ComAgent: Multi-LLM based Agentic AI Empowered Intelligent Wireless Networks
This addresses the bottleneck of automating complex cross-layer optimization in emerging 6G wireless networks, though it appears incremental as an enhancement over existing LLM-based approaches.
The paper tackles the problem of manually translating high-level intents into mathematical formulations for 6G network optimization by introducing ComAgent, a multi-LLM agentic AI framework that achieves expert-comparable performance in beamforming optimization and outperforms monolithic LLMs across wireless tasks.
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.