<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2026-clasp">
    <titleInfo>
        <title>CLASP: A Closed-Loop Behavior Alignment Framework for Social Media Agent Simulation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Laisong</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shanfeng</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wei</namePart>
        <namePart type="family">Xie</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhenhua</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhenhao</namePart>
        <namePart type="family">Luo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Baosheng</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) provide a powerful foundation for social media simulation, but their utility is fundamentally limited by the accuracy of user behavior modeling. Existing LLM agents exhibit behavioral homogenization and fail to capture users’ inherent identities and evolving preferences. To address this, we propose CLASP, a closed-loop behavior alignment framework for social media agents. CLASP leverages explicit, dynamically refined personas to bridge users’ historical behaviors and subsequent agent actions, ensuring behavioral consistency and temporal adaptability. Our framework adopts a decoupled dual-model design to separate persona refinement from action generation. This design enables continual behavior alignment driven by action prediction discrepancies. To facilitate training and evaluation, we further construct BlueTrack, a large-scale Bluesky dataset that covers long-horizon and heterogeneous social behaviors with complete action elements. Extensive experiments demonstrate that CLASP outperforms baselines in behavioral alignment with real users. It improves the overall alignment quality by up to 31.8% and reduces its variance by 32.1% during long-sequence simulation. This work provides a practical reference for further exploration in realistic social media simulation.</abstract>
    <identifier type="citekey">li-etal-2026-clasp</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1426/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>32590</start>
            <end>32609</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T CLASP: A Closed-Loop Behavior Alignment Framework for Social Media Agent Simulation
%A Li, Laisong
%A Wang, Shanfeng
%A Xie, Wei
%A Wang, Zhenhua
%A Luo, Zhenhao
%A Wang, Baosheng
%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 li-etal-2026-clasp
%X Large language models (LLMs) provide a powerful foundation for social media simulation, but their utility is fundamentally limited by the accuracy of user behavior modeling. Existing LLM agents exhibit behavioral homogenization and fail to capture users’ inherent identities and evolving preferences. To address this, we propose CLASP, a closed-loop behavior alignment framework for social media agents. CLASP leverages explicit, dynamically refined personas to bridge users’ historical behaviors and subsequent agent actions, ensuring behavioral consistency and temporal adaptability. Our framework adopts a decoupled dual-model design to separate persona refinement from action generation. This design enables continual behavior alignment driven by action prediction discrepancies. To facilitate training and evaluation, we further construct BlueTrack, a large-scale Bluesky dataset that covers long-horizon and heterogeneous social behaviors with complete action elements. Extensive experiments demonstrate that CLASP outperforms baselines in behavioral alignment with real users. It improves the overall alignment quality by up to 31.8% and reduces its variance by 32.1% during long-sequence simulation. This work provides a practical reference for further exploration in realistic social media simulation.
%U https://aclanthology.org/2026.emnlp-main.1426/
%P 32590-32609

Markdown (Informal)

[CLASP: A Closed-Loop Behavior Alignment Framework for Social Media Agent Simulation](https://aclanthology.org/2026.emnlp-main.1426/) (Li et al., EMNLP 2026)

• CLASP: A Closed-Loop Behavior Alignment Framework for Social Media Agent Simulation (Li et al., EMNLP 2026)

ACL

• Laisong Li, Shanfeng Wang, Wei Xie, Zhenhua Wang, Zhenhao Luo, and Baosheng Wang. 2026. CLASP: A Closed-Loop Behavior Alignment Framework for Social Media Agent Simulation. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 32590–32609, Budapest, Hungary. Association for Computational Linguistics.