NDT Factory: Synthesizing Verified Network Digital Twins from Semantic Models via Multi-Agent LLM

2026-09-10

AI Summary

本文提出NDT工厂，利用多代理LLM从语义模型合成可执行的行为网络数字孪生，以解决自适应网络服务意图评估问题。

Abstract

Autonomous network management requires systems that can evaluate Network Service Intents (NSIs) under varying conditions without manual implementation of analysis logic, as envisioned in TM Forum Level~4 (L4) autonomy. Behavioral Network Digital Twins (NDTs) enable such evaluation, but existing NDTs rely on pre-defined analytical logic, limiting adaptability for evolving closed-loop control. This paper introduces the NDT factory, a multi-agent software system that synthesizes executable behavioral NDTs on demand from semantic models using Large Language Model (LLM). We validate the system using a Call Admission Control (CAC) case study, where deterministic what-if analysis serves as the admission decision process. The NDT factory generates a complete CAC NDT through parallel synthesis and orchestration, achieving 100% compilation and test pass rates across multiple runs. Simulation over 300 NSIs shows 99.3% decision agreement with a reference implementation, 90% admission rate, and correct attribution of all rejections, demonstrating reliable synthesis with deterministic, verifiable execution.

Problem

• Network Digital Twins
• Semantic Models
• Autonomous Network Management
• Multi-Agent System
• Large Language Model

Innovation

• multi-agent system
• Large Language Model (LLM)
• Network Digital Twins (NDTs)
• semantic models
• autonomous network management