<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-2026-neuro">
    <titleInfo>
        <title>Neuro-Symbolic Agentic Reinforcement Learning for Long-Term Original Character Companionship and Interaction</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zhenhan</namePart>
        <namePart type="family">Huang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Maria</namePart>
            <namePart type="family">Liakata</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Viviane</namePart>
            <namePart type="given">P</namePart>
            <namePart type="family">Moreira</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jiajun</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Jurgens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-391-3</identifier>
    </relatedItem>
    <abstract>As human-agent interaction (HAI) evolves toward long-term social companionship, users expect *Original Character (OC)* agents to maintain a consistent persona, manage shared memories, and adapt to ever-changing preferences. However, LLM-based agents optimized by prompting or SFT exhibit a generalization gap: they behave as myopic instruction followers, leading to cascading errors in multi-turn interactions. For the agents to learn trajectory-level value functions that enable farsighted decision-making, we propose the NSARL framework, which formalizes OC companion agents’ interactions as a POMDP and decomposes the agent into three sub-policies (Router, Memory, and Persona), optimized via closed-loop RL from AI feedback (RLAIF) with verifiable rewards in a graph-constrained action space. Our preliminary experiments indicate a trade-off: SFT yields stronger persona generation, while NSARL improves structural logic, through conservative strategies (e.g., over-routing) that increase workflow completeness, advocating for a hybrid deployment strategy.</abstract>
    <identifier type="citekey">huang-2026-neuro</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-short.44/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>530</start>
            <end>539</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Neuro-Symbolic Agentic Reinforcement Learning for Long-Term Original Character Companionship and Interaction
%A Huang, Zhenhan
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-391-3
%F huang-2026-neuro
%X As human-agent interaction (HAI) evolves toward long-term social companionship, users expect *Original Character (OC)* agents to maintain a consistent persona, manage shared memories, and adapt to ever-changing preferences. However, LLM-based agents optimized by prompting or SFT exhibit a generalization gap: they behave as myopic instruction followers, leading to cascading errors in multi-turn interactions. For the agents to learn trajectory-level value functions that enable farsighted decision-making, we propose the NSARL framework, which formalizes OC companion agents’ interactions as a POMDP and decomposes the agent into three sub-policies (Router, Memory, and Persona), optimized via closed-loop RL from AI feedback (RLAIF) with verifiable rewards in a graph-constrained action space. Our preliminary experiments indicate a trade-off: SFT yields stronger persona generation, while NSARL improves structural logic, through conservative strategies (e.g., over-routing) that increase workflow completeness, advocating for a hybrid deployment strategy.
%U https://aclanthology.org/2026.acl-short.44/
%P 530-539

Markdown (Informal)

[Neuro-Symbolic Agentic Reinforcement Learning for Long-Term Original Character Companionship and Interaction](https://aclanthology.org/2026.acl-short.44/) (Huang, ACL 2026)

• Neuro-Symbolic Agentic Reinforcement Learning for Long-Term Original Character Companionship and Interaction (Huang, ACL 2026)

ACL

• Zhenhan Huang. 2026. Neuro-Symbolic Agentic Reinforcement Learning for Long-Term Original Character Companionship and Interaction. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 530–539, San Diego, California, United States. Association for Computational Linguistics.