MultiGA: Leveraging Multi-Source Seeding in Genetic Algorithms
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_ | 1866918424498667520 |
|---|---|
| author | Ng, Isabelle Diana May-Xin Weerasooriya, Tharindu Cyril Zhu, Haitao Wei, Wei |
| author_facet | Ng, Isabelle Diana May-Xin Weerasooriya, Tharindu Cyril Zhu, Haitao Wei, Wei |
| contents | In this paper, we introduce, MultiGA, an optimization framework which applies genetic algorithm principles to address complex natural language tasks and reasoning problems by sampling from a diverse population of LLMs to initialize the population of candidate solutions. MultiGA generates a range of outputs from various parent LLMs and uses a neutral fitness function to evaluate them. Through an iterative recombination process, we mix and refine these generations until an optimal solution is achieved. Our results show that MultiGA produces high accuracy across multiple benchmarks, and these insights lay the foundation for future research looking closer at integrating multiple LLMs for unexplored tasks in which selecting only one pre-trained model is unclear or suboptimal. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_04097 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MultiGA: Leveraging Multi-Source Seeding in Genetic Algorithms Ng, Isabelle Diana May-Xin Weerasooriya, Tharindu Cyril Zhu, Haitao Wei, Wei Neural and Evolutionary Computing Artificial Intelligence In this paper, we introduce, MultiGA, an optimization framework which applies genetic algorithm principles to address complex natural language tasks and reasoning problems by sampling from a diverse population of LLMs to initialize the population of candidate solutions. MultiGA generates a range of outputs from various parent LLMs and uses a neutral fitness function to evaluate them. Through an iterative recombination process, we mix and refine these generations until an optimal solution is achieved. Our results show that MultiGA produces high accuracy across multiple benchmarks, and these insights lay the foundation for future research looking closer at integrating multiple LLMs for unexplored tasks in which selecting only one pre-trained model is unclear or suboptimal. |
| title | MultiGA: Leveraging Multi-Source Seeding in Genetic Algorithms |
| topic | Neural and Evolutionary Computing Artificial Intelligence |
| url | https://arxiv.org/abs/2512.04097 |