Agentic AI for Scalable and Robust Optical Systems Control

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Zehao, Han, Mingzhe, Cheng, Wei, Huang, Yue-Kai, Ji, Philip, Wu, Denton, Safari, Mahdi, Holtorf, Flemming, AlQubaisi, Kenaish, Linke, Norbert M., Zhuo, Danyang, Chen, Yiran, Wang, Ting, Englund, Dirk, Chen, Tingjun
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912921172312064
author Wang, Zehao
Han, Mingzhe
Cheng, Wei
Huang, Yue-Kai
Ji, Philip
Wu, Denton
Safari, Mahdi
Holtorf, Flemming
AlQubaisi, Kenaish
Linke, Norbert M.
Zhuo, Danyang
Chen, Yiran
Wang, Ting
Englund, Dirk
Chen, Tingjun
author_facet Wang, Zehao
Han, Mingzhe
Cheng, Wei
Huang, Yue-Kai
Ji, Philip
Wu, Denton
Safari, Mahdi
Holtorf, Flemming
AlQubaisi, Kenaish
Linke, Norbert M.
Zhuo, Danyang
Chen, Yiran
Wang, Ting
Englund, Dirk
Chen, Tingjun
contents We present AgentOptics, an agentic AI framework for high-fidelity, autonomous optical system control built on the Model Context Protocol (MCP). AgentOptics interprets natural language tasks and executes protocol-compliant actions on heterogeneous optical devices through a structured tool abstraction layer. We implement 64 standardized MCP tools across 8 representative optical devices and construct a 410-task benchmark to evaluate request understanding, role-aware responses, multi-step coordination, robustness to linguistic variation, and error handling. We assess two deployment configurations--commercial online LLMs and locally hosted open-source LLMs--and compare them with LLM-based code generation baselines. AgentOptics achieves 87.7%--99.0% average task success rates, significantly outperforming code-generation approaches, which reach up to 50% success. We further demonstrate broader applicability through five case studies extending beyond device-level control to system orchestration, monitoring, and closed-loop optimization. These include DWDM link provisioning and coordinated monitoring of coherent 400 GbE and analog radio-over-fiber (ARoF) channels; autonomous characterization and bias optimization of a wideband ARoF link carrying 5G fronthaul traffic; multi-span channel provisioning with launch power optimization; closed-loop fiber polarization stabilization; and distributed acoustic sensing (DAS)-based fiber monitoring with LLM-assisted event detection. These results establish AgentOptics as a scalable, robust paradigm for autonomous control and orchestration of heterogeneous optical systems.
format Preprint
id arxiv_https___arxiv_org_abs_2602_20144
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Agentic AI for Scalable and Robust Optical Systems Control
Wang, Zehao
Han, Mingzhe
Cheng, Wei
Huang, Yue-Kai
Ji, Philip
Wu, Denton
Safari, Mahdi
Holtorf, Flemming
AlQubaisi, Kenaish
Linke, Norbert M.
Zhuo, Danyang
Chen, Yiran
Wang, Ting
Englund, Dirk
Chen, Tingjun
Systems and Control
Artificial Intelligence
Networking and Internet Architecture
We present AgentOptics, an agentic AI framework for high-fidelity, autonomous optical system control built on the Model Context Protocol (MCP). AgentOptics interprets natural language tasks and executes protocol-compliant actions on heterogeneous optical devices through a structured tool abstraction layer. We implement 64 standardized MCP tools across 8 representative optical devices and construct a 410-task benchmark to evaluate request understanding, role-aware responses, multi-step coordination, robustness to linguistic variation, and error handling. We assess two deployment configurations--commercial online LLMs and locally hosted open-source LLMs--and compare them with LLM-based code generation baselines. AgentOptics achieves 87.7%--99.0% average task success rates, significantly outperforming code-generation approaches, which reach up to 50% success. We further demonstrate broader applicability through five case studies extending beyond device-level control to system orchestration, monitoring, and closed-loop optimization. These include DWDM link provisioning and coordinated monitoring of coherent 400 GbE and analog radio-over-fiber (ARoF) channels; autonomous characterization and bias optimization of a wideband ARoF link carrying 5G fronthaul traffic; multi-span channel provisioning with launch power optimization; closed-loop fiber polarization stabilization; and distributed acoustic sensing (DAS)-based fiber monitoring with LLM-assisted event detection. These results establish AgentOptics as a scalable, robust paradigm for autonomous control and orchestration of heterogeneous optical systems.
title Agentic AI for Scalable and Robust Optical Systems Control
topic Systems and Control
Artificial Intelligence
Networking and Internet Architecture
url https://arxiv.org/abs/2602.20144