An LLM-Empowered Adaptive Evolutionary Algorithm For Multi-Component Deep Learning Systems
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910999585488896 |
|---|---|
| author | Tian, Haoxiang Han, Xingshuo Wu, Guoquan Guo, An Zhang, Yuan Zhou. Jie Li, Shuo Wei, Jun Zhang, Tianwei |
| author_facet | Tian, Haoxiang Han, Xingshuo Wu, Guoquan Guo, An Zhang, Yuan Zhou. Jie Li, Shuo Wei, Jun Zhang, Tianwei |
| contents | Multi-objective evolutionary algorithms (MOEAs) are widely used for searching optimal solutions in complex multi-component applications. Traditional MOEAs for multi-component deep learning (MCDL) systems face challenges in enhancing the search efficiency while maintaining the diversity. To combat these, this paper proposes $μ$MOEA, the first LLM-empowered adaptive evolutionary search algorithm to detect safety violations in MCDL systems. Inspired by the context-understanding ability of Large Language Models (LLMs), $μ$MOEA promotes the LLM to comprehend the optimization problem and generate an initial population tailed to evolutionary objectives. Subsequently, it employs adaptive selection and variation to iteratively produce offspring, balancing the evolutionary efficiency and diversity. During the evolutionary process, to navigate away from the local optima, $μ$MOEA integrates the evolutionary experience back into the LLM. This utilization harnesses the LLM's quantitative reasoning prowess to generate differential seeds, breaking away from current optimal solutions. We evaluate $μ$MOEA in finding safety violations of MCDL systems, and compare its performance with state-of-the-art MOEA methods. Experimental results show that $μ$MOEA can significantly improve the efficiency and diversity of the evolutionary search. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_00829 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | An LLM-Empowered Adaptive Evolutionary Algorithm For Multi-Component Deep Learning Systems Tian, Haoxiang Han, Xingshuo Wu, Guoquan Guo, An Zhang, Yuan Zhou. Jie Li, Shuo Wei, Jun Zhang, Tianwei Neural and Evolutionary Computing Artificial Intelligence Multi-objective evolutionary algorithms (MOEAs) are widely used for searching optimal solutions in complex multi-component applications. Traditional MOEAs for multi-component deep learning (MCDL) systems face challenges in enhancing the search efficiency while maintaining the diversity. To combat these, this paper proposes $μ$MOEA, the first LLM-empowered adaptive evolutionary search algorithm to detect safety violations in MCDL systems. Inspired by the context-understanding ability of Large Language Models (LLMs), $μ$MOEA promotes the LLM to comprehend the optimization problem and generate an initial population tailed to evolutionary objectives. Subsequently, it employs adaptive selection and variation to iteratively produce offspring, balancing the evolutionary efficiency and diversity. During the evolutionary process, to navigate away from the local optima, $μ$MOEA integrates the evolutionary experience back into the LLM. This utilization harnesses the LLM's quantitative reasoning prowess to generate differential seeds, breaking away from current optimal solutions. We evaluate $μ$MOEA in finding safety violations of MCDL systems, and compare its performance with state-of-the-art MOEA methods. Experimental results show that $μ$MOEA can significantly improve the efficiency and diversity of the evolutionary search. |
| title | An LLM-Empowered Adaptive Evolutionary Algorithm For Multi-Component Deep Learning Systems |
| topic | Neural and Evolutionary Computing Artificial Intelligence |
| url | https://arxiv.org/abs/2501.00829 |