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 tests using symbolic regression, the agentic setup with 5 mini--AR demonstrated competitive performance, generating established epsilon-lexicase implementations and outperforming tournament selection on several problems. AI
IMPACT Demonstrates potential for AI to automate complex system design, potentially accelerating research and development in evolutionary computation.
RANK_REASON Academic paper detailing a novel application of AI in automating a component of evolutionary algorithms. [lever_c_demoted from research: ic=1 ai=1.0]
Read on arXiv cs.NE (Neural & Evolutionary) →
- 5 mini--AR
- Agentic AI
- arXiv
- epsilon-lexicase
- genetic programming
- large language model
- MAD epsilon-lexicase
- retrieval-augmented generation
- Symbolic regression
- tournament selection
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
