Revisiting Routing Optimization in Cross-Layer Networks with LLM-Assisted Auxiliary Graphs

We investigate routing optimization in cross-layer networks using a large language model (LLM)-assisted auxiliary graph. Numerical results show that it significantly outperforms both heuristic and DRL methods in terms of resource efficiency and latency reduction.

Authors

Institutions

Publication Details

Published
2025-11-05
DOI
https://doi.org/10.1109/acp66871.2025.11350587
Primary Topic
Software-Defined Networks and 5G
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Revisiting Routing Optimization in Cross-Layer Networks with LLM-Assisted Auxiliary Graphs

Qiaolun Zhang, Jiarui Zhang, Ruikun Wang, Zheng Zhang et al.
Software-Defined Networks and 5G
article

Revisiting Routing Optimization in Cross-Layer Networks with LLM-Assisted Auxiliary Graphs

Qiaolun Zhang, Jiarui Zhang, Ruikun Wang, Zheng Zhang, Xin Wang, Massimo Tornatore, Jingjing Wang, Zhiqun Gu
article en

Abstract

We investigate routing optimization in cross-layer networks using a large language model (LLM)-assisted auxiliary graph. Numerical results show that it significantly outperforms both heuristic and DRL methods in terms of resource efficiency and latency reduction.

Beijing University of Posts and Telecommunications (CN), Qingdao University of Science and Technology (CN), Beijing Information Science & Technology University (CN), Politecnico di Milano (IT)
Decent work and economic growth
Openalex Percentile: Top 28%
Software-Defined Networks and 5G
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.