![[2602.22539] Agentic AI for Intent-driven Optimization in Cell-free O-RAN](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.22539] Agentic AI for Intent-driven Optimization in Cell-free O-RAN
Summary
This paper presents an agentic AI framework for optimizing intent-driven operations in cell-free O-RAN, enhancing collaboration among agents to meet complex operator-defined intents.
Why It Matters
As the telecommunications industry increasingly adopts open RAN architectures, understanding how to utilize agentic AI for optimizing network operations becomes crucial. This research addresses the gap in managing complex intents, which can lead to improved efficiency and energy savings in network management.
Key Takeaways
- Introduces a framework for agentic AI to optimize operations in cell-free O-RAN.
- Demonstrates significant energy savings by reducing active O-RUs by 41.93%.
- Utilizes a parameter-efficient fine-tuning method to enhance scalability and reduce memory usage by 92%.
Computer Science > Artificial Intelligence arXiv:2602.22539 (cs) [Submitted on 26 Feb 2026] Title:Agentic AI for Intent-driven Optimization in Cell-free O-RAN Authors:Mohammad Hossein Shokouhi, Vincent W.S. Wong View a PDF of the paper titled Agentic AI for Intent-driven Optimization in Cell-free O-RAN, by Mohammad Hossein Shokouhi and Vincent W.S. Wong View PDF HTML (experimental) Abstract:Agentic artificial intelligence (AI) is emerging as a key enabler for autonomous radio access networks (RANs), where multiple large language model (LLM)-based agents reason and collaborate to achieve operator-defined intents. The open RAN (O-RAN) architecture enables the deployment and coordination of such agents. However, most existing works consider simple intents handled by independent agents, while complex intents that require coordination among agents remain unexplored. In this paper, we propose an agentic AI framework for intent translation and optimization in cell-free O-RAN. A supervisor agent translates the operator intents into an optimization objective and minimum rate requirements. Based on this information, a user weighting agent retrieves relevant prior experience from a memory module to determine the user priority weights for precoding. If the intent includes an energy-saving objective, then an open radio unit (O-RU) management agent will also be activated to determine the set of active O-RUs by using a deep reinforcement learning (DRL) algorithm. A monitoring agent measu...
