Comparing six LLaMEA prompt and selection variants on 5D BBOB problems, the 1+1 elitist variant using both simplify and random-perturbation prompts produced the best anytime performance, and behaviour metrics link this to stronger exploitation and less stagnation.
Research Report RR-6829, INRIA (2009), https://hal.inria.fr/inria-00362633
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Behaviour Space Analysis of LLM-driven Meta-heuristic Discovery
Comparing six LLaMEA prompt and selection variants on 5D BBOB problems, the 1+1 elitist variant using both simplify and random-perturbation prompts produced the best anytime performance, and behaviour metrics link this to stronger exploitation and less stagnation.