Metaheuristics and Large Language Models Join Forces: Toward an Integrated Optimization Approach
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 resu...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10818476/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841557023313887232 |
|---|---|
| author | Camilo Chacon Sartori Christian Blum Filippo Bistaffa Guillem Rodriguez Corominas |
| author_facet | Camilo Chacon Sartori Christian Blum Filippo Bistaffa Guillem Rodriguez Corominas |
| author_sort | Camilo Chacon Sartori |
| collection | DOAJ |
| description | 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: <uri>https://github.com/camilochs/optipattern</uri>. |
| format | Article |
| id | doaj-art-7abf0e295a0044298e39c22ea9d734e4 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-7abf0e295a0044298e39c22ea9d734e42025-01-07T00:01:46ZengIEEEIEEE Access2169-35362025-01-01132058207910.1109/ACCESS.2024.352417610818476Metaheuristics and Large Language Models Join Forces: Toward an Integrated Optimization ApproachCamilo Chacon Sartori0https://orcid.org/0000-0002-8543-9893Christian Blum1https://orcid.org/0000-0002-1736-3559Filippo Bistaffa2https://orcid.org/0000-0003-1658-6125Guillem Rodriguez Corominas3https://orcid.org/0000-0002-3863-2017Artificial Intelligence Research Institute (IIIA-CSIC), Bellaterra, Barcelona, SpainArtificial Intelligence Research Institute (IIIA-CSIC), Bellaterra, Barcelona, SpainArtificial Intelligence Research Institute (IIIA-CSIC), Bellaterra, Barcelona, SpainArtificial Intelligence Research Institute (IIIA-CSIC), Bellaterra, Barcelona, SpainSince 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: <uri>https://github.com/camilochs/optipattern</uri>.https://ieeexplore.ieee.org/document/10818476/Combinatorial optimizationhybrid algorithmmetaheuristicslarge language models |
| spellingShingle | Camilo Chacon Sartori Christian Blum Filippo Bistaffa Guillem Rodriguez Corominas Metaheuristics and Large Language Models Join Forces: Toward an Integrated Optimization Approach IEEE Access Combinatorial optimization hybrid algorithm metaheuristics large language models |
| title | Metaheuristics and Large Language Models Join Forces: Toward an Integrated Optimization Approach |
| title_full | Metaheuristics and Large Language Models Join Forces: Toward an Integrated Optimization Approach |
| title_fullStr | Metaheuristics and Large Language Models Join Forces: Toward an Integrated Optimization Approach |
| title_full_unstemmed | Metaheuristics and Large Language Models Join Forces: Toward an Integrated Optimization Approach |
| title_short | Metaheuristics and Large Language Models Join Forces: Toward an Integrated Optimization Approach |
| title_sort | metaheuristics and large language models join forces toward an integrated optimization approach |
| topic | Combinatorial optimization hybrid algorithm metaheuristics large language models |
| url | https://ieeexplore.ieee.org/document/10818476/ |
| work_keys_str_mv | AT camilochaconsartori metaheuristicsandlargelanguagemodelsjoinforcestowardanintegratedoptimizationapproach AT christianblum metaheuristicsandlargelanguagemodelsjoinforcestowardanintegratedoptimizationapproach AT filippobistaffa metaheuristicsandlargelanguagemodelsjoinforcestowardanintegratedoptimizationapproach AT guillemrodriguezcorominas metaheuristicsandlargelanguagemodelsjoinforcestowardanintegratedoptimizationapproach |