Constrained Network Slice Assignment via Large Language Models

Modern networks support \emph{network slicing}, which partitions physical infrastructure into virtual slices tailored to different service requirements (e.g., high bandwidth, low latency). Optimally allocating users to slices is a constrained optimization problem that traditionally requires complex algorithms. In this paper, we explore the use of Large Language Models (LLMs) to tackle the radio resource allocation for network slicing. We focus on two approaches: (1) using an LLM in a zero-shot setting to directly assign user service requests to slices, and (2) formulating an integer programming model where the LLM provides semantic insight by estimating similarity between requests. Our experiments show that an LLM, even with zero-shot prompting, can produce a reasonable first draft of slice assignments, though it may violate some capacity or latency constraints. We then incorporate the LLM’s understanding of service requirements into an optimization solver to generate an improved allocation. The results demonstrate that LLM-guided grouping of requests (based on minimal textual input) achieves performance comparable to traditional methods using detailed numerical data in terms of resource utilization and slice isolation. While the LLM alone is not perfect in satisfying all constraints, it significantly reduces the search space and, in conjunction with exact solvers, highlights a promising collaboration for efficient 5G network slicing resource allocation.