发表机构
University of Ottawa; Bell Labs Research（渥太华大学; 贝尔实验室研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出NDT工厂，一种基于多智能体LLM的系统，从语义模型按需合成可执行的行为网络数字孪生，在CAC案例中实现100%编译测试通过率及99.3%决策一致性。
AI 中文摘要
自主网络管理需要能够在不同条件下评估网络服务意图（NSI）而无需手动实现分析逻辑的系统，正如TM论坛L4级（L4）自主性所设想的那样。行为网络数字孪生（NDT）能够实现这种评估，但现有的NDT依赖于预定义的分析逻辑，限制了其对不断演进的闭环控制的适应性。本文介绍了NDT工厂，一个多智能体软件系统，它使用大型语言模型（LLM）按需从语义模型合成可执行的行为NDT。我们使用呼叫接纳控制（CAC）案例研究验证了该系统，其中确定性假设分析作为接纳决策过程。NDT工厂通过并行合成和编排生成完整的CAC NDT，在多次运行中实现了100%的编译和测试通过率。对300个NSI的模拟显示，与参考实现有99.3%的决策一致性，90%的接纳率，以及所有拒绝的正确归因，证明了具有确定性、可验证执行的可靠合成。
英文摘要
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.
Comments6 pages, 4 figures, accepted to IEEE Global Communications (Globecom) Conference, 2026
