<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="weizhou-lyu-2026-retrieval">
    <titleInfo>
        <title>Retrieval is Enough: A Memory-Augmented Agent for Algorithm Selection</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zhang</namePart>
        <namePart type="family">Weizhou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lixing</namePart>
        <namePart type="family">Lyu</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 Second Workshop for REsearch on Agent Language Models (REALM 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ehsan</namePart>
            <namePart type="family">Kamalloo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nicolas</namePart>
            <namePart type="family">Gontier</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nikolai</namePart>
            <namePart type="family">Rozanov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Maryam</namePart>
            <namePart type="family">Hashemzadeh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Akhil</namePart>
            <namePart type="family">Arora</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">979-8-89176-485-9</identifier>
    </relatedItem>
    <abstract>Selecting the best algorithm for each optimization instance is difficult because algorithm performance can vary substantially across instance structures and parameter settings. Existing learned selectors often encode historical experience in fixed model parameters, making new performance records costly to incorporate. We introduce a memory augmented agent for instance wise algorithm selection based on retrieval augmented generation. Given a new instance, the agent retrieves structurally similar historical cases, each containing the complete performance profile of all candidate options rather than only the winning label. It then reasons over the retrieved objective gaps and rankings before invoking an algorithm and configuration. New verified records can be added directly to the external memory without retraining the selector. We evaluate the proposed approach on 10,898 geographically grounded hub location instances, using 8,718 instances for retrieval and 2,180 for testing across five algorithm and configuration options. The proposed method achieves 68.35% selection accuracy and a 0.549% objective gap relative to the virtual best solver, outperforming the single best solver and retrieval only label voting baselines. These results demonstrate the value of combining retrieval with reasoning over complete solver performance records.</abstract>
    <identifier type="citekey">weizhou-lyu-2026-retrieval</identifier>
    <location>
        <url>https://aclanthology.org/2026.realm-1.20/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>295</start>
            <end>305</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Retrieval is Enough: A Memory-Augmented Agent for Algorithm Selection
%A Weizhou, Zhang
%A Lyu, Lixing
%Y Kamalloo, Ehsan
%Y Gontier, Nicolas
%Y Rozanov, Nikolai
%Y Hashemzadeh, Maryam
%Y Arora, Akhil
%S Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-485-9
%F weizhou-lyu-2026-retrieval
%X Selecting the best algorithm for each optimization instance is difficult because algorithm performance can vary substantially across instance structures and parameter settings. Existing learned selectors often encode historical experience in fixed model parameters, making new performance records costly to incorporate. We introduce a memory augmented agent for instance wise algorithm selection based on retrieval augmented generation. Given a new instance, the agent retrieves structurally similar historical cases, each containing the complete performance profile of all candidate options rather than only the winning label. It then reasons over the retrieved objective gaps and rankings before invoking an algorithm and configuration. New verified records can be added directly to the external memory without retraining the selector. We evaluate the proposed approach on 10,898 geographically grounded hub location instances, using 8,718 instances for retrieval and 2,180 for testing across five algorithm and configuration options. The proposed method achieves 68.35% selection accuracy and a 0.549% objective gap relative to the virtual best solver, outperforming the single best solver and retrieval only label voting baselines. These results demonstrate the value of combining retrieval with reasoning over complete solver performance records.
%U https://aclanthology.org/2026.realm-1.20/
%P 295-305

Markdown (Informal)

[Retrieval is Enough: A Memory-Augmented Agent for Algorithm Selection](https://aclanthology.org/2026.realm-1.20/) (Weizhou & Lyu, REALM 2026)

• Retrieval is Enough: A Memory-Augmented Agent for Algorithm Selection (Weizhou & Lyu, REALM 2026)

ACL

• Zhang Weizhou and Lixing Lyu. 2026. Retrieval is Enough: A Memory-Augmented Agent for Algorithm Selection. In Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026), pages 295–305, Budapest, Hungary. Association for Computational Linguistics.