aiqbench analysis
This research demonstrates how Large Language Models can effectively synthesize valid, resilient network topologies directly from natural language specifications, addressing a key bottleneck in network automation. By benchmarking both proprietary and open-weight models against structural correctness and connectivity metrics, the study provides actionable insights for selecting AI tools that reliably handle complex infrastructure constraints. The work establishes a critical foundation for intent-driven design, where high-level requirements are automatically translated into deployable technical architectures without sacrificing safety or performance.
An LLM-Based Framework for Intent-Driven Network Topology Design
arXiv:2607.00292v2 Announce Type: replace-cross Abstract: 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.
Abstract: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.
Networking and Internet Architecture (cs.NI); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
arXiv:2607.00292 [cs.NI]
(or arXiv:2607.00292v2 [cs.NI] for this version)
https://doi.org/10.48550/arXiv.2607.00292 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 234 words
