Improving Existing Optimization Algorithms with LLMs
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929711903408128 |
|---|---|
| author | Sartori, Camilo Chacón Blum, Christian |
| author_facet | Sartori, Camilo Chacón Blum, Christian |
| contents | The integration of Large Language Models (LLMs) into optimization has created a powerful synergy, opening exciting research opportunities. This paper investigates how LLMs can enhance existing optimization algorithms. Using their pre-trained knowledge, we demonstrate their ability to propose innovative heuristic variations and implementation strategies. To evaluate this, we applied a non-trivial optimization algorithm, Construct, Merge, Solve and Adapt (CMSA) -- a hybrid metaheuristic for combinatorial optimization problems that incorporates a heuristic in the solution construction phase. Our results show that an alternative heuristic proposed by GPT-4o outperforms the expert-designed heuristic of CMSA, with the performance gap widening on larger and denser graphs. Project URL: https://imp-opt-algo-llms.surge.sh/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_08298 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Improving Existing Optimization Algorithms with LLMs Sartori, Camilo Chacón Blum, Christian Artificial Intelligence Computation and Language Machine Learning Software Engineering I.2.7; I.2.8 The integration of Large Language Models (LLMs) into optimization has created a powerful synergy, opening exciting research opportunities. This paper investigates how LLMs can enhance existing optimization algorithms. Using their pre-trained knowledge, we demonstrate their ability to propose innovative heuristic variations and implementation strategies. To evaluate this, we applied a non-trivial optimization algorithm, Construct, Merge, Solve and Adapt (CMSA) -- a hybrid metaheuristic for combinatorial optimization problems that incorporates a heuristic in the solution construction phase. Our results show that an alternative heuristic proposed by GPT-4o outperforms the expert-designed heuristic of CMSA, with the performance gap widening on larger and denser graphs. Project URL: https://imp-opt-algo-llms.surge.sh/ |
| title | Improving Existing Optimization Algorithms with LLMs |
| topic | Artificial Intelligence Computation and Language Machine Learning Software Engineering I.2.7; I.2.8 |
| url | https://arxiv.org/abs/2502.08298 |