Cross-Domain Query Translation for Network Troubleshooting: A Multi-Agent LLM Framework with Privacy Preservation and Self-Reflection

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Tran, Nguyen Phuc, Jaumard, Brigitte, Premkumar, Karthikeyan, Memon, Salman
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914573949337600
author Tran, Nguyen Phuc
Jaumard, Brigitte
Premkumar, Karthikeyan
Memon, Salman
author_facet Tran, Nguyen Phuc
Jaumard, Brigitte
Premkumar, Karthikeyan
Memon, Salman
contents This paper presents a hierarchical multi-agent LLM architecture to bridge communication gaps between non-technical end users and telecommunications domain experts in private network environments. We propose a cross-domain query translation framework that leverages specialized language models coordinated through multi-agent reflection-based reasoning. The resulting system addresses three critical challenges: (1) accurately classify user queries related to telecommunications network issues using a dual-stage hierarchical approach, (2) preserve user privacy through the anonymization of semantically relevant personally identifiable information (PII) while maintaining diagnostic utility, and (3) translate technical expert responses into user-comprehensible language. Our approach employs ReAct-style agents enhanced with self-reflection mechanisms for iterative output refinement, semantic-preserving anonymization techniques respecting $k$-anonymity and differential privacy principles, and few-shot learning strategies designed for limited training data scenarios. The framework was comprehensively evaluated on 10,000 previously unseen validation scenarios across various vertical industries.
format Preprint
id arxiv_https___arxiv_org_abs_2604_13353
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Cross-Domain Query Translation for Network Troubleshooting: A Multi-Agent LLM Framework with Privacy Preservation and Self-Reflection
Tran, Nguyen Phuc
Jaumard, Brigitte
Premkumar, Karthikeyan
Memon, Salman
Networking and Internet Architecture
This paper presents a hierarchical multi-agent LLM architecture to bridge communication gaps between non-technical end users and telecommunications domain experts in private network environments. We propose a cross-domain query translation framework that leverages specialized language models coordinated through multi-agent reflection-based reasoning. The resulting system addresses three critical challenges: (1) accurately classify user queries related to telecommunications network issues using a dual-stage hierarchical approach, (2) preserve user privacy through the anonymization of semantically relevant personally identifiable information (PII) while maintaining diagnostic utility, and (3) translate technical expert responses into user-comprehensible language. Our approach employs ReAct-style agents enhanced with self-reflection mechanisms for iterative output refinement, semantic-preserving anonymization techniques respecting $k$-anonymity and differential privacy principles, and few-shot learning strategies designed for limited training data scenarios. The framework was comprehensively evaluated on 10,000 previously unseen validation scenarios across various vertical industries.
title Cross-Domain Query Translation for Network Troubleshooting: A Multi-Agent LLM Framework with Privacy Preservation and Self-Reflection
topic Networking and Internet Architecture
url https://arxiv.org/abs/2604.13353