Researchers have developed an agentic AI framework to automate the configuration of parent selection algorithms in genetic programming. This framework utilizes large language model reasoning and retrieval-augmented generation to identify and implement these algorithms. In testing with symbolic regression problems, the strongest configuration, referred to as '5 mini--AR', demonstrated competitive performance, generating established epsilon-lexicase implementations and generally outperforming tournament selection. AI
IMPACT This research demonstrates the potential for AI to automate the design of evolutionary systems, potentially accelerating development in fields that use genetic programming.
RANK_REASON The cluster contains an academic paper detailing a new methodology for automating AI system design. [lever_c_demoted from research: ic=1 ai=1.0]
Read on arXiv cs.NE (Neural & Evolutionary) →
- 5 mini--AR
- arXiv
- epsilon-lexicase
- Hugging Face
- José Hernández
- MAD epsilon-lexicase
- Tournament selection
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →