<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2026-adamempip">
    <titleInfo>
        <title>AdaMemPIP: Adaptive Memory Pipeline Orchestration for LLM Agents</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Huicheng</namePart>
        <namePart type="family">Huang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaohui</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yuanning</namePart>
        <namePart type="family">Cui</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zequn</namePart>
        <namePart type="family">Sun</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wei</namePart>
        <namePart type="family">Hu</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 model (LLM) agents increasingly depend on external memory to support long-horizon interaction. Yet many current memory systems still rely on largely fixed default rules once their pipelines are configured. They often apply the same extraction, retrieval, and evidence-organization choices across inputs. This is restrictive. Different memory needs require different choices. We propose AdaMemPIP, an adaptive memory orchestration framework for LLM agents. AdaMemPIP uses an LLM to route both memory storage and memory usage. For storage, it selects extractors for each new batch of dialogue records and writes the extracted items to matched memory libraries. For usage, it selects retrieval methods, target libraries, and organization strategies for each query, then executes the resulting pipeline. The framework is also extensible: new extractors, retrievers, stores, and organizers can be added without changing the overall control logic. This makes AdaMemPIP a flexible framework to long-term agent memory.</abstract>
    <identifier type="citekey">huang-etal-2026-adamempip</identifier>
    <identifier type="doi">10.18653/2026.findings-emnlp.1118</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.1118/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>23684</start>
            <end>23693</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T AdaMemPIP: Adaptive Memory Pipeline Orchestration for LLM Agents
%A Huang, Huicheng
%A Zhang, Xiaohui
%A Cui, Yuanning
%A Sun, Zequn
%A Hu, Wei
%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 huang-etal-2026-adamempip
%X Large language model (LLM) agents increasingly depend on external memory to support long-horizon interaction. Yet many current memory systems still rely on largely fixed default rules once their pipelines are configured. They often apply the same extraction, retrieval, and evidence-organization choices across inputs. This is restrictive. Different memory needs require different choices. We propose AdaMemPIP, an adaptive memory orchestration framework for LLM agents. AdaMemPIP uses an LLM to route both memory storage and memory usage. For storage, it selects extractors for each new batch of dialogue records and writes the extracted items to matched memory libraries. For usage, it selects retrieval methods, target libraries, and organization strategies for each query, then executes the resulting pipeline. The framework is also extensible: new extractors, retrievers, stores, and organizers can be added without changing the overall control logic. This makes AdaMemPIP a flexible framework to long-term agent memory.
%R 10.18653/2026.findings-emnlp.1118
%U https://aclanthology.org/2026.findings-emnlp.1118/
%U https://doi.org/10.18653/2026.findings-emnlp.1118
%P 23684-23693

Markdown (Informal)

[AdaMemPIP: Adaptive Memory Pipeline Orchestration for LLM Agents](https://aclanthology.org/2026.findings-emnlp.1118/) (Huang et al., Findings 2026)

• AdaMemPIP: Adaptive Memory Pipeline Orchestration for LLM Agents (Huang et al., Findings 2026)

ACL

• Huicheng Huang, Xiaohui Zhang, Yuanning Cui, Zequn Sun, and Wei Hu. 2026. AdaMemPIP: Adaptive Memory Pipeline Orchestration for LLM Agents. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 23684–23693, Budapest, Hungary. Association for Computational Linguistics.