Beyond Scalar Fitness: Behavioural Feedback for LLM-Driven Metaheuristic Evolution
It is found that neutral framing of behavioural features, reporting the feature value without prescriptive advice, consistently outperforms the prescriptive variants, and that prescriptive feedback steers the median feature value in the advised direction in only 37% of cases despite empirically grounded advice.
Max Harell, N. Stein, Thomas Bäck
· 0 citations