arXiv cs.NE
· Papers
Benchmarking Zero-Shot LLM-Generated Parent Selection in Genetic Programming for Symbolic Regression
arXiv:2607.23505v1 Announce Type: new Abstract: Parent selection significantly affects exploration, exploitation, and complexity control in genetic programming (GP) for symbolic regression. It is unclear whether large language models (LLMs) can synthesize effective operators in a zero-shot setting without iterative met