<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2026-trace-traceable">
    <titleInfo>
        <title>TRACE: A Traceable Agentic Co-Optimizer for Experimental Optimization</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Haoran</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Keyuan</namePart>
        <namePart type="family">Zhou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Keyan</namePart>
        <namePart type="family">Ding</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jiangzhen</namePart>
        <namePart type="family">Fu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hui</namePart>
        <namePart type="family">Qian</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Qiang</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Huajun</namePart>
        <namePart type="family">Chen</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>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>Low-budget experimental optimization requires making consequential experimental decisions from a small number of observations. Bayesian optimization (BO) and related black-box optimizers provide strong proposal mechanisms, but they often hide the intermediate decisions that matter to experimental users. Direct LLM recommendation can leverage broad domain priors and natural-language reasoning, but is difficult to control, audit, or align with the statistical search guarantees of the underlying optimizer. We introduce TRACE, a traceable agentic co-optimizer that keeps the optimizer as the search backbone while wrapping it in an auditable agentic decision layer. TRACE represents agent interventions as bounded actions backed by reusable skills, organizes external and experiential evidence through an Evidence Skill System, and records every optimization step as a decision trace. On low-budget reaction-optimization benchmarks, TRACE improves over the corresponding BO-only optimizers and over LLM-assisted and tree-search baselines on most evaluated metrics. These gains suggest that our agentic system can effectively support experimental optimization by providing structured, traceable decision support around its actions, evidence use, and intervention logic.</abstract>
    <identifier type="citekey">xu-etal-2026-trace-traceable</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.295/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>6264</start>
            <end>6281</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T TRACE: A Traceable Agentic Co-Optimizer for Experimental Optimization
%A Xu, Haoran
%A Zhou, Keyuan
%A Ding, Keyan
%A Fu, Jiangzhen
%A Qian, Hui
%A Zhang, Qiang
%A Chen, Huajun
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F xu-etal-2026-trace-traceable
%X Low-budget experimental optimization requires making consequential experimental decisions from a small number of observations. Bayesian optimization (BO) and related black-box optimizers provide strong proposal mechanisms, but they often hide the intermediate decisions that matter to experimental users. Direct LLM recommendation can leverage broad domain priors and natural-language reasoning, but is difficult to control, audit, or align with the statistical search guarantees of the underlying optimizer. We introduce TRACE, a traceable agentic co-optimizer that keeps the optimizer as the search backbone while wrapping it in an auditable agentic decision layer. TRACE represents agent interventions as bounded actions backed by reusable skills, organizes external and experiential evidence through an Evidence Skill System, and records every optimization step as a decision trace. On low-budget reaction-optimization benchmarks, TRACE improves over the corresponding BO-only optimizers and over LLM-assisted and tree-search baselines on most evaluated metrics. These gains suggest that our agentic system can effectively support experimental optimization by providing structured, traceable decision support around its actions, evidence use, and intervention logic.
%U https://aclanthology.org/2026.findings-emnlp.295/
%P 6264-6281

Markdown (Informal)

[TRACE: A Traceable Agentic Co-Optimizer for Experimental Optimization](https://aclanthology.org/2026.findings-emnlp.295/) (Xu et al., Findings 2026)

• TRACE: A Traceable Agentic Co-Optimizer for Experimental Optimization (Xu et al., Findings 2026)

ACL

• Haoran Xu, Keyuan Zhou, Keyan Ding, Jiangzhen Fu, Hui Qian, Qiang Zhang, and Huajun Chen. 2026. TRACE: A Traceable Agentic Co-Optimizer for Experimental Optimization. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 6264–6281, Budapest, Hungary. Association for Computational Linguistics.