# First Field Trial of LLM-Powered AI Agent for Lifecycle Management of Autonomous Driving Optical Networks

arXiv: https://arxiv.org/abs/2409.14605 · HTML: https://mlsanity.com/paper/2409.14605/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Sep 2024.

## Built on by (most cited first, 8 of 8)

- [Generative AI-Driven Hierarchical Multi-Agent Framework for Zero-Touch Optical Networks](https://mlsanity.com/paper/2510.05625/) (2025)
- [First Field-Trial Demonstration of L4 Autonomous Optical Network for Distributed AI Training Communication: An LLM-Powered Multi-AI-Agent Solution](https://mlsanity.com/paper/2504.01234/) (2025)
- [Agentic AI for Scalable and Robust Optical Systems Control](https://mlsanity.com/paper/2602.20144/) (2026)
- [A T-API-Compliant ReAct Agentic Loop for Optical Networks: Generic vs. Domain-Specific Tool Abstractions](https://mlsanity.com/paper/2606.18000/) (2026)
- [Agentic AI for IPoDWDM Network Lifecycle Automation: An MCP-Enabled Architecture](https://mlsanity.com/paper/2607.05958/) (2026)
- [MCP-Enabled Agentic AI for Autonomous IPoDWDM Network Lifecycle Automation](https://mlsanity.com/paper/2607.05975/) (2026)
- [Human Grounded Evaluation of Large Language Models for Optical Network Automation](https://mlsanity.com/paper/2607.18068/) (2026)
- [Toward Agentic Optical Networks: A Vision of LLM Agent-Driven Autonomous Lifecycle Management](https://mlsanity.com/paper/2609.32226/) (2026)

## Abstract (arXiv)

We design and demonstrate the first field trial of LLM-powered AI Agent for ADON. Three operation modes of the Agent are proposed for network lifecycle management. The Agent efficiently processes wavelength add/drop and soft/hard failures, and achieves comparable performance to human-designed algorithms for power optimization.