<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cui-niu-2026-cvar">
    <titleInfo>
        <title>CVaR-RMD: CVaR Selection Pressure for Robust Metaheuristic Discovery</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ruodai</namePart>
        <namePart type="family">Cui</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Li</namePart>
        <namePart type="family">Niu</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>Large language models have recently been used to discover heuristics through iterative program search, offering a promising approach to automated algorithm design. However, candidates selected by average performance may degrade across instance families, random seeds, and problem scales because mean-based objectives can obscure rare but severe failures. We propose CVaR-RMD, a risk-sensitive evolutionary framework that uses an LLM to mutate executable heuristic programs and ranks candidates by empirical conditional value-at-risk over heterogeneous evaluation conditions. Across three combinatorial optimization domains, CVaR-based selection improves upper-tail performance and reduces failure rates while maintaining competitive mean performance. These gains persist on larger unseen instances and independently curated within-domain benchmarks. Code is available https://github.com/BeyondHeaven/CVaR-RMD.</abstract>
    <identifier type="citekey">cui-niu-2026-cvar</identifier>
    <identifier type="doi">10.18653/2026.findings-emnlp.687</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.687/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>14407</start>
            <end>14429</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T CVaR-RMD: CVaR Selection Pressure for Robust Metaheuristic Discovery
%A Cui, Ruodai
%A Niu, Li
%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 cui-niu-2026-cvar
%X Large language models have recently been used to discover heuristics through iterative program search, offering a promising approach to automated algorithm design. However, candidates selected by average performance may degrade across instance families, random seeds, and problem scales because mean-based objectives can obscure rare but severe failures. We propose CVaR-RMD, a risk-sensitive evolutionary framework that uses an LLM to mutate executable heuristic programs and ranks candidates by empirical conditional value-at-risk over heterogeneous evaluation conditions. Across three combinatorial optimization domains, CVaR-based selection improves upper-tail performance and reduces failure rates while maintaining competitive mean performance. These gains persist on larger unseen instances and independently curated within-domain benchmarks. Code is available https://github.com/BeyondHeaven/CVaR-RMD.
%R 10.18653/2026.findings-emnlp.687
%U https://aclanthology.org/2026.findings-emnlp.687/
%U https://doi.org/10.18653/2026.findings-emnlp.687
%P 14407-14429

Markdown (Informal)

[CVaR-RMD: CVaR Selection Pressure for Robust Metaheuristic Discovery](https://aclanthology.org/2026.findings-emnlp.687/) (Cui & Niu, Findings 2026)

• CVaR-RMD: CVaR Selection Pressure for Robust Metaheuristic Discovery (Cui & Niu, Findings 2026)

ACL

• Ruodai Cui and Li Niu. 2026. CVaR-RMD: CVaR Selection Pressure for Robust Metaheuristic Discovery. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 14407–14429, Budapest, Hungary. Association for Computational Linguistics.