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

2026-04-14

AI Summary

This work addresses the communication barriers between non-technical users and telecommunications experts in private networks, which arise from linguistic gaps, privacy constraints, and cross-domain comprehension challenges. To overcome these issues, the authors propose a hierarchical multi-agent large language model architecture that integrates a self-reflection-augmented ReAct framework, a semantics-preserving PII anonymization mechanism, a two-stage query classifier, and a few-shot learning strategy. The system ensures k-anonymity and differential privacy while enabling high-fidelity semantic translation and the generation of technically accurate yet accessible responses. Evaluation across 10,000 unseen scenarios spanning multiple industries demonstrates that the approach accurately classifies user intent, effectively safeguards privacy, and produces comprehensible expert-level replies.

Technology Category

• Multiagent Systems: Agent Communication
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Machine Learning: Privacy

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems

Abstract

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.

Problem

• cross-domain query translation
• network troubleshooting
• privacy preservation
• multi-agent LLM
• user-expert communication gap

Innovation

• multi-agent LLM
• cross-domain query translation
• privacy-preserving anonymization
• self-reflection mechanism
• few-shot learning