ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909347136667648 |
|---|---|
| author | Ye, Haoran Wang, Jiarui Cao, Zhiguang Berto, Federico Hua, Chuanbo Kim, Haeyeon Park, Jinkyoo Song, Guojie |
| author_facet | Ye, Haoran Wang, Jiarui Cao, Zhiguang Berto, Federico Hua, Chuanbo Kim, Haeyeon Park, Jinkyoo Song, Guojie |
| contents | The omnipresence of NP-hard combinatorial optimization problems (COPs) compels domain experts to engage in trial-and-error heuristic design. The long-standing endeavor of design automation has gained new momentum with the rise of large language models (LLMs). This paper introduces Language Hyper-Heuristics (LHHs), an emerging variant of Hyper-Heuristics that leverages LLMs for heuristic generation, featuring minimal manual intervention and open-ended heuristic spaces. To empower LHHs, we present Reflective Evolution (ReEvo), a novel integration of evolutionary search for efficiently exploring the heuristic space, and LLM reflections to provide verbal gradients within the space. Across five heterogeneous algorithmic types, six different COPs, and both white-box and black-box views of COPs, ReEvo yields state-of-the-art and competitive meta-heuristics, evolutionary algorithms, heuristics, and neural solvers, while being more sample-efficient than prior LHHs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_01145 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution Ye, Haoran Wang, Jiarui Cao, Zhiguang Berto, Federico Hua, Chuanbo Kim, Haeyeon Park, Jinkyoo Song, Guojie Neural and Evolutionary Computing Artificial Intelligence The omnipresence of NP-hard combinatorial optimization problems (COPs) compels domain experts to engage in trial-and-error heuristic design. The long-standing endeavor of design automation has gained new momentum with the rise of large language models (LLMs). This paper introduces Language Hyper-Heuristics (LHHs), an emerging variant of Hyper-Heuristics that leverages LLMs for heuristic generation, featuring minimal manual intervention and open-ended heuristic spaces. To empower LHHs, we present Reflective Evolution (ReEvo), a novel integration of evolutionary search for efficiently exploring the heuristic space, and LLM reflections to provide verbal gradients within the space. Across five heterogeneous algorithmic types, six different COPs, and both white-box and black-box views of COPs, ReEvo yields state-of-the-art and competitive meta-heuristics, evolutionary algorithms, heuristics, and neural solvers, while being more sample-efficient than prior LHHs. |
| title | ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution |
| topic | Neural and Evolutionary Computing Artificial Intelligence |
| url | https://arxiv.org/abs/2402.01145 |