Landscape-aware Automated Algorithm Design: An Efficient Framework for Real-world Optimization
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908812941721600 |
|---|---|
| author | Yin, Haoran Pan, Shuaiqun Wei, Zhao Wong, Jian Cheng Ong, Yew-Soon Kononova, Anna V. Bäck, Thomas van Stein, Niki |
| author_facet | Yin, Haoran Pan, Shuaiqun Wei, Zhao Wong, Jian Cheng Ong, Yew-Soon Kononova, Anna V. Bäck, Thomas van Stein, Niki |
| contents | The advent of Large Language Models (LLMs) has opened new frontiers in automated algorithm design, giving rise to numerous powerful methods. However, these approaches retain critical limitations: they require extensive evaluation of the target problem to guide the search process, making them impractical for real-world optimization tasks, where each evaluation consumes substantial computational resources. This research proposes an innovative and efficient framework that decouples algorithm discovery from high-cost evaluation. Our core innovation lies in combining a Genetic Programming (GP) function generator with an LLM-driven evolutionary algorithm designer. The evolutionary direction of the GP-based function generator is guided by the similarity between the landscape characteristics of generated proxy functions and those of real-world problems, ensuring that algorithms discovered via proxy functions exhibit comparable performance on real-world problems. Our method enables deep exploration of the algorithmic space before final validation while avoiding costly real-world evaluations. We validated the framework's efficacy across multiple real-world problems, demonstrating its ability to discover high-performance algorithms while substantially reducing expensive evaluations. This approach shows a path to apply LLM-based automated algorithm design to computationally intensive real-world optimization challenges. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_04529 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Landscape-aware Automated Algorithm Design: An Efficient Framework for Real-world Optimization Yin, Haoran Pan, Shuaiqun Wei, Zhao Wong, Jian Cheng Ong, Yew-Soon Kononova, Anna V. Bäck, Thomas van Stein, Niki Neural and Evolutionary Computing The advent of Large Language Models (LLMs) has opened new frontiers in automated algorithm design, giving rise to numerous powerful methods. However, these approaches retain critical limitations: they require extensive evaluation of the target problem to guide the search process, making them impractical for real-world optimization tasks, where each evaluation consumes substantial computational resources. This research proposes an innovative and efficient framework that decouples algorithm discovery from high-cost evaluation. Our core innovation lies in combining a Genetic Programming (GP) function generator with an LLM-driven evolutionary algorithm designer. The evolutionary direction of the GP-based function generator is guided by the similarity between the landscape characteristics of generated proxy functions and those of real-world problems, ensuring that algorithms discovered via proxy functions exhibit comparable performance on real-world problems. Our method enables deep exploration of the algorithmic space before final validation while avoiding costly real-world evaluations. We validated the framework's efficacy across multiple real-world problems, demonstrating its ability to discover high-performance algorithms while substantially reducing expensive evaluations. This approach shows a path to apply LLM-based automated algorithm design to computationally intensive real-world optimization challenges. |
| title | Landscape-aware Automated Algorithm Design: An Efficient Framework for Real-world Optimization |
| topic | Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2602.04529 |