Agentic AI for Scalable and Robust Optical Systems Control

TL;DR

AgentOptics introduces an AI framework that autonomously controls complex optical systems using natural language, achieving high success rates and demonstrating versatility across multiple optical tasks and system types.

Contribution

The paper presents AgentOptics, a novel AI system that interprets natural language commands to autonomously manage diverse optical devices with high accuracy and robustness.

Findings

Achieves 87.7%-99.0% task success rate, outperforming code-generation baselines.

Demonstrates applicability in system orchestration, monitoring, and optimization tasks.

Validates effectiveness across 8 optical devices and 410 benchmark tasks.

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.