@inproceedings{grie-etal-2025-toolbox,
    title = "A Toolbox for Improving Evolutionary Prompt Search",
    author = "Grie, Daniel  and
      Kimmich, Maximilian  and
      Maucher, Johannes  and
      Vu, Thang",
    editor = "Cardoso, Henrique Lopes  and
      Sousa-Silva, Rui  and
      Koponen, Maarit  and
      Pareja-Lora, Antonio",
    booktitle = "Proceedings of the 2nd LUHME Workshop",
    month = oct,
    year = "2025",
    address = "Bologna, Italy",
    publisher = "UP - Universidade do Porto (https://doi.org/10.21747/978-989-9193-73-4/lan2), LIACC - Laborat{\'o}rio de Intelig{\^e}ncia Artificial e Ci{\^e}ncia de Computadores da Universidade do Porto, CLUP - Centro de Lingu{\'i}stica da Universidade do Porto, UEF - The University of Eastern Finland {\textbackslash}{\&} UAH - Universidad de Alcal{\'a}.",
    url = "https://preview.aclanthology.org/ingest-luhme/2025.luhme-1.6/",
    pages = "58--66",
    abstract = "Evolutionary prompt optimization has demonstrated effectiveness in refining prompts for LLMs. However, existing approaches lack robust operators and efficient evaluation mechanisms. In this work, we propose several key improvements to evolutionary prompt optimization that can partially generalize to prompt optimization in general: 1) decomposing evolution into distinct steps to enhance the evolution and its control, 2) introducing an LLM-based judge to verify the evolutions, 3) integrating human feedback to refine the evolutionary operator, and 4) developing more efficient evaluation strategies that maintain performance while reducing computational overhead. Our approach improves both optimization quality and efficiency. We release our code, enabling prompt optimization on new tasks and facilitating further research in this area."
}