Agentic AI for Scalable and Robust Optical Systems Control
2026-02-23 • Artificial Intelligence
Artificial IntelligenceNetworking and Internet Architecture
AI summaryⓘ
The authors introduce AgentOptics, an AI system that can understand and carry out complex commands to control different optical devices automatically. It uses a special protocol to communicate with various tools and devices, allowing it to handle many tasks reliably. They tested it on a wide range of optical control tasks and found it much better than other AI approaches that just generate code. They also showed it works well in real-world scenarios like managing communication links and optimizing signals in fiber optics. Overall, their work shows how AI can help manage complicated optical systems efficiently and accurately.
Agentic AIModel Context Protocol (MCP)optical systemsnatural language processingDWDM (Dense Wavelength Division Multiplexing)analog radio-over-fiber (ARoF)fiber polarization stabilizationdistributed acoustic sensing (DAS)LLM (Large Language Models)closed-loop optimization
Authors
Zehao Wang, Mingzhe Han, Wei Cheng, Yue-Kai Huang, Philip Ji, Denton Wu, Mahdi Safari, Flemming Holtorf, Kenaish AlQubaisi, Norbert M. Linke, Danyang Zhuo, Yiran Chen, Ting Wang, Dirk Englund, Tingjun Chen
Abstract
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.