dsm2cli: An Observable Pipeline for Translating Network Intents into Multivendor CLI with Independent Semantic Assessment

• Jerônimo Menezes UFRGS / UNIPAMPA https://orcid.org/0009-0009-3179-1195
• Leonardo Bitzki UFRGS / UNIPAMPA https://orcid.org/0009-0001-8040-7083
• Diego Kreutz UNIPAMPA https://orcid.org/0000-0003-0830-0238
• Gefte Almeida UNIPAMPA https://orcid.org/0009-0009-3354-3785
• Marcio Pohlmann UFRGS / UNIPAMPA https://orcid.org/0009-0003-0856-3756
• Rodrigo Mansilha UNIPAMPA https://orcid.org/0000-0002-2083-653X

DOI: https://doi.org/10.5753/sbrc_estendido.2026.23256

Resumo

Network configuration in multivendor environments remains challenging due to semantic inconsistencies and limited observability in intent-to-CLI workflows. We present dsm2cli, an observable pipeline that translates structured intents into multivendor CLI with independent LLM-based semantic assessment. The approach separates translation from evaluation and produces artifacts such as traceability data, votes, verdicts, and telemetry under a unified contract, without targeting formal verification. Across six scenarios, four configurations, and 72 executions, results show that dsm2cli enables comparison of strategies, exposes semantic failures missed by generation-only workflows, and highlights trade-offs between robustness, cost, and latency.

Referências

Ansible Community (2026). Templating (jinja2) — ansible community documentation. Online documentation. Accessed: 2026-03-26.

Hollósi, G., Ficzere, D., and Varga, P. (2024). Generative AI for low-level NETCONF configuration in network management based on YANG models. In 2024 20th International Conference on Network and Service Management (CNSM), pages 1–7. IEEE.

Hong, J., Tu, N. V., and Hong, J. W.-K. (2025). A comprehensive survey on llm-based network management and operations. International Journal of Network Management, 35(6):e70029.

Jeong, E.-D., Kim, H.-G., Nam, S., Yoo, J.-H., and Hong, J. W.-K. (2024). S-witch: Switch configuration assistant with LLM and prompt engineering. In IEEE/IFIP Network Operations and Management Symposium (NOMS), pages 1–7. IEEE.

Leivadeas, A. and Falkner, M. (2023). A survey on intent-based networking. IEEE Communications Surveys & Tutorials, 25(1):625–655.

Lira, O. G., Caicedo, O. M., and da Fonseca, N. L. (2024). Large language models for zero touch network configuration management. IEEE Communications Magazine, 63(7):146–153.

Long, S., Tan, J., Mao, B., Tang, F., Li, Y., Zhao, M., and Kato, N. (2025). A survey on intelligent network operations and performance optimization based on large language models. IEEE Communications Surveys & Tutorials, 27(6):3915–3949.

Tageldien, M., Selim, B., and Sboui, L. (2025). Large language models in intent-based networking: a comprehensive survey across the intent lifecycle. In 2025 International Telecommunications Conference (ITC-Egypt), pages 810–817. IEEE.

Tu, N., Nam, S., and Hong, J. W.-K. (2025). Intent-based network configuration using large language models. International Journal of Network Management, 35(1):e2313.

Wallin, S., Larsson, P., and Folkesson, P. (2011). Automating network and service configuration using netconf and yang. In LISA’11: Large Installation System Administration Conference. USENIX.

Wang, C., Scazzariello, M., Farshin, A., Kostic, D., and Chiesa, M. (2023). Making network configuration human friendly. arXiv preprint.

Wei, Y., Xie, X., Hu, T., Zuo, Y., Chen, X., Chi, K., and Cui, Y. (2025). INTA: Intent-based translation for network configuration with LLM agents. arXiv preprint.

Zeydan, E. and Turk, Y. (2020). Recent advances in intent-based networking: A survey. In 2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring), pages 1–5.