<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ogawa-etal-2026-designing">
    <titleInfo>
        <title>Designing LLM Agents for User-Centered Language Service Selection</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ryoichiro</namePart>
        <namePart type="family">Ogawa</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Donghui</namePart>
        <namePart type="family">Lin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Fumito</namePart>
        <namePart type="family">Uwano</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Stelios</namePart>
            <namePart type="family">Piperidis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Núria</namePart>
            <namePart type="family">Bel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Henk</namePart>
            <namePart type="family">van den Heuvel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nancy</namePart>
            <namePart type="family">Ide</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Simon</namePart>
            <namePart type="family">Krek</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Antonio</namePart>
            <namePart type="family">Toral</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>ELRA Language Resource Association</publisher>
            <place>
                <placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>With the rapid expansion of language resources and services across repositories and platforms, users face an overwhelming number of options. While this diversity promises flexibility, non-experts struggle to compose appropriate resource pipelines and select services that satisfy both functional and non-functional requirements. We propose a user-centered framework of LLM agents that interprets natural-language requests and performs end-to-end language service selection. The agents extract functional requirements to form coherent task compositions and select suitable language services for each component by interpreting non-functional quality aspects embedded in contextual cues. To ensure reliable and explainable decisions, we employ a four-step structured reasoning procedure that combines Few-Shot exemplars and Chain-of-Thought reasoning: extracting functional requirements, inducing non-functional evaluation axes, applying these axes as constraints in candidate retrieval, and determining a final composition. We construct a benchmark dataset pairing diverse user requests with standardized language service profiles containing metadata and quality indicators, and evaluate our framework against representative prompting-based baselines. Results show consistent gains in Precision, Recall, and F1-score, demonstrating improved capture of both functional intent and quality preferences. These findings demonstrate that structured LLM agents can bridge natural-language user intents and language service configurations, enabling end-to-end selection and composition in a transparent and user-centered manner.</abstract>
    <identifier type="citekey">ogawa-etal-2026-designing</identifier>
    <identifier type="doi">10.63317/59qnh9w46bv6</identifier>
    <location>
        <url>https://aclanthology.org/2026.lrec-1.42/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>599</start>
            <end>608</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Designing LLM Agents for User-Centered Language Service Selection
%A Ogawa, Ryoichiro
%A Lin, Donghui
%A Uwano, Fumito
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F ogawa-etal-2026-designing
%X With the rapid expansion of language resources and services across repositories and platforms, users face an overwhelming number of options. While this diversity promises flexibility, non-experts struggle to compose appropriate resource pipelines and select services that satisfy both functional and non-functional requirements. We propose a user-centered framework of LLM agents that interprets natural-language requests and performs end-to-end language service selection. The agents extract functional requirements to form coherent task compositions and select suitable language services for each component by interpreting non-functional quality aspects embedded in contextual cues. To ensure reliable and explainable decisions, we employ a four-step structured reasoning procedure that combines Few-Shot exemplars and Chain-of-Thought reasoning: extracting functional requirements, inducing non-functional evaluation axes, applying these axes as constraints in candidate retrieval, and determining a final composition. We construct a benchmark dataset pairing diverse user requests with standardized language service profiles containing metadata and quality indicators, and evaluate our framework against representative prompting-based baselines. Results show consistent gains in Precision, Recall, and F1-score, demonstrating improved capture of both functional intent and quality preferences. These findings demonstrate that structured LLM agents can bridge natural-language user intents and language service configurations, enabling end-to-end selection and composition in a transparent and user-centered manner.
%R 10.63317/59qnh9w46bv6
%U https://aclanthology.org/2026.lrec-1.42/
%U https://doi.org/10.63317/59qnh9w46bv6
%P 599-608

Markdown (Informal)

[Designing LLM Agents for User-Centered Language Service Selection](https://aclanthology.org/2026.lrec-1.42/) (Ogawa et al., LREC 2026)

• Designing LLM Agents for User-Centered Language Service Selection (Ogawa et al., LREC 2026)

ACL

• Ryoichiro Ogawa, Donghui Lin, and Fumito Uwano. 2026. Designing LLM Agents for User-Centered Language Service Selection. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 599–608, Palma de Mallorca, Spain. ELRA Language Resource Association.