DESIRE6G PROJECT

Part of EU Open Research Repository
Published November 15, 2025 | Version v1
Presentation Open

LLM-Based Algorithm Selection For Network Optimization and Orchestration

Authors/Creators

  • 1. ROR icon University of Amsterdam

Description

A modular LLM-based framework that uses contextual reasoning to dynamically select the most suitable optimization algorithm for real-time network orchestration. It addresses scaling challenges, reduces manual decision-making, and improves SLA-aware service partitioning across distributed infrastructures. Presented live at the SC25 Conference INDIS Workshop.

Files

INDIS SC25 LLM-based Network Optimization Algorithm Selection and Orchestration Dalgkitsis Presentation v2.pdf

Files (5.7 MB)

Additional details

Funding

European Commission
DESIRE6G - Deep Programmability and Secure Distributed Intelligence for Real-Time End-to-End 6G Networks 101096466