发表机构
CERI-LIA, University of Avignon（阿维尼翁大学CERI-LIA实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出一个结合分层建模和系统验证的约束驱动流水线，利用大语言模型从自然语言需求生成结构有效且符合约束的网络拓扑，并通过多模型对比评估其正确性和弹性。
AI 中文摘要
从自然语言需求设计可部署且弹性的网络拓扑仍然是网络自动化中的一个挑战性问题。本研究通过一个结合分层建模和系统验证的约束驱动流水线，研究大语言模型（LLMs）生成结构有效且符合约束的网络拓扑的能力。该框架通过多模型比较评估，涉及专有和开源LLMs在四个真实网络场景上，这些场景作为公共数据集发布。我们使用节点和边的F1分数与参考拓扑对比来评估结构正确性，并通过服务器和内容连接性指标评估弹性。此外，我们分析了常见的失败模式，包括生成拓扑中的接口不匹配和方向不一致。总体而言，这项工作为理解LLMs在拓扑合成中如何处理结构和弹性约束提供了一个系统基准，并支持AI驱动网络设计中的知情模型选择。
英文摘要
Designing deployable and resilient network topologies from natural language requirements remains a challenging problem in network automation. This work investigates the ability of Large Language Models (LLMs) to generate structurally valid and constraint-compliant network topologies through a constraint-driven pipeline combining hierarchical modeling and systematic validation. The framework is evaluated via a multimodel comparison of proprietary and open-weight LLMs across four realistic network scenarios released as a public dataset. We assess structural correctness using node and edge F1-scores against reference topologies, and evaluate resilience through server and content connectivity metrics. In addition, we analyze common failure modes, including interface mismatches and directional inconsistencies in generated topologies. Overall, this work provides a systematic benchmark for understanding how LLMs handle structural and resilience constraints in topology synthesis, and supports informed model selection for AI-driven network design.
