<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bian-etal-2026-membook">
    <titleInfo>
        <title>MemBook: A Hierarchical Reasoning-based Memory Framework for Hallucination-Resistant LLM Agents</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tongshu</namePart>
        <namePart type="family">Bian</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yunxin</namePart>
        <namePart type="family">li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhenran</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tianqi</namePart>
        <namePart type="family">Shi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Longyue</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Baotian</namePart>
        <namePart type="family">Hu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Min</namePart>
        <namePart type="family">Zhang</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 is a cornerstone of foundation model-based agents for ultra-long-term interaction. However, hallucinated or noisy information can accumulate inside memory systems and progressively contaminate downstream tasks. Existing systems face two key challenges: (1) memory construction mechanisms trade off between faithful recall and hallucination suppression; and (2) retrieval relies on shallow semantic similarity, failing to distinguish logically irrelevant memories. We propose **MemBook**, a hierarchical time-aware memory framework for hallucination-resistant agents. For memory construction, MemBook introduces a stateful memory stabilization mechanism that prevents hallucinated claims from being consolidated into persistent memory and organizes reliable memories into an evolving Session–Chapter–Memory Point hierarchy. For memory retrieval, MemBook performs reasoning-based hierarchical retrieval over this evolving memory book to identify temporally and logically relevant memories. Experiments on HaluMem-Medium, HaluMem-Long, and LongMemEval show that MemBook improves extraction quality and downstream performance while suppressing cross-stage hallucination propagation. Notably, MemBook remains stable under ultra-long contexts, outperforming GAM by absolute 19.57% QA accuracy improvement on HaluMem-Long.</abstract>
    <identifier type="citekey">bian-etal-2026-membook</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.1847/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>39444</start>
            <end>39470</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T MemBook: A Hierarchical Reasoning-based Memory Framework for Hallucination-Resistant LLM Agents
%A Bian, Tongshu
%A li, Yunxin
%A Xu, Zhenran
%A Shi, Tianqi
%A Wang, Longyue
%A Hu, Baotian
%A Zhang, Min
%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 bian-etal-2026-membook
%X Memory is a cornerstone of foundation model-based agents for ultra-long-term interaction. However, hallucinated or noisy information can accumulate inside memory systems and progressively contaminate downstream tasks. Existing systems face two key challenges: (1) memory construction mechanisms trade off between faithful recall and hallucination suppression; and (2) retrieval relies on shallow semantic similarity, failing to distinguish logically irrelevant memories. We propose **MemBook**, a hierarchical time-aware memory framework for hallucination-resistant agents. For memory construction, MemBook introduces a stateful memory stabilization mechanism that prevents hallucinated claims from being consolidated into persistent memory and organizes reliable memories into an evolving Session–Chapter–Memory Point hierarchy. For memory retrieval, MemBook performs reasoning-based hierarchical retrieval over this evolving memory book to identify temporally and logically relevant memories. Experiments on HaluMem-Medium, HaluMem-Long, and LongMemEval show that MemBook improves extraction quality and downstream performance while suppressing cross-stage hallucination propagation. Notably, MemBook remains stable under ultra-long contexts, outperforming GAM by absolute 19.57% QA accuracy improvement on HaluMem-Long.
%U https://aclanthology.org/2026.findings-emnlp.1847/
%P 39444-39470

Markdown (Informal)

[MemBook: A Hierarchical Reasoning-based Memory Framework for Hallucination-Resistant LLM Agents](https://aclanthology.org/2026.findings-emnlp.1847/) (Bian et al., Findings 2026)

• MemBook: A Hierarchical Reasoning-based Memory Framework for Hallucination-Resistant LLM Agents (Bian et al., Findings 2026)

ACL

• Tongshu Bian, Yunxin li, Zhenran Xu, Tianqi Shi, Longyue Wang, Baotian Hu, and Min Zhang. 2026. MemBook: A Hierarchical Reasoning-based Memory Framework for Hallucination-Resistant LLM Agents. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 39444–39470, Budapest, Hungary. Association for Computational Linguistics.