Saved in:
Bibliographic Details
Main Authors: Song, Youngjin, Lee, Wookjin, Kim, Hong Ki, Lee, Sang Hyun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.07492
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915486235623424
author Song, Youngjin
Lee, Wookjin
Kim, Hong Ki
Lee, Sang Hyun
author_facet Song, Youngjin
Lee, Wookjin
Kim, Hong Ki
Lee, Sang Hyun
contents This work develops an LLM-based optimization framework ensuring strict constraint satisfaction in network optimization. While LLMs possess contextual reasoning capabilities, existing approaches often fail to enforce constraints, causing infeasible solutions. Unlike conventional methods that address average constraints, the proposed framework integrates a natural language-based input encoding strategy to restrict the solution space and guarantee feasibility. For multi-access edge computing networks, task allocation is optimized while minimizing worst-case latency. Numerical evaluations demonstrate LLMs as a promising tool for constraint-aware network optimization, offering insights into their inference capabilities.
format Preprint
id arxiv_https___arxiv_org_abs_2509_07492
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Constraint-Compliant Network Optimization through Large Language Models
Song, Youngjin
Lee, Wookjin
Kim, Hong Ki
Lee, Sang Hyun
Networking and Internet Architecture
This work develops an LLM-based optimization framework ensuring strict constraint satisfaction in network optimization. While LLMs possess contextual reasoning capabilities, existing approaches often fail to enforce constraints, causing infeasible solutions. Unlike conventional methods that address average constraints, the proposed framework integrates a natural language-based input encoding strategy to restrict the solution space and guarantee feasibility. For multi-access edge computing networks, task allocation is optimized while minimizing worst-case latency. Numerical evaluations demonstrate LLMs as a promising tool for constraint-aware network optimization, offering insights into their inference capabilities.
title Constraint-Compliant Network Optimization through Large Language Models
topic Networking and Internet Architecture
url https://arxiv.org/abs/2509.07492