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; Meixia Fu; Min Zhang; Yongli Zhao; Shanguo Huang; Alan Pak Tao Lau; Danshi Wang

arXiv · 2609.32226

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·Meixia Fu·Min Zhang·Yongli Zhao·Shanguo Huang·Alan Pak Tao Lau·Danshi Wang

View original source ↗Read source document ↗Export metadata ↓

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.

Explore related subjects

cs.NI cs.AI

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Yao Zhang, Shengnan Li, Yuchen Song, Yidi Wang, Yue Pang, Wenbin Chen, Xiaotian Jiang, Xiao Luo, Meixia Fu, Min Zhang, Yongli Zhao, Shanguo Huang, Alan Pak Tao Lau, Danshi Wang. 2026-09-26. Toward Agentic Optical Networks: A Vision of LLM Agent-Driven Autonomous Lifecycle Management. https://arxiv.org/abs/2609.32226

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Cell-Free Massive MIMO Under Mobility: A Fairness-Differentiated Handover Scheme

While cell-free massive MIMO (CF-mMIMO) offers high and uniform network-wide throughput in static networks, its performance in mobile networks is not yet fully addressed. In this paper, we evaluate the throughput performance of urban mobile CF-mMIMO networks under a comprehensive throughput model and show that it suffers from large performance degradation due to the combined effect of channel aging and handover overheads. To restore the uniformly good performance of CF-mMIMO under mobility, we formulate a novel optimization problem to maximize the nett throughput that considers both channel aging and handover cost. We derive a near-optimal solution nearOpt for our transformed and relaxed optimization problem with Newton's method. We then design a heuristic handover algorithm, FairDiff, to differentiate prioritized and optional handovers using a policy threshold based on Jain's fairness index, in order to achieve uniform throughput over the network. Our extensive evaluation of the mobile throughput performance of our handover schemes in realistic urban mobile networks shows that, unlike the existing literature benchmarks that obtain very low throughput under mobility, our FairDiff scheme consistently achieves the near-optimal throughput comparable to nearOpt and highest network-wide throughput with the lowest computational complexity among all considered schemes. We thus for the first time propose a handover scheme that delivers the promise of uniformly good throughput for mobile CF-mMIMO, making it a feasible architecture for practical mobile networks.

cs.NI↗

arXiv2026

Embodied AI in 6G Networks: From Intelligent Connectivity to Physical Intelligence

Embodied artificial intelligence (AI) couples perception and learned decision making to actions that change the physical world. This coupling distinguishes an embodied agent from a conventional connected controller: the agent maintains task state and uncertainty, reasons about the consequences of actions, and adapts from subsequent observations. Wireless networking becomes relevant when perception, inference, or coordination is distributed, but it should not replace local safety control. This article develops a tutorial perception--communication--action (PCA) architecture that exposes task state, action deadlines, uncertainty, agent intent, and safety envelopes to a 6G orchestration plane. It separates capabilities already addressed by 5G and 5G-Advanced from functions that motivate 6G, including task-state interfaces, semantic freshness, predictive digital twins, and safety-aware coordination across agents. A multi-robot simulation study is retained to illustrate joint sensing, communication, and computation control. The results show where network orchestration improves task utility and where local autonomy remains essential.

cs.NI↗

arXiv2026

HOCCL: Offloading Collective Communication from GPU Cores to Accelerate Distributed Training

Large language model training involves massive computation on GPU streaming multiprocessors (SMs), the primary compute units of GPUs. Since SMs host specialized accelerators such as Tensor Cores, their efficient utilization is critical to training efficiency. Unfortunately, existing collective communication systems compete with computation for SMs, as they consume SMs for communication-related data movement and synchronization operations. We observe that communication can, in principle, be driven by DMA engines, thereby eliminating SM involvement in communication. Based on this insight, we propose HOCCL, a zero-SM collective communication framework consisting of three components: a stream manager, a point-to-point (P2P) executor, and a collective scheduler. The stream manager preserves operator-level temporal ordering with other GPU kernels. The P2P executor enables zero-SM point-to-point communication, while the collective scheduler orchestrates P2P transfers to maximize bandwidth. Experiments show that HOCCL preserves near-peak communication performance, achieving within 3% of the state of the art on average, while eliminating communication occupancy on nearly 10% of total GPU SMs. By freeing SM resources for computation, HOCCL improves end-to-end training throughput by up to 5%.

cs.NI↗