAgent, a multi-LLM agentic AI framework. ComAgent employs a closed-loop Perception-Planning-Action-Reflection cycle, coordinating specialized agents for literature search, coding, and scoring to autonomously generate solver-ready formulations and reproducible simulations. By iteratively decomposing problems and self-correcting errors, the framework effectively bridges the gap between user intent and execution. Evaluations demonstrate that ComAgent achieves expert-comparable performance in complex beamforming optimization and outperforms monolithic LLMs across diverse wireless tasks, highlighting its potential for automating design in emerging wireless networks.

Problem

• 6G networks
• cross-layer optimization
• intent translation
• mathematical formulation
• wireless network automation

Innovation

• Multi-LLM
• Agentic AI
• Closed-loop reasoning
• Wireless network optimization
• Autonomous formulation generation