Toward Agentic Optical Networks: A Vision of LLM Agent-Driven Autonomous Lifecycle Management

Yao Zhang; Shengnan Li; Yuchen Song; Yidi Wang; Yue Pang; Wenbin Chen; Xiaotian Jiang; Xiao Luo

cs.NISep 26, 2026

Toward Agentic Optical Networks: A Vision of LLM Agent-Driven Autonomous Lifecycle Management

Authors: Yao Zhang, Shengnan Li, Yuchen Song, Yidi Wang, Yue Pang, Wenbin Chen, Xiaotian Jiang, Xiao Luo,

Organizations: State Key Laboratory of Information Photonic and Optical Communication, Beijing University of Posts and Telecommunications, Beijing, 100876, China · China Telecom Cloud Network Operating System R&D Center, Beijing, 102299, China · State Key Laboratory of Optical Fiber and Cable Manufacture Technology, China Telecom Research Institute, Beijing, China · School of Automation and Electrical Engineering, Institute of Industrial Internet, University of Science and Technology Beijing, Beijing, 100083, China ·

Abstract

As optical networks continue to expand in scale, complexity, and service diversity, the implementation of automation has become essential for ensuring agility, efficiency, and reliability in lifecycle management (LCM) of optical networks. Large language model (LLM) Agent, distinguished by its progressively sophisticated capabilities in logical reasoning, adaptive decision-making, complex problem solving, and multi-task orchestration, presents great opportunities to advance network automation beyond traditional AI techniques. Nevertheless, the application of LLM Agent in optical networks remains in its early exploratory stage, challenged by the lack of multi-task coordination, high computational demands, data dependence, and reliability concerns. In this paper, we envision a conceptual roadmap toward Agentic Optical Networks (AONs) by integrating LLM Agents throughout the LCM with high-level autonomy. First, we trace the evolution from manual operations to AI-empowered frameworks and distill key technologies in Agent, providing actionable insights into leveraging its strengths for addressing practical network automation challenges. A core contribution of this paper is the proposal of a hierarchical multi-Agent framework, which is specifically developed to manage every phase in LCM of AONs, including planning, deployment, operation, maintenance, upgrade, and decommission, thereby enabling more cohesive and comprehensive automation throughout the entire lifecycle. In addition, future directions and underlying challenges are also discussed at the intersection of LLM and optical networks. By aligning the LLM Agent with the specialized requirements of AONs, this work aims to explore the potential for the evolution of optical networks moving from task-level semi-automatic execution toward lifecycle-level full autonomy.

Figures & tables

Figure 1: A comprehensive overview of the structure and key topics covered in this work.

Applications	Capabilities and scope	Method Type	Ref
Framework of LLM-driven optical network	LLM applications, challenges, and opportunities for intelligent network operations, prediction, and analysis	GPT-based prompt	[ 55 ]
	Capabilities and limitations of applying LLMs to optical networks	Conceptual	[ 13 , 12 , 57 , 72 ]
Alarm/Log analysis	LLM-enabled professional alarm/log Q&A, analysis, and reasoning	GPT-based prompt	[ 61 ]
		LLaMA fine-tune	[ 37 ]
QoT estimation	LLM-assisted QoT estimation and DT-based multi-task network management	GPT-based prompt	[ 68 ]
Failure management	LLM-based fault analysis and management fused multi-mode data	GPT-based prompt	[ 63 ]

Table 1: Representative works integrating LLMs with optical networks

Figure 2: Key technologies for domain enhancement. (a) Fine-tune (b) Reinforcement learning (c) RAG (d) Prompt engineer (e) AI workflow (f) Harness engineering-enhanced AI Agents.

Figure 3: Diagrammatic representation of the key tasks corresponding to each phase of the optical network lifecycle, covering planning, deployment, operation, maintenance, upgrade, and decommission.

Figure 4: Hierarchical multi-Agent framework for optical network full-lifecycle management. The architecture consists of four layers of intelligent Agents. At the top layer, the Network Director Agent interacts with the user/operator, handling both intent input and feedback aggregation from lower layers. The second layer comprises three administrative Agents, each responsible for a major domain of network lifecycle management. The third layer includes primary Agents that oversee the automation of specific lifecycle phases. At the bottom layer, sub-Agents are assigned to execute concrete tasks.

Lifecycle phase	Representative knowledge and data	Representative tools and interfaces
Planning	Network topology; traffic demands and forecasts; equipment specifications; deployment constraints; equipment databases;	RSA tool; QoT estimation; resource planning; DT platform;
Deployment	Equipment inventory; device capabilities; configuration templates; installation records;	NMS API; device configuration interfaces; commissioning and diagnostic tools;
Operation	service statistics; topology and network state; QoT measurements; alarm information; action logs;	Real-time telemetry APIs; QoT estimation; RSA tool; DT platform; NMS API; performance-analysis scripts;
Maintenance	Alarm rules; historical cases; maintenance records; OTDR traces; equipment state information; troubleshooting procedures;	Alarm analysis tools; fault-diagnosis tools; OTDR APIs; DT platform; NMS API; recovery and reconfiguration tools;
Upgrade	Capacity requirements; traffic growth trends; equipment databases; spectrum utilization; upgrade constraints;	Capacity optimization tool; RSA tool; QoT estimation; DT platform; resource planning; configuration and validation tools;
Decommission	Service inventory; SLA requirements; equipment and asset records; retirement procedures;	QoT and performance verification; service migration tools; NMS API; asset-management systems; configuration tools

Table 2: Representative knowledge, network data, and tools for Agents across different lifecycle phases of AONs.

Figure 5: Schematic of multi-Agent collaboration in the planning phase of the optical network, (a) coordination among Planning Agent, Infrastructure Selector, and Parameter Selector, (b)-(c) functional workflow of the Infrastructure Selector and the Parameter Scheduler: based on the input, the LLM plans the task, retrieves necessary information via RAG from the knowledge base, and invokes tools to carry out a sequence of operations. Once the task is completed and the objective is met, it returns the results to the higher-level Agent.

Figure 6: Schematic of multi-Agent collaboration in the deployment phase of the optical network, (a) coordination among Deployment Agent, Field Engineer, and Performance Tuner, (b) functional workflow of the Field Engineer, (c) functional workflow of the Performance Tuner.

Figure 7: An illustration of multi-Agent collaboration during the operation phase of AONs, along with the functional workflow of the Dynamic Operator and a detailed description of its behavior in a channel adding scenario.

Figure 8: Schematic of functional workflow of the Automated Inspector in operation phase, along with a detailed description of its behavior in a network anomaly inspection scenario.

Figure 9: Schematic of multi-Agent collaboration in the maintenance phase of the AONs. Faults trigger alarms and cause anomalies in performance indicators, which are detected by the Alarm Handler and Abnormal-data Handler. By correlating alarms with performance data, the Maintenance Agent identifies the fault and assists maintenance personnel in resolution. A fault diagnosis report is generated once the fault is resolved and the system returns to normal.

Figure 10: Illustration of Agent collaboration in a specific fault diagnosis and recovery scenario during the maintenance phase. The figure demonstrates the whole process, including fault triggering, alarm and performance anomaly detection, Agent-driven root cause analysis, on-site repair guidance, and final result consolidation.

Figure 11: Schematic of multi-Agent collaboration in the upgrade phase of the AONs. The figure depicts how the Upgrade Agent predicts capacity saturation and coordinates with sub-Agents, including the Upgrade Planner, Validation Specialist, Performance Optimizer, and Business Manager, to carry out a C-to-C+L band upgrade. It visualizes each Agent’s role in planning, device validation, performance optimization, and scheduling, ensuring a seamless and efficient network upgrade process.

Figure 12: Schematic of multi-Agent collaboration in the decommission phase of the AONs. The figure depicts how the Decommission Agent monitors traffic and initiates decommissioning workflows when link utilization drops. It highlights the roles of the Retirement Planner, Service Switcher, and Device Manager in evaluating SLA impact, rerouting services, coordinating switching windows, and physically decommissioning network elements, ensuring minimal disruption and efficient resource reclamation.

LLM Agent Orchestration

Large language model agent orchestration coordinates models, tools, and workflows to complete complex tasks reliably and efficiently.

See all 463 papers

Agentic AI for Scalable and Robust Optical Systems Control
Feb 23, 2026Zehao Wang, Mingzhe Han, Wei Cheng +12LLM Agent Orchestration AI Agent Benchmarks
Department of Electrical and Computer Engineering, Duke University, Durham, NC 27708, USA · NEC Laboratories America, Princeton, NJ 08540, USA · Duke Quantum Center and Department of Physics, Duke University, Durham, NC, USA 27708 +4
First Demonstration of Multi-Agent LLM System for Million-Scale Optical Link Management in Global Production AIDCs
Aug 24, 2026Jingyi Su, Yihao Zhang, Dianxuan Fu +15Fault Diagnosis Multi-Agent LLM Systems
State Key Laboratory of Photonics and Communications,School of Information Science and Electronic Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China · Systems Department, Baidu, Beijing, China · Optical Research Department, Huawei Technologies, Dongguan, China.
Role-Based Agentic AI for Intent-Driven Network and Service Orchestration
May 6, 2026Juan Parra-Ullauri, Talha Ahmed Khan, Daniel McHugh +4Multi-Agent Coordination Multi-Agent Orchestration
Research & Commercialisation, BT Group, UK.

Feb 23, 2026J/K move · Enter open · S save

Agentic AI for Scalable and Robust Optical Systems Control

Zehao Wang, Mingzhe Han, Wei Cheng, Yue-Kai Huang+11

Department of Electrical and Computer Engineering, Duke University, Durham, NC 27708, USA · NEC Laboratories America, Princeton, NJ 08540, USA · Duke Quantum Center and Department of Physics, Duke University, Durham, NC, USA 27708+4

LLM Agent Orchestration AI Agent Benchmarks LLM Agents

Open paper AskPDF arXiv

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.

Abstract

LLM Agent Orchestration

Explore similar work

Agentic AI for Scalable and Robust Optical Systems Control

First Demonstration of Multi-Agent LLM System for Million-Scale Optical Link Management in Global Production AIDCs

Role-Based Agentic AI for Intent-Driven Network and Service Orchestration