Saved in:
Bibliographic Details
Main Authors: Li, Haoyun, Xiao, Ming, Wang, Kezhi, Schober, Robert, Kim, Dong In, Guan, Yong Liang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.19607
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914283697209344
author Li, Haoyun
Xiao, Ming
Wang, Kezhi
Schober, Robert
Kim, Dong In
Guan, Yong Liang
author_facet Li, Haoyun
Xiao, Ming
Wang, Kezhi
Schober, Robert
Kim, Dong In
Guan, Yong Liang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_19607
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ComAgent: Multi-LLM based Agentic AI Empowered Intelligent Wireless Networks
Li, Haoyun
Xiao, Ming
Wang, Kezhi
Schober, Robert
Kim, Dong In
Guan, Yong Liang
Artificial Intelligence
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.
title ComAgent: Multi-LLM based Agentic AI Empowered Intelligent Wireless Networks
topic Artificial Intelligence
url https://arxiv.org/abs/2601.19607