Enregistré dans:
Détails bibliographiques
Auteurs principaux: Sarıdaş, İrşat Emin, Salan, Onur, Görçin, Ali, Hokelek, Ibrahim, Çırpan, Hakan Ali
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2606.01222
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914621494919168
author Sarıdaş, İrşat Emin
Salan, Onur
Görçin, Ali
Hokelek, Ibrahim
Çırpan, Hakan Ali
author_facet Sarıdaş, İrşat Emin
Salan, Onur
Görçin, Ali
Hokelek, Ibrahim
Çırpan, Hakan Ali
contents While Large Language Models (LLMs) offer a promising path toward intent-driven network management by translating natural language human intents into machine-readable configurations, they often suffer from hallucinations and structural inconsistencies in multi-step and complex tasks. To address these challenges, this paper proposes a retrieval-augmented and task decomposition-based multi-agent LLM framework for Beyond 5G network auto-configuration. The framework employs a semantic retrieval-augmented generation pipeline to ensure that its outputs are aligned with technical standards and vendor-specific manuals. Furthermore, it introduces a modular architecture for configuration generation, closed-loop configuration verification, and network deployment, in which complex tasks are decomposed into smaller sub-tasks handled by specialized agents. In this architecture, hallucinated configuration parameters are identified by the configuration verifier agent and corrected through low computational segment-level regeneration. The performance evaluation experiments with the OpenAirInterface emulator demonstrate that the proposed task decomposition-based configuration and verification approach improves the average success rate by 22.7% over monolithic methods, achieving 94.4% success in network configuration.
format Preprint
id arxiv_https___arxiv_org_abs_2606_01222
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle RAG-driven Multi-Agent LLM Framework with Task Decomposition for Beyond 5G Auto-Configuration
Sarıdaş, İrşat Emin
Salan, Onur
Görçin, Ali
Hokelek, Ibrahim
Çırpan, Hakan Ali
Signal Processing
While Large Language Models (LLMs) offer a promising path toward intent-driven network management by translating natural language human intents into machine-readable configurations, they often suffer from hallucinations and structural inconsistencies in multi-step and complex tasks. To address these challenges, this paper proposes a retrieval-augmented and task decomposition-based multi-agent LLM framework for Beyond 5G network auto-configuration. The framework employs a semantic retrieval-augmented generation pipeline to ensure that its outputs are aligned with technical standards and vendor-specific manuals. Furthermore, it introduces a modular architecture for configuration generation, closed-loop configuration verification, and network deployment, in which complex tasks are decomposed into smaller sub-tasks handled by specialized agents. In this architecture, hallucinated configuration parameters are identified by the configuration verifier agent and corrected through low computational segment-level regeneration. The performance evaluation experiments with the OpenAirInterface emulator demonstrate that the proposed task decomposition-based configuration and verification approach improves the average success rate by 22.7% over monolithic methods, achieving 94.4% success in network configuration.
title RAG-driven Multi-Agent LLM Framework with Task Decomposition for Beyond 5G Auto-Configuration
topic Signal Processing
url https://arxiv.org/abs/2606.01222