<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="peng-etal-2026-evogenui">
    <titleInfo>
        <title>EvoGenUI-Bench: Evaluating LLMs as Multi-Turn Generative UI Assistants</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yue</namePart>
        <namePart type="family">Peng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lanke</namePart>
        <namePart type="family">Xia</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zihan</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jiahao</namePart>
        <namePart type="family">Ye</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ke</namePart>
        <namePart type="family">Ning</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hongyi</namePart>
        <namePart type="family">Wen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Large language models can generate interactive web interfaces, but reliable generative UI requires maintaining an executable artifact as user requests evolve. We introduce EvoGenUI-Bench, a benchmark for multi-turn interface maintenance comprising 150 five-turn tasks and 750 turns across three scenarios: information presentation, executable interaction, and tool-grounded external state. We execute generated artifacts in a browser and evaluate them using screenshots, source and DOM evidence, actor traces, and runtime logs. Beyond turn-level and episode-level success, we measure cross-turn retention with Adjacent Pass Retention. Across eight models, even the strongest achieves 74.9% Turn Pass while completing only 37.3% of five-turn episodes; APR further falls to 52.4% on tool-grounded tasks. Diagnostic analysis shows that presentation failures center on information architecture, interaction failures on derived-state propagation and affordance binding, and tool-grounded failures additionally involve external-state grounding and requirement decomposition. These results reframe generative UI evaluation from judging isolated outputs to testing whether interface behavior, derived state, external state, and assistant claims remain synchronized as the artifact evolves.</abstract>
    <identifier type="citekey">peng-etal-2026-evogenui</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1158/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>26533</start>
            <end>26549</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T EvoGenUI-Bench: Evaluating LLMs as Multi-Turn Generative UI Assistants
%A Peng, Yue
%A Xia, Lanke
%A Wang, Zihan
%A Ye, Jiahao
%A Ning, Ke
%A Wen, Hongyi
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F peng-etal-2026-evogenui
%X Large language models can generate interactive web interfaces, but reliable generative UI requires maintaining an executable artifact as user requests evolve. We introduce EvoGenUI-Bench, a benchmark for multi-turn interface maintenance comprising 150 five-turn tasks and 750 turns across three scenarios: information presentation, executable interaction, and tool-grounded external state. We execute generated artifacts in a browser and evaluate them using screenshots, source and DOM evidence, actor traces, and runtime logs. Beyond turn-level and episode-level success, we measure cross-turn retention with Adjacent Pass Retention. Across eight models, even the strongest achieves 74.9% Turn Pass while completing only 37.3% of five-turn episodes; APR further falls to 52.4% on tool-grounded tasks. Diagnostic analysis shows that presentation failures center on information architecture, interaction failures on derived-state propagation and affordance binding, and tool-grounded failures additionally involve external-state grounding and requirement decomposition. These results reframe generative UI evaluation from judging isolated outputs to testing whether interface behavior, derived state, external state, and assistant claims remain synchronized as the artifact evolves.
%U https://aclanthology.org/2026.emnlp-main.1158/
%P 26533-26549

Markdown (Informal)

[EvoGenUI-Bench: Evaluating LLMs as Multi-Turn Generative UI Assistants](https://aclanthology.org/2026.emnlp-main.1158/) (Peng et al., EMNLP 2026)

• EvoGenUI-Bench: Evaluating LLMs as Multi-Turn Generative UI Assistants (Peng et al., EMNLP 2026)

ACL

• Yue Peng, Lanke Xia, Zihan Wang, Jiahao Ye, Ke Ning, and Hongyi Wen. 2026. EvoGenUI-Bench: Evaluating LLMs as Multi-Turn Generative UI Assistants. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 26533–26549, Budapest, Hungary. Association for Computational Linguistics.