Metaheuristics and Large Language Models Join Forces: Toward an Integrated Optimization Approach
Not on the map. Why?
Abstract (arXiv)
Since the rise of Large Language Models (LLMs) a couple of years ago, researchers in metaheuristics (MHs) have wondered how to use their power in a beneficial way within their algorithms. This paper introduces a novel approach that leverages LLMs as pattern recognition tools to improve MHs. The resulting hybrid method, tested in the context of a social network-based combinatorial optimization problem, outperforms existing state-of-the-art approaches that combine machine learning with MHs regarding the obtained solution quality. By carefully designing prompts, we demonstrate that the output obtained from LLMs can be used as problem knowledge, leading to improved results. Lastly, we acknowledge LLMs' potential drawbacks and limitations and consider it essential to examine them to advance this type of research further. Our method can be reproduced using a tool available at: https://github.com/camilochs/optipattern.
Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 33 of its 64 references that are in the map. First posted on arXiv 28 May 2024.
Builds on
33 of 64 references.
References · 33
- 2017Attention Is All You Needcited by 59,932
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2023GPT-4 Technical Reportcited by 18,132
- 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
- 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
- 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,175
- 2022Emergent Abilities of Large Language Modelscited by 2,483
- 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
- 2023Large Language Models as Optimizerscited by 830
- 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 752
- 2018Machine Learning for Combinatorial Optimization: a Methodological Tour d'Horizoncited by 612
- 2024Large Language Models for Mathematical Reasoning: Progresses and Challengescited by 283
21 more
- 2023LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Modelscited by 279
- 2022Reasoning with Language Model Prompting: A Surveycited by 251
- 2023Large Language Models as General Pattern Machinescited by 196
- 2024Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attentioncited by 194
- 2023Efficient Large Language Models: A Surveycited by 183
- 2023Large Language Models as Evolutionary Optimizerscited by 122
- 2022Large Language Models are few(1)-shot Table Reasonerscited by 116
- 2024Rethinking Interpretability in the Era of Large Language Modelscited by 110
- 2023LLM360: Towards Fully Transparent Open-Source LLMscited by 100
- 2024LLaMoCo: Instruction Tuning of Large Language Models for Optimization Code Generationcited by 45
- 2023Exploring the psychology of LLMs' Moral and Legal Reasoningcited by 43
- 2024Are Large Language Models Good Prompt Optimizers?cited by 37
- 2023Towards Optimizing with Large Language Modelscited by 34
- 2024Prompting open-source and commercial language models for grammatical error correction of English learner textcited by 24
- 2023ChatGPT's One-year Anniversary: Are Open-Source Large Language Models Catching up?cited by 15
- 2021Reproducibility in Evolutionary Computationcited by 12
- 2024Risk and Response in Large Language Models: Evaluating Key Threat Categoriescited by 10
- 2020Boosting Ant Colony Optimization via Solution Prediction and Machine Learningcited by 7
- 2021FastCover: An Unsupervised Learning Framework for Multi-Hop Influence Maximization in Social Networkscited by 4
- 2022A machine learning framework for neighbor generation in metaheuristic searchcited by 4
- 2022An attention model for the formation of collectives in real-world domainscited by 2
Built on by
Citing papers per year: 2024: 1; 2025: 5.
6 papers.
- 2024A Systematic Survey on Large Language Models for Algorithm Designcited by 65
- 2025Large Language Models and Evolutionary Computation: A Critical Review of Bidirectional Interaction, Automated Algorithm Design, and Co-Adaptive Systemscited by 6
- 2025Combinatorial Optimization for All: Using LLMs to Aid Non-Experts in Improving Optimization Algorithmscited by 5
- 2025Large Language Models in Operations Research: Methods, Applications, and Challengescited by 4
- 2025RAG/LLM Augmented Switching Driven Polymorphic Metaheuristic Frameworkcited by 0
- 2025LLM-Based Instance-Driven Heuristic Bias In the Context of a Biased Random Key Genetic Algorithmcited by 0
- 2025Large Language Models in Operations Research: Methods, Applications, and Challenges18 Sep 2025
- 2025LLM-Based Instance-Driven Heuristic Bias In the Context of a Biased Random Key Genetic Algorithm5 Sep 2025
- 2025Large Language Models and Evolutionary Computation: A Critical Review of Bidirectional Interaction, Automated Algorithm Design, and Co-Adaptive Systems21 May 2025
- 2025RAG/LLM Augmented Switching Driven Polymorphic Metaheuristic Framework20 May 2025
- 2025Combinatorial Optimization for All: Using LLMs to Aid Non-Experts in Improving Optimization Algorithms14 Mar 2025
- 2024A Systematic Survey on Large Language Models for Algorithm Design11 Oct 2024