Large Language Model-Driven Surrogate-Assisted Evolutionary Algorithm for Expensive Optimization
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913926022692864 |
|---|---|
| author | Xie, Lindong Li, Genghui Wang, Zhenkun Chung, Edward Gong, Maoguo |
| author_facet | Xie, Lindong Li, Genghui Wang, Zhenkun Chung, Edward Gong, Maoguo |
| contents | Surrogate-assisted evolutionary algorithms (SAEAs) are a key tool for addressing costly optimization tasks, with their efficiency being heavily dependent on the selection of surrogate models and infill sampling criteria. However, designing an effective dynamic selection strategy for SAEAs is labor-intensive and requires substantial domain knowledge. To address this challenge, this paper proposes LLM-SAEA, a novel approach that integrates large language models (LLMs) to configure both surrogate models and infill sampling criteria online. Specifically, LLM-SAEA develops a collaboration-of-experts framework, where one LLM serves as a scoring expert (LLM-SE), assigning scores to surrogate models and infill sampling criteria based on their optimization performance, while another LLM acts as a decision expert (LLM-DE), selecting the appropriate configurations by analyzing their scores along with the current optimization state. Experimental results demonstrate that LLM-SAEA outperforms several state-of-the-art algorithms across standard test cases. The source code is publicly available at https://github.com/ForrestXie9/LLM-SAEA. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_02892 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Large Language Model-Driven Surrogate-Assisted Evolutionary Algorithm for Expensive Optimization Xie, Lindong Li, Genghui Wang, Zhenkun Chung, Edward Gong, Maoguo Neural and Evolutionary Computing Artificial Intelligence Surrogate-assisted evolutionary algorithms (SAEAs) are a key tool for addressing costly optimization tasks, with their efficiency being heavily dependent on the selection of surrogate models and infill sampling criteria. However, designing an effective dynamic selection strategy for SAEAs is labor-intensive and requires substantial domain knowledge. To address this challenge, this paper proposes LLM-SAEA, a novel approach that integrates large language models (LLMs) to configure both surrogate models and infill sampling criteria online. Specifically, LLM-SAEA develops a collaboration-of-experts framework, where one LLM serves as a scoring expert (LLM-SE), assigning scores to surrogate models and infill sampling criteria based on their optimization performance, while another LLM acts as a decision expert (LLM-DE), selecting the appropriate configurations by analyzing their scores along with the current optimization state. Experimental results demonstrate that LLM-SAEA outperforms several state-of-the-art algorithms across standard test cases. The source code is publicly available at https://github.com/ForrestXie9/LLM-SAEA. |
| title | Large Language Model-Driven Surrogate-Assisted Evolutionary Algorithm for Expensive Optimization |
| topic | Neural and Evolutionary Computing Artificial Intelligence |
| url | https://arxiv.org/abs/2507.02892 |