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

TL;DR

ComAgent is a multi-LLM framework that autonomously translates high-level wireless network design intents into executable solutions, effectively bridging the gap between user goals and implementation through iterative problem decomposition and self-correction.

Contribution

It introduces a novel multi-agent LLM system with a closed-loop cycle for automating complex wireless network optimization tasks, surpassing monolithic LLMs in performance.

Findings

Achieves expert-level performance in beamforming optimization.

Outperforms monolithic LLMs across various wireless tasks.

Demonstrates effective problem decomposition and self-correction.

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.