<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="madmoun-lahlou-2026-communication">
    <titleInfo>
        <title>Communication Enables Cooperation in LLM Agents: A Comparison with Curriculum-Based Approaches</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Hachem</namePart>
        <namePart type="family">Madmoun</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Salem</namePart>
        <namePart type="family">Lahlou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Vera</namePart>
            <namePart type="family">Demberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kentaro</namePart>
            <namePart type="family">Inui</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lluís</namePart>
            <namePart type="family">Marquez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Rabat, Morocco</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-381-4</identifier>
    </relatedItem>
    <abstract>Eliciting cooperation in multi-agent LLM systems is critical for AI alignment. We investigate two approaches: direct communication and curriculum learning. In a 4-player Stag Hunt, a one-word “cheap talk” channel increases cooperation from 0% to 48.3%, demonstrating communication as a robust coordination mechanism. In contrast, we find that curriculum learning is highly sensitive to design choices: our pedagogical curriculum through progressively complex games reduced agent payoffs by 27.4% in an Iterated Public Goods Game with Punishment. Qualitative analysis reveals that curricula emphasizing defection-equilibrium games can induce “learned pessimism” in agents. These findings suggest that for coordination problems, simple communication protocols may be more reliable than experience-based training, and that curriculum design for social dilemmas requires careful attention to the strategic lessons embedded in game sequences.</abstract>
    <identifier type="citekey">madmoun-lahlou-2026-communication</identifier>
    <location>
        <url>https://aclanthology.org/2026.eacl-short.23/</url>
    </location>
    <part>
        <date>2026-03</date>
        <extent unit="page">
            <start>307</start>
            <end>321</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Communication Enables Cooperation in LLM Agents: A Comparison with Curriculum-Based Approaches
%A Madmoun, Hachem
%A Lahlou, Salem
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-381-4
%F madmoun-lahlou-2026-communication
%X Eliciting cooperation in multi-agent LLM systems is critical for AI alignment. We investigate two approaches: direct communication and curriculum learning. In a 4-player Stag Hunt, a one-word “cheap talk” channel increases cooperation from 0% to 48.3%, demonstrating communication as a robust coordination mechanism. In contrast, we find that curriculum learning is highly sensitive to design choices: our pedagogical curriculum through progressively complex games reduced agent payoffs by 27.4% in an Iterated Public Goods Game with Punishment. Qualitative analysis reveals that curricula emphasizing defection-equilibrium games can induce “learned pessimism” in agents. These findings suggest that for coordination problems, simple communication protocols may be more reliable than experience-based training, and that curriculum design for social dilemmas requires careful attention to the strategic lessons embedded in game sequences.
%U https://aclanthology.org/2026.eacl-short.23/
%P 307-321

Markdown (Informal)

[Communication Enables Cooperation in LLM Agents: A Comparison with Curriculum-Based Approaches](https://aclanthology.org/2026.eacl-short.23/) (Madmoun & Lahlou, EACL 2026)

• Communication Enables Cooperation in LLM Agents: A Comparison with Curriculum-Based Approaches (Madmoun & Lahlou, EACL 2026)

ACL

• Hachem Madmoun and Salem Lahlou. 2026. Communication Enables Cooperation in LLM Agents: A Comparison with Curriculum-Based Approaches. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers), pages 307–321, Rabat, Morocco. Association for Computational Linguistics.