<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liao-etal-2026-retrieval">
    <titleInfo>
        <title>From Retrieval to Reconstruction: Constructing Evolvable Cognitive Memory for Long-term Dialogue</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zirui</namePart>
        <namePart type="family">Liao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">ZhengXian</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhuohong</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yunyao</namePart>
        <namePart type="family">Yu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaoyu</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yifan</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Haoqian</namePart>
        <namePart type="family">Wang</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 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Large Language Models (LLMs) serving as long-term personal companions require memory systems that support complex reasoning over extended dialogues. However, existing Retrieval-Augmented Generation (RAG) frameworks treat memory as passive storage, suffering from semantic collapse—where subjective beliefs and objective facts become indistinguishable—and rigid navigation that fails to connect dispersed information. We introduce CogMem, a cognitive memory architecture that reconstructs dialogue context through explicit structure. CogMem organizes memory via the PEC²F (Person-Event-Concept-Claim-Fact) schema, using dedicated Claim nodes to separate subjective attributions from objective records and prevent information contamination. Rather than static retrieval, CogMem employs a deterministic controller with four cognitive operators (anchoring, traversal, intersection, evidence grounding) that dynamically navigate the graph based on query intent. Comprehensive evaluation on LoCoMo and LongMemEval shows that CogMem achieves state-of-the-art performance across all task categories, surpassing neural memory systems and graph retrieval methods. These results demonstrate that structured cognitive modeling significantly improves long-term memory accuracy and robustness compared to passive vector retrieval.</abstract>
    <identifier type="citekey">liao-etal-2026-retrieval</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1014/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>23325</start>
            <end>23345</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T From Retrieval to Reconstruction: Constructing Evolvable Cognitive Memory for Long-term Dialogue
%A Liao, Zirui
%A Wu, ZhengXian
%A Chen, Zhuohong
%A Yu, Yunyao
%A Liu, Xiaoyu
%A Xu, Yifan
%A Wang, Haoqian
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F liao-etal-2026-retrieval
%X Large Language Models (LLMs) serving as long-term personal companions require memory systems that support complex reasoning over extended dialogues. However, existing Retrieval-Augmented Generation (RAG) frameworks treat memory as passive storage, suffering from semantic collapse—where subjective beliefs and objective facts become indistinguishable—and rigid navigation that fails to connect dispersed information. We introduce CogMem, a cognitive memory architecture that reconstructs dialogue context through explicit structure. CogMem organizes memory via the PEC²F (Person-Event-Concept-Claim-Fact) schema, using dedicated Claim nodes to separate subjective attributions from objective records and prevent information contamination. Rather than static retrieval, CogMem employs a deterministic controller with four cognitive operators (anchoring, traversal, intersection, evidence grounding) that dynamically navigate the graph based on query intent. Comprehensive evaluation on LoCoMo and LongMemEval shows that CogMem achieves state-of-the-art performance across all task categories, surpassing neural memory systems and graph retrieval methods. These results demonstrate that structured cognitive modeling significantly improves long-term memory accuracy and robustness compared to passive vector retrieval.
%U https://aclanthology.org/2026.emnlp-main.1014/
%P 23325-23345

Markdown (Informal)

[From Retrieval to Reconstruction: Constructing Evolvable Cognitive Memory for Long-term Dialogue](https://aclanthology.org/2026.emnlp-main.1014/) (Liao et al., EMNLP 2026)

• From Retrieval to Reconstruction: Constructing Evolvable Cognitive Memory for Long-term Dialogue (Liao et al., EMNLP 2026)

ACL

• Zirui Liao, ZhengXian Wu, Zhuohong Chen, Yunyao Yu, Xiaoyu Liu, Yifan Xu, and Haoqian Wang. 2026. From Retrieval to Reconstruction: Constructing Evolvable Cognitive Memory for Long-term Dialogue. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 23325–23345, Budapest, Hungary. Association for Computational Linguistics.