<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2026-tshmem">
    <titleInfo>
        <title>TSHMem: A Temporal-Semantic Hierarchical Memory Graph for Long-Term Conversational Agents</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Feiyang</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wenhao</namePart>
        <namePart type="family">Yu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Li</namePart>
        <namePart type="family">Xiang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Quanyu</namePart>
        <namePart type="family">Dai</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Irwin</namePart>
        <namePart type="family">King</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>Long-term conversational agents often face time-sensitive queries, requiring evidence that is both contextually relevant and valid for a specific time, event, or factual update. However, noisy temporal-entity cues, weak coupling between temporal anchors and retrieval paths, and sparse long-tail evidence often lead memory systems to retrieve semantically similar but temporally invalid or outdated evidence. We propose TSHMem, a Temporal-Semantic Hierarchical Memory Graph for long-term conversational agents. TSHMem addresses noisy conversational evidence by organizing dialogue turns, self-contained statements, hierarchical summaries, and entities into a heterogeneous memory graph. To connect temporal constraints with retrieval paths, it parses temporal intent, activates query-relevant entities, resolves event-referenced constraints, and injects temporal relevance into graph transition probabilities. It then combines time-aware structural propagation with semantic matching and hierarchical ranking to retrieve compact evidence that is temporally valid, contextually relevant, and robust to sparse long-tail memories. Experiments on LongMemEval S* and LoCoMo show that TSHMem consistently outperforms strong retrieval and memory-agent baselines, achieving 66.3% accuracy on LongMemEval S*, with an absolute gain of 18.6% over the strongest baseline while retrieving fewer evidence tokens.</abstract>
    <identifier type="citekey">xu-etal-2026-tshmem</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1034/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>23747</start>
            <end>23766</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T TSHMem: A Temporal-Semantic Hierarchical Memory Graph for Long-Term Conversational Agents
%A Xu, Feiyang
%A Yu, Wenhao
%A Xiang, Li
%A Dai, Quanyu
%A King, Irwin
%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 xu-etal-2026-tshmem
%X Long-term conversational agents often face time-sensitive queries, requiring evidence that is both contextually relevant and valid for a specific time, event, or factual update. However, noisy temporal-entity cues, weak coupling between temporal anchors and retrieval paths, and sparse long-tail evidence often lead memory systems to retrieve semantically similar but temporally invalid or outdated evidence. We propose TSHMem, a Temporal-Semantic Hierarchical Memory Graph for long-term conversational agents. TSHMem addresses noisy conversational evidence by organizing dialogue turns, self-contained statements, hierarchical summaries, and entities into a heterogeneous memory graph. To connect temporal constraints with retrieval paths, it parses temporal intent, activates query-relevant entities, resolves event-referenced constraints, and injects temporal relevance into graph transition probabilities. It then combines time-aware structural propagation with semantic matching and hierarchical ranking to retrieve compact evidence that is temporally valid, contextually relevant, and robust to sparse long-tail memories. Experiments on LongMemEval S* and LoCoMo show that TSHMem consistently outperforms strong retrieval and memory-agent baselines, achieving 66.3% accuracy on LongMemEval S*, with an absolute gain of 18.6% over the strongest baseline while retrieving fewer evidence tokens.
%U https://aclanthology.org/2026.emnlp-main.1034/
%P 23747-23766

Markdown (Informal)

[TSHMem: A Temporal-Semantic Hierarchical Memory Graph for Long-Term Conversational Agents](https://aclanthology.org/2026.emnlp-main.1034/) (Xu et al., EMNLP 2026)

• TSHMem: A Temporal-Semantic Hierarchical Memory Graph for Long-Term Conversational Agents (Xu et al., EMNLP 2026)

ACL

• Feiyang Xu, Wenhao Yu, Li Xiang, Quanyu Dai, and Irwin King. 2026. TSHMem: A Temporal-Semantic Hierarchical Memory Graph for Long-Term Conversational Agents. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 23747–23766, Budapest, Hungary. Association for Computational Linguistics.