@techreport{contreras-bmwg-ai-agent-benchmarking-00,
    number =    {draft-contreras-bmwg-ai-agent-benchmarking-00},
    type =      {Internet-Draft},
    institution =   {Internet Engineering Task Force},
    publisher = {Internet Engineering Task Force},
    note =      {Work in Progress},
    url =       {https://datatracker.ietf.org/doc/draft-contreras-bmwg-ai-agent-benchmarking/00/},
    author =    {Luis M. Contreras},
    title =     {{Benchmarking Methodology for AI Agents in Network Operations}},
    pagetotal = 8,
    year =      2026,
    month =     jul,
    day =       6,
    abstract =  {This document defines a benchmarking methodology for evaluating Artificial Intelligence (AI) agents performing network operations tasks such as configuration, troubleshooting, and optimization. This document focuses on task-oriented performance metrics, including task completion success, execution efficiency, and robustness across multi-step workflows, proposing benchmarking practices towards agent- based, closed-loop network operation scenarios. The proposed methodology aims to provide a reproducible and vendor- independent framework to compare AI agent effectiveness in controlled network environments.},
}