MemPulse: Memory Pulse-Driven Adaptive Long-Context Reasoning with Fact-based Hypergraph

Wenbiao Tao; Yuanfu Wang; Yunshi Lan; Chao Yang

MemPulse: Memory Pulse-Driven Adaptive Long-Context Reasoning with Fact-based Hypergraph

Wenbiao Tao, Yuanfu Wang, Yunshi Lan, Chao Yang

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

Memory-augmented long-context reasoning boosts LLMs’ complex task solving via external knowledge, yet current methods suffer from disjointed memory retrieval-induced context drift and aimless iterations causing premature convergence or redundant computation. We present MemPulse, integrating fact-based memory hypergraphs and pulse-driven adaptive iteration. It builds hypergraphs with facts as hyperedges to gather scattered information and sustain coherent context evolution. Its memory pulse engine computes agent confidence and structural novelty to output dynamic control signals, adjusting retrieval range and stopping criteria for logical reasoning with minimal overhead. Evaluated on Locomo, MemPulse surpasses mainstream baselines in reasoning accuracy and efficiency.

Anthology ID:: 2026.findings-emnlp.947
Volume:: Findings of the Association for Computational Linguistics: EMNLP 2026
Month:: October
Year:: 2026
Address:: Budapest, Hungary
Editors:: Hung-Yi Lee, Sunipa Dev, Jessy Li, Desmond Elliott
Venue:: Findings
SIG:: SIGDAT
Publisher:: Association for Computational Linguistics
Note:
Pages:: 19960–19975
Language:
URL:: https://aclanthology.org/2026.findings-emnlp.947/
DOI:
Bibkey:
Cite (ACL):: Wenbiao Tao, Yuanfu Wang, Yunshi Lan, and Chao Yang. 2026. MemPulse: Memory Pulse-Driven Adaptive Long-Context Reasoning with Fact-based Hypergraph. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 19960–19975, Budapest, Hungary. Association for Computational Linguistics.
Cite (Informal):: MemPulse: Memory Pulse-Driven Adaptive Long-Context Reasoning with Fact-based Hypergraph (Tao et al., Findings 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.findings-emnlp.947.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{tao-etal-2026-mempulse,
    title = "{M}em{P}ulse: Memory Pulse-Driven Adaptive Long-Context Reasoning with Fact-based Hypergraph",
    author = "Tao, Wenbiao  and
      Wang, Yuanfu  and
      Lan, Yunshi  and
      Yang, Chao",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-emnlp.947/",
    pages = "19960--19975",
    ISBN = "979-8-89176-462-0",
    abstract = "Memory-augmented long-context reasoning boosts LLMs' complex task solving via external knowledge, yet current methods suffer from disjointed memory retrieval-induced context drift and aimless iterations causing premature convergence or redundant computation. We present MemPulse, integrating fact-based memory hypergraphs and pulse-driven adaptive iteration. It builds hypergraphs with facts as hyperedges to gather scattered information and sustain coherent context evolution. Its memory pulse engine computes agent confidence and structural novelty to output dynamic control signals, adjusting retrieval range and stopping criteria for logical reasoning with minimal overhead. Evaluated on Locomo, MemPulse surpasses mainstream baselines in reasoning accuracy and efficiency."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tao-etal-2026-mempulse">
    <titleInfo>
        <title>MemPulse: Memory Pulse-Driven Adaptive Long-Context Reasoning with Fact-based Hypergraph</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Wenbiao</namePart>
        <namePart type="family">Tao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yuanfu</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yunshi</namePart>
        <namePart type="family">Lan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chao</namePart>
        <namePart type="family">Yang</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>Memory-augmented long-context reasoning boosts LLMs’ complex task solving via external knowledge, yet current methods suffer from disjointed memory retrieval-induced context drift and aimless iterations causing premature convergence or redundant computation. We present MemPulse, integrating fact-based memory hypergraphs and pulse-driven adaptive iteration. It builds hypergraphs with facts as hyperedges to gather scattered information and sustain coherent context evolution. Its memory pulse engine computes agent confidence and structural novelty to output dynamic control signals, adjusting retrieval range and stopping criteria for logical reasoning with minimal overhead. Evaluated on Locomo, MemPulse surpasses mainstream baselines in reasoning accuracy and efficiency.</abstract>
    <identifier type="citekey">tao-etal-2026-mempulse</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.947/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>19960</start>
            <end>19975</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T MemPulse: Memory Pulse-Driven Adaptive Long-Context Reasoning with Fact-based Hypergraph
%A Tao, Wenbiao
%A Wang, Yuanfu
%A Lan, Yunshi
%A Yang, Chao
%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 tao-etal-2026-mempulse
%X Memory-augmented long-context reasoning boosts LLMs’ complex task solving via external knowledge, yet current methods suffer from disjointed memory retrieval-induced context drift and aimless iterations causing premature convergence or redundant computation. We present MemPulse, integrating fact-based memory hypergraphs and pulse-driven adaptive iteration. It builds hypergraphs with facts as hyperedges to gather scattered information and sustain coherent context evolution. Its memory pulse engine computes agent confidence and structural novelty to output dynamic control signals, adjusting retrieval range and stopping criteria for logical reasoning with minimal overhead. Evaluated on Locomo, MemPulse surpasses mainstream baselines in reasoning accuracy and efficiency.
%U https://aclanthology.org/2026.findings-emnlp.947/
%P 19960-19975

Download as File

Markdown (Informal)

[MemPulse: Memory Pulse-Driven Adaptive Long-Context Reasoning with Fact-based Hypergraph](https://aclanthology.org/2026.findings-emnlp.947/) (Tao et al., Findings 2026)

MemPulse: Memory Pulse-Driven Adaptive Long-Context Reasoning with Fact-based Hypergraph (Tao et al., Findings 2026)

ACL

Wenbiao Tao, Yuanfu Wang, Yunshi Lan, and Chao Yang. 2026. MemPulse: Memory Pulse-Driven Adaptive Long-Context Reasoning with Fact-based Hypergraph. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 19960–19975, Budapest, Hungary. Association for Computational Linguistics.