# LM4Opt-RA: A Multi-Candidate LLM Framework with Structured Ranking for Automating Network Resource Allocation

arXiv: https://arxiv.org/abs/2512.00039 · HTML: https://mlsanity.com/paper/2512.00039/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 18 of its 73 references that are in the map.
- First posted on arXiv 13 Nov 2025.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 18 of 18)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models](https://mlsanity.com/paper/2410.05229/) (2024)
- [NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions](https://mlsanity.com/paper/2303.08233/) (2023)
- [Let Me Speak Freely? A Study on the Impact of Format Restrictions on Performance of Large Language Models](https://mlsanity.com/paper/2408.02442/) (2024)
- [On the Road to 6G: Visions, Requirements, Key Technologies and Testbeds](https://mlsanity.com/paper/2302.14536/) (2023)
- [OptiMUS: Optimization Modeling Using MIP Solvers and large language models](https://mlsanity.com/paper/2310.06116/) (2023)
- [Improving Automatic VQA Evaluation Using Large Language Models](https://mlsanity.com/paper/2310.02567/) (2023)
- [Holy Grail 2.0: From Natural Language to Constraint Models](https://mlsanity.com/paper/2308.01589/) (2023)
- [Synthesizing mixed-integer linear programming models from natural language descriptions](https://mlsanity.com/paper/2311.15271/) (2023)
- [LM4OPT: Unveiling the Potential of Large Language Models in Formulating Mathematical Optimization Problems](https://mlsanity.com/paper/2403.01342/) (2024)
- [Evaluating LLM Reasoning in the Operations Research Domain with ORQA](https://mlsanity.com/paper/2412.17874/) (2024)
- [Optimal Slice Allocation in 5G Core Networks](https://mlsanity.com/paper/1802.04655/) (2018)
- [Patient-centric HetNets Powered by Machine Learning and Big Data Analytics for 6G Networks](https://mlsanity.com/paper/2003.08239/) (2020)
- [Optimal Virtual Network Function Deployment for 5G Network Slicing in a Hybrid Cloud Infrastructure](https://mlsanity.com/paper/2006.08774/) (2020)
- [5G New Radio Resource Allocation Optimization for Heterogeneous Services](https://mlsanity.com/paper/2011.00612/) (2020)
- [Slice-Aware Resource Calendaring in Cloud-based Radio Access Networks](https://mlsanity.com/paper/2203.00278/) (2022)

## Abstract (arXiv)

Building on advancements in Large Language Models (LLMs), we can tackle complex analytical and mathematical reasoning tasks requiring nuanced contextual understanding. A prime example of such complex tasks is modelling resource allocation optimization in networks, which extends beyond translating natural language inputs into mathematical equations or Linear Programming (LP), Integer Linear Programming (ILP), and Mixed-Integer Linear Programming (MILP) models. However, existing benchmarks and datasets cannot address the complexities of such problems with dynamic environments, interdependent variables, and heterogeneous constraints. To address this gap, we introduce NL4RA, a curated dataset comprising 50 resource allocation optimization problems formulated as LP, ILP, and MILP. We then evaluate the performance of well-known open-source LLMs with varying parameter counts. To enhance existing LLM based methods, we introduce LM4Opt RA, a multi candidate framework that applies diverse prompting strategies such as direct, few shot, and chain of thought, combined with a structured ranking mechanism to improve accuracy. We identified discrepancies between human judgments and automated scoring such as ROUGE, BLEU, or BERT scores. However, human evaluation is time-consuming and requires specialized expertise, making it impractical for a fully automated end-to-end framework. To quantify the difference between LLM-generated responses and ground truth, we introduce LLM-Assisted Mathematical Evaluation (LAME), an automated metric designed for mathematical formulations. Using LM4Opt-RA, Llama-3.1-70B achieved a LAME score of 0.8007, outperforming other models by a significant margin, followed closely by Llama-3.1-8B. While baseline LLMs demonstrate considerable promise, they still lag behind human expertise; our proposed method surpasses these baselines regarding LAME and other metrics.