Saved in:
Bibliographic Details
Main Authors: Lira, Oscar G., Caicedo, Oscar M., Da Fonseca, Nelson L. S.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.02861
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915648966230016
author Lira, Oscar G.
Caicedo, Oscar M.
Da Fonseca, Nelson L. S.
author_facet Lira, Oscar G.
Caicedo, Oscar M.
Da Fonseca, Nelson L. S.
contents As modern networks grow in scale and complexity, manual configuration becomes increasingly inefficient and prone to human error. While intent-driven self-configuration using large language models has shown significant promise, such models remain computationally expensive, resource-intensive, and often raise privacy concerns because they typically rely on external cloud infrastructure. This work introduces SLM_netconfig, a fine-tuned small language model framework that uses an agent-based architecture and parameter-efficient adaptation techniques to translate configuration intents expressed as natural language requirements or questions into syntactically and semantically valid network configurations. The system is trained on a domain-specific dataset generated through a pipeline derived from vendor documentation, ensuring strong alignment with real-world configuration practices. Extensive evaluation shows that SLM_netconfig, when using its question-to-configuration model, achieves higher syntactic accuracy and goal accuracy than LLM-NetCFG while substantially reducing translation latency and producing concise, interpretable configurations. These results demonstrate that fine-tuned small language models, as implemented in SLM_netconfig, can deliver efficient, accurate, and privacy-preserving automated configuration generation entirely on-premise, making them a practical and scalable solution for modern autonomous network configuration.
format Preprint
id arxiv_https___arxiv_org_abs_2512_02861
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Network Self-Configuration based on Fine-Tuned Small Language Models
Lira, Oscar G.
Caicedo, Oscar M.
Da Fonseca, Nelson L. S.
Networking and Internet Architecture
As modern networks grow in scale and complexity, manual configuration becomes increasingly inefficient and prone to human error. While intent-driven self-configuration using large language models has shown significant promise, such models remain computationally expensive, resource-intensive, and often raise privacy concerns because they typically rely on external cloud infrastructure. This work introduces SLM_netconfig, a fine-tuned small language model framework that uses an agent-based architecture and parameter-efficient adaptation techniques to translate configuration intents expressed as natural language requirements or questions into syntactically and semantically valid network configurations. The system is trained on a domain-specific dataset generated through a pipeline derived from vendor documentation, ensuring strong alignment with real-world configuration practices. Extensive evaluation shows that SLM_netconfig, when using its question-to-configuration model, achieves higher syntactic accuracy and goal accuracy than LLM-NetCFG while substantially reducing translation latency and producing concise, interpretable configurations. These results demonstrate that fine-tuned small language models, as implemented in SLM_netconfig, can deliver efficient, accurate, and privacy-preserving automated configuration generation entirely on-premise, making them a practical and scalable solution for modern autonomous network configuration.
title Network Self-Configuration based on Fine-Tuned Small Language Models
topic Networking and Internet Architecture
url https://arxiv.org/abs/2512.02861