The AI Telco Engineer: Toward Autonomous Discovery of Wireless Communications Algorithms

TL;DR

This paper demonstrates how agentic AI, using large language models, can autonomously design wireless communication algorithms that are competitive with traditional methods, with advantages in explainability and extensibility.

Contribution

It introduces a framework leveraging LLMs for autonomous design and evaluation of wireless algorithms across PHY and MAC layers, showing promising results.

Findings

Framework produces algorithms competitive with traditional baselines.

Generated algorithms are fully explainable and extensible.

Algorithms outperform some conventional methods in hours.

Abstract

Agentic AI is rapidly transforming the way research is conducted, from prototyping ideas to reproducing results found in the literature. In this paper, we explore the ability of agentic AI to autonomously design wireless communication algorithms. To that end, we implement a dedicated framework that leverages large language models (LLMs) to iteratively generate, evaluate, and refine candidate algorithms. We evaluate the framework on three tasks spanning the physical (PHY) and medium access control (MAC) layers: statistics-agnostic channel estimation, channel estimation with known covariance, and link adaptation. Our results show that, in a matter of hours, the framework produces algorithms that are competitive with and, in some cases, outperforming conventional baselines. Moreover, unlike neural network-based approaches, the generated algorithms are fully explainable and extensible. This work represents a first step toward the autonomous discovery of novel wireless communication algorithms, and we look forward to the progress our community makes in this direction.