Automating Parent Selection Configuration in Genetic Programming with Agentic AI

2026-08-17

AI Summary

研究使用代理AI自动化遗传编程中父代选择算法的设计，通过符号回归测试不同大语言模型的效果，发现最佳配置5 mini--AR表现良好。

Abstract

We investigate whether agentic artificial intelligence can automate parts of the process of designing genetic programming systems by introducing an agentic framework that identifies and implements parent selection algorithms using large language model (LLM) reasoning and retrieval-augmented generation. Using symbolic regression as a test bed, we first conduct an ablation study across four LLM types to evaluate the effects of agentic reasoning and retrieval on generated algorithm categories, validity, implementation similarity, and downstream performance. Results show that these components substantially influence the types of algorithms generated, but their downstream performance largely depends on the underlying LLM. The strongest configuration, the full agentic setup with 5 mini (5 mini--AR), consistently generated established $ε$-lexicase implementations while maintaining competitive downstream performance. We then benchmark this configuration against fixed implementations of tournament selection and semi-dynamic MAD $ε$-lexicase. Across six symbolic regression problems, 5 mini--AR performed similarly to $ε$-lexicase while generally outperforming tournament selection. These findings demonstrate the potential of agentic AI to translate domain knowledge into generating executable components, providing a step toward automated configuration and design of evolutionary systems.

Problem

• agentic AI
• genetic programming
• parent selection
• automated configuration

Innovation

• agentic AI
• genetic programming
• parent selection
• large language model (LLM)
• ε-lexicase