<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2026-testing">
    <titleInfo>
        <title>Testing Behavioral Adaptation in Repeated Interactions Between LLM Agents</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Lixin</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yixuan</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiankun</namePart>
        <namePart type="family">Lin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yutian</namePart>
        <namePart type="family">Lu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shiguang</namePart>
        <namePart type="family">NI</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 Second Workshop for REsearch on Agent Language Models (REALM 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ehsan</namePart>
            <namePart type="family">Kamalloo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nicolas</namePart>
            <namePart type="family">Gontier</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nikolai</namePart>
            <namePart type="family">Rozanov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Maryam</namePart>
            <namePart type="family">Hashemzadeh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Akhil</namePart>
            <namePart type="family">Arora</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">979-8-89176-485-9</identifier>
    </relatedItem>
    <abstract>High aggregate scores can make language agents appear socially responsive even when they merely repeat a prompt-conditioned action. We introduce an identifiability-first framework that separates observed outcomes from evidence of adaptation. Across 3,465 released iterated-prisoner’s-dilemma simulations, 94.5% never change joint regime, leaving reciprocity largely unidentifiable. Controlled histories across nine models reveal opponent-dependent responses that vary substantially across equivalent interfaces. The released checkpoints have the smallest opponent-recency effects. Only the intervention cohort shows reliable propagation after a scripted defection. The diagnostic transfers to longer histories, a multiplayer game, and released-interface wrappers, although model rankings do not. Outcome-only evaluation conflates regime selection with adaptive behavior. Separating opportunity, response, and robustness prevents stable outcomes from being mistaken for social dynamics.</abstract>
    <identifier type="citekey">liu-etal-2026-testing</identifier>
    <location>
        <url>https://aclanthology.org/2026.realm-1.67/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>973</start>
            <end>985</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Testing Behavioral Adaptation in Repeated Interactions Between LLM Agents
%A Liu, Lixin
%A Li, Yixuan
%A Lin, Xiankun
%A Lu, Yutian
%A NI, Shiguang
%Y Kamalloo, Ehsan
%Y Gontier, Nicolas
%Y Rozanov, Nikolai
%Y Hashemzadeh, Maryam
%Y Arora, Akhil
%S Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-485-9
%F liu-etal-2026-testing
%X High aggregate scores can make language agents appear socially responsive even when they merely repeat a prompt-conditioned action. We introduce an identifiability-first framework that separates observed outcomes from evidence of adaptation. Across 3,465 released iterated-prisoner’s-dilemma simulations, 94.5% never change joint regime, leaving reciprocity largely unidentifiable. Controlled histories across nine models reveal opponent-dependent responses that vary substantially across equivalent interfaces. The released checkpoints have the smallest opponent-recency effects. Only the intervention cohort shows reliable propagation after a scripted defection. The diagnostic transfers to longer histories, a multiplayer game, and released-interface wrappers, although model rankings do not. Outcome-only evaluation conflates regime selection with adaptive behavior. Separating opportunity, response, and robustness prevents stable outcomes from being mistaken for social dynamics.
%U https://aclanthology.org/2026.realm-1.67/
%P 973-985

Markdown (Informal)

[Testing Behavioral Adaptation in Repeated Interactions Between LLM Agents](https://aclanthology.org/2026.realm-1.67/) (Liu et al., REALM 2026)

• Testing Behavioral Adaptation in Repeated Interactions Between LLM Agents (Liu et al., REALM 2026)

ACL

• Lixin Liu, Yixuan Li, Xiankun Lin, Yutian Lu, and Shiguang NI. 2026. Testing Behavioral Adaptation in Repeated Interactions Between LLM Agents. In Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026), pages 973–985, Budapest, Hungary. Association for Computational Linguistics.