A Toolbox for Improving Evolutionary Prompt Search

Daniel Grieβhaber; Maximilian Kimmich; Johannes Maucher; Thang Vu

A Toolbox for Improving Evolutionary Prompt Search

Daniel Grieβhaber, Maximilian Kimmich, Johannes Maucher, Thang Vu

Correct Metadata for

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

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.

Anthology ID:: 2025.luhme-1.6
Volume:: Proceedings of the 2nd LUHME Workshop
Month:: October
Year:: 2025
Address:: Bologna, Italy
Editors:: Henrique Lopes Cardoso, Rui Sousa-Silva, Maarit Koponen, Antonio Pareja-Lora
Venues:: LUHME | WS
SIG:
Publisher:: LUHME
Note:
Pages:: 58–66
Language:
URL:: https://aclanthology.org/2025.luhme-1.6/
DOI:
Bibkey:
Cite (ACL):: Daniel Grieβhaber, Maximilian Kimmich, Johannes Maucher, and Thang Vu. 2025. A Toolbox for Improving Evolutionary Prompt Search. In Proceedings of the 2nd LUHME Workshop, pages 58–66, Bologna, Italy. LUHME.
Cite (Informal):: A Toolbox for Improving Evolutionary Prompt Search (Grieβhaber et al., LUHME 2025)
Copy Citation:
PDF:: https://aclanthology.org/2025.luhme-1.6.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{griebhaber-etal-2025-toolbox,
    title = "A Toolbox for Improving Evolutionary Prompt Search",
    author = "Grie{\ensuremath{\beta}}haber, 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 = "LUHME",
    url = "https://aclanthology.org/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."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="griebhaber-etal-2025-toolbox">
    <titleInfo>
        <title>A Toolbox for Improving Evolutionary Prompt Search</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Daniel</namePart>
        <namePart type="family">Grie\ensuremathβhaber</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Maximilian</namePart>
        <namePart type="family">Kimmich</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Johannes</namePart>
        <namePart type="family">Maucher</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Thang</namePart>
        <namePart type="family">Vu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2nd LUHME Workshop</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Henrique</namePart>
            <namePart type="given">Lopes</namePart>
            <namePart type="family">Cardoso</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rui</namePart>
            <namePart type="family">Sousa-Silva</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Maarit</namePart>
            <namePart type="family">Koponen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Antonio</namePart>
            <namePart type="family">Pareja-Lora</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>LUHME</publisher>
            <place>
                <placeTerm type="text">Bologna, Italy</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <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.</abstract>
    <identifier type="citekey">griebhaber-etal-2025-toolbox</identifier>
    <location>
        <url>https://aclanthology.org/2025.luhme-1.6/</url>
    </location>
    <part>
        <date>2025-10</date>
        <extent unit="page">
            <start>58</start>
            <end>66</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T A Toolbox for Improving Evolutionary Prompt Search
%A Grie\ensuremathβhaber, Daniel
%A Kimmich, Maximilian
%A Maucher, Johannes
%A Vu, Thang
%Y Cardoso, Henrique Lopes
%Y Sousa-Silva, Rui
%Y Koponen, Maarit
%Y Pareja-Lora, Antonio
%S Proceedings of the 2nd LUHME Workshop
%D 2025
%8 October
%I LUHME
%C Bologna, Italy
%F griebhaber-etal-2025-toolbox
%X 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.
%U https://aclanthology.org/2025.luhme-1.6/
%P 58-66

Download as File

Markdown (Informal)

[A Toolbox for Improving Evolutionary Prompt Search](https://aclanthology.org/2025.luhme-1.6/) (Grieβhaber et al., LUHME 2025)

A Toolbox for Improving Evolutionary Prompt Search (Grieβhaber et al., LUHME 2025)

ACL

Daniel Grieβhaber, Maximilian Kimmich, Johannes Maucher, and Thang Vu. 2025. A Toolbox for Improving Evolutionary Prompt Search. In Proceedings of the 2nd LUHME Workshop, pages 58–66, Bologna, Italy. LUHME.