From Understanding to Excelling: Template-Free Algorithm Design through Structural-Functional Co-Evolution
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915197211377664 |
|---|---|
| author | Zhao, Zhe Wen, Haibin Wang, Pengkun Wei, Ye Zhang, Zaixi Lin, Xi Liu, Fei An, Bo Xiong, Hui Wang, Yang Zhang, Qingfu |
| author_facet | Zhao, Zhe Wen, Haibin Wang, Pengkun Wei, Ye Zhang, Zaixi Lin, Xi Liu, Fei An, Bo Xiong, Hui Wang, Yang Zhang, Qingfu |
| contents | Large language models (LLMs) have greatly accelerated the automation of algorithm generation and optimization. However, current methods such as EoH and FunSearch mainly rely on predefined templates and expert-specified functions that focus solely on the local evolution of key functionalities. Consequently, they fail to fully leverage the synergistic benefits of the overall architecture and the potential of global optimization. In this paper, we introduce an end-to-end algorithm generation and optimization framework based on LLMs. Our approach utilizes the deep semantic understanding of LLMs to convert natural language requirements or human-authored papers into code solutions, and employs a two-dimensional co-evolution strategy to optimize both functional and structural aspects. This closed-loop process spans problem analysis, code generation, and global optimization, automatically identifying key algorithm modules for multi-level joint optimization and continually enhancing performance and design innovation. Extensive experiments demonstrate that our method outperforms traditional local optimization approaches in both performance and innovation, while also exhibiting strong adaptability to unknown environments and breakthrough potential in structural design. By building on human research, our framework generates and optimizes novel algorithms that surpass those designed by human experts, broadening the applicability of LLMs for algorithm design and providing a novel solution pathway for automated algorithm development. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_10721 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | From Understanding to Excelling: Template-Free Algorithm Design through Structural-Functional Co-Evolution Zhao, Zhe Wen, Haibin Wang, Pengkun Wei, Ye Zhang, Zaixi Lin, Xi Liu, Fei An, Bo Xiong, Hui Wang, Yang Zhang, Qingfu Software Engineering Artificial Intelligence 68W20, 68T20 I.2.7 Large language models (LLMs) have greatly accelerated the automation of algorithm generation and optimization. However, current methods such as EoH and FunSearch mainly rely on predefined templates and expert-specified functions that focus solely on the local evolution of key functionalities. Consequently, they fail to fully leverage the synergistic benefits of the overall architecture and the potential of global optimization. In this paper, we introduce an end-to-end algorithm generation and optimization framework based on LLMs. Our approach utilizes the deep semantic understanding of LLMs to convert natural language requirements or human-authored papers into code solutions, and employs a two-dimensional co-evolution strategy to optimize both functional and structural aspects. This closed-loop process spans problem analysis, code generation, and global optimization, automatically identifying key algorithm modules for multi-level joint optimization and continually enhancing performance and design innovation. Extensive experiments demonstrate that our method outperforms traditional local optimization approaches in both performance and innovation, while also exhibiting strong adaptability to unknown environments and breakthrough potential in structural design. By building on human research, our framework generates and optimizes novel algorithms that surpass those designed by human experts, broadening the applicability of LLMs for algorithm design and providing a novel solution pathway for automated algorithm development. |
| title | From Understanding to Excelling: Template-Free Algorithm Design through Structural-Functional Co-Evolution |
| topic | Software Engineering Artificial Intelligence 68W20, 68T20 I.2.7 |
| url | https://arxiv.org/abs/2503.10721 |