Reimagining RAN Automation in 6G: An Agentic AI Framework with Hierarchical Online Decision Transformer
Md Arafat Habib, Medhat Elsayed, Majid Bavand, Pedro Enrique Iturria Rivera, Yigit Ozcan, Melike Erol-Kantarci

TL;DR
This paper introduces an agentic AI framework for 6G wireless networks, utilizing a Hierarchical Online Decision Transformer to coordinate diverse AI agents guided by natural language inputs, improving network performance and self-healing capabilities.
Contribution
It presents a novel hierarchical AI framework with a decision transformer and retrieval-augmented generation for dynamic network management and operator intent validation.
Findings
Improved throughput, reduced delay, and higher energy efficiency compared to baselines.
Achieved 88.5% accuracy in operator intent validation.
Recovered 90% of performance during interruptions through self-healing.
Abstract
In this paper, we propose an Agentic Artificial Intelligence (AI) framework for wireless networks. The framework coordinates a pool of AI agents guided by Natural Language (NL) inputs from a human operator. At its core, the super agent is powered by a Hierarchical Online Decision Transformer (H-ODT). It orchestrates three categories of agents: (i) inter-slice, intra-slice resource allocation agents, (ii) network application orchestration agents, and (iii) self-healing agents. The orchestration takes place with the help of an Agentic Retrieval-Augmented Generation (RAG) module that integrates knowledge from heterogeneous sources. In this proposed methodology, the super agent directly interfaces with operators and generates sequential policies to activate relevant agents. The proposed framework is evaluated against three state-of-the-art baselines, showing improved throughput, reduced…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
