Long-Term Agent Memory through Complementary Curation and Consolidation

Abhishek Gupta; Dongge Han; Daniel Madrigal; Wei-Ning Chen; Mayukh Das; Victor Rühle; Saravan Rajmohan

Long-Term Agent Memory through Complementary Curation and Consolidation

Abhishek Gupta, Dongge Han, Daniel Madrigal, Wei-Ning Chen, Mayukh Das, Victor Rühle, Saravan Rajmohan

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use ... for bold, ... for italic, ... for underline, <sc>...</sc> for small-caps, <tt>...<tt> for typewriter text, <url>...</url> for URLs, <a href=...> for hyperlinks, and <par/> for paragraph breaks.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

Long-horizon dialogue agents require effective memory systems to recall facts, events, and relationships from interaction histories. In this work, we propose a hybrid-memory architecture comprising episodic memories and structured relational memories and a consolidation mechanism which preserves efficiency. We conduct an empirical study across two benchmarks: LoCoMo and LongMemEval-S. Our experiments demonstrate that the two memory types are consistently complementary, combining both outperform state-of-the-art memory frameworks and achieves 90.2% accuracy on LoCoMo and 85.5% on LongMemEval-S.

Anthology ID:: 2026.findings-aacl.218
Volume:: Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
Month:: November
Year:: 2026
Address:: Hengqin, China
Editors:: Yue Zhang, Ruifeng Xu, Ayu Purwarianti, Tong Rong, Jun Suzuki
Venue:: Findings
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 4286–4294
Language:
URL:: https://aclanthology.org/2026.findings-aacl.218/
DOI:
Bibkey:
Cite (ACL):: Abhishek Gupta, Dongge Han, Daniel Madrigal, Wei-Ning Chen, Mayukh Das, Victor Rühle, and Saravan Rajmohan. 2026. Long-Term Agent Memory through Complementary Curation and Consolidation. In Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026, pages 4286–4294, Hengqin, China. Association for Computational Linguistics.
Cite (Informal):: Long-Term Agent Memory through Complementary Curation and Consolidation (Gupta et al., Findings 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.findings-aacl.218.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{gupta-etal-2026-long,
    title = "Long-Term Agent Memory through Complementary Curation and Consolidation",
    author = {Gupta, Abhishek  and
      Han, Dongge  and
      Madrigal, Daniel  and
      Chen, Wei-Ning  and
      Das, Mayukh  and
      R{\"u}hle, Victor  and
      Rajmohan, Saravan},
    editor = "Zhang, Yue  and
      Xu, Ruifeng  and
      Purwarianti, Ayu  and
      Rong, Tong  and
      Suzuki, Jun",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {IJCNLP}-{AACL} 2026",
    month = nov,
    year = "2026",
    address = "Hengqin, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-aacl.218/",
    pages = "4286--4294",
    ISBN = "979-8-89176-444-6",
    abstract = "Long-horizon dialogue agents require effective memory systems to recall facts, events, and relationships from interaction histories. In this work, we propose a hybrid-memory architecture comprising episodic memories and structured relational memories and a consolidation mechanism which preserves efficiency. We conduct an empirical study across two benchmarks: LoCoMo and LongMemEval-S. Our experiments demonstrate that the two memory types are consistently complementary, combining both outperform state-of-the-art memory frameworks and achieves 90.2{\%} accuracy on LoCoMo and 85.5{\%} on LongMemEval-S."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gupta-etal-2026-long">
    <titleInfo>
        <title>Long-Term Agent Memory through Complementary Curation and Consolidation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Abhishek</namePart>
        <namePart type="family">Gupta</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dongge</namePart>
        <namePart type="family">Han</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Daniel</namePart>
        <namePart type="family">Madrigal</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wei-Ning</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mayukh</namePart>
        <namePart type="family">Das</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Victor</namePart>
        <namePart type="family">Rühle</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Saravan</namePart>
        <namePart type="family">Rajmohan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yue</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ruifeng</namePart>
            <namePart type="family">Xu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ayu</namePart>
            <namePart type="family">Purwarianti</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tong</namePart>
            <namePart type="family">Rong</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jun</namePart>
            <namePart type="family">Suzuki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Hengqin, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-444-6</identifier>
    </relatedItem>
    <abstract>Long-horizon dialogue agents require effective memory systems to recall facts, events, and relationships from interaction histories. In this work, we propose a hybrid-memory architecture comprising episodic memories and structured relational memories and a consolidation mechanism which preserves efficiency. We conduct an empirical study across two benchmarks: LoCoMo and LongMemEval-S. Our experiments demonstrate that the two memory types are consistently complementary, combining both outperform state-of-the-art memory frameworks and achieves 90.2% accuracy on LoCoMo and 85.5% on LongMemEval-S.</abstract>
    <identifier type="citekey">gupta-etal-2026-long</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-aacl.218/</url>
    </location>
    <part>
        <date>2026-11</date>
        <extent unit="page">
            <start>4286</start>
            <end>4294</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Long-Term Agent Memory through Complementary Curation and Consolidation
%A Gupta, Abhishek
%A Han, Dongge
%A Madrigal, Daniel
%A Chen, Wei-Ning
%A Das, Mayukh
%A Rühle, Victor
%A Rajmohan, Saravan
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-444-6
%F gupta-etal-2026-long
%X Long-horizon dialogue agents require effective memory systems to recall facts, events, and relationships from interaction histories. In this work, we propose a hybrid-memory architecture comprising episodic memories and structured relational memories and a consolidation mechanism which preserves efficiency. We conduct an empirical study across two benchmarks: LoCoMo and LongMemEval-S. Our experiments demonstrate that the two memory types are consistently complementary, combining both outperform state-of-the-art memory frameworks and achieves 90.2% accuracy on LoCoMo and 85.5% on LongMemEval-S.
%U https://aclanthology.org/2026.findings-aacl.218/
%P 4286-4294

Download as File

Markdown (Informal)

[Long-Term Agent Memory through Complementary Curation and Consolidation](https://aclanthology.org/2026.findings-aacl.218/) (Gupta et al., Findings 2026)

Long-Term Agent Memory through Complementary Curation and Consolidation (Gupta et al., Findings 2026)

ACL

Abhishek Gupta, Dongge Han, Daniel Madrigal, Wei-Ning Chen, Mayukh Das, Victor Rühle, and Saravan Rajmohan. 2026. Long-Term Agent Memory through Complementary Curation and Consolidation. In Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026, pages 4286–4294, Hengqin, China. Association for Computational Linguistics.