Large language models (LLMs) are increasingly adopted for network automation, yet their output quality and inference cost can vary substantially across LLM families. We present HuGLEN, a stepwise evaluation pipeline that uses an LLM-as-a-judge together with a small set of expert ratings to enable scalable and reproducible comparison of candidate LLMs, and to rank them using a quality efficiency score (QES).
arXiv:2606. 10942v1 Announce Type: cross Abstract: As artificial intelligence and machine learning (AI/ML) models become integral to network operations, their lack of transparency poses a significant barrier to operator trust.
By Kiarash Rezaei, Omran Ayoub, Sebastian Troia, Francesco Lelli, Paolo Monti, Carlos Natalino
arXiv:2607. 20675v1 Announce Type: new Abstract: Machine learning (ML) models are increasingly integrated into optical network automation frameworks to support tasks such as failure management, performance monitoring and resource allocation.
By Omran Ayoub, Carlos Natalino, Ali Al Housseini, Felix Foschum, Philipp Morger, Tiziano Leidi, David Hock, Paolo Monti
As artificial intelligence and machine learning (AI/ML) models become integral to network operations, their lack of transparency poses a significant barrier to operator trust. Existing explainable artificial intelligence (XAI) techniques often fail to bridge this gap for non-specialists, producing technical outputs that are difficult to translate into actionable insights.
arXiv:2608. 00044v1 Announce Type: cross Abstract: We propose a retrieval-based framework for crossdomain quality-of-transmission (QoT) estimation that leverages transferable feature representations while avoiding reliance on source-domain-specific decision boundaries.
By Ali Al Housseini, Carlos Natalino, Paolo Monti, Omran Ayoub
arXiv:2607. 20666v1 Announce Type: cross Abstract: The robustness of machine learning techniques across heterogeneous network domains remains an open challenge in optical networks.
By Ali Al Housseini, Carlos Natalino, Paolo Monti, Omran Ayoub
arXiv:2602.20144v2 Announce Type: replace-cross
Abstract: We present AgentOptics, an agentic AI framework for high-fidelity, autonomous optical system control built on the Model Context Protocol (MCP...
By 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
arXiv:2608. 03071v1 Announce Type: new Abstract: Large language model agents derive much of their capability from tool use.
By Guoyao Yu, Xiaoqing Sun, Ziqi Huang, Shaojing Fan, Zhongyi Zhang, Xiaomeng Hu, Xiaobo Xue, Yangyang Shi, Xiong Xiao, Yang Song, Biao Lyu, Rong Wen, Xing Li, Qinming He, Shunming Zhu, Zhenguang Liu
arXiv:2603. 16728v2 Announce Type: replace Abstract: Vision-language models (VLMs) are increasingly deployed in high-stakes settings where reliable uncertainty quantification (UQ) is as important as predictive accuracy.
By Robert Welch, Emir Konuk, Kevin Smith
arXiv:2608. 19807v1 Announce Type: new Abstract: Vision-language models (VLMs) can estimate physical quantities such as duration, speed, and acceleration from visual observations, but existing benchmarks primarily assess overall model performance against annotated ground truth.
By Rongyu Yu, Ke Niu, Fengxiang He
arXiv:2607. 06786v1 Announce Type: cross Abstract: Standards bodies, including TM Forum, 3GPP, and ETSI, are converging on Agentic AI as the foundation for next-generation network management, where Large AI Model (LAM)-based agents autonomously interpret intent, coordinate resources, and adapt operational behaviors at runtime.
By Petar Djukic, Sudipta Acharya, Takai Eddine Kennouche, Burak Kantarci
The paper introduces SCX Router, a lightweight GLiClass-based model selector that assigns suitability scores to inference-time language models without autoregressive generation. It uses a 0.6B-parameter Qwen3 decoder with a shallow bidirectional scorer, preserving a text-only key–value cache across sessions and predicting task attributes such as type, difficulty, and expected output length. The authors build a comprehensive task ontology with 23 families, 115 types, and 1,173 synthetic examples, generating 150,000 verifier-scored tasks to train the router, which outperforms baseline models on LiveBench subsets with a top‑1 score of 0.707 versus 0.696 for the strongest fixed model.
By Ihor Stepanov, Aleksandr Smechov, Mykhailo Shtopko, Dmytro Vodianytskyi, Oleksandr Lukashov