<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="o-neill-etal-2026-cooperate">
    <titleInfo>
        <title>Cooperate to Compete: Strategic Coordination in Multi-Agent Conquest</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Abigail</namePart>
        <namePart type="family">O’Neill</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alan</namePart>
        <namePart type="family">Zhu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mihran</namePart>
        <namePart type="family">Miroyan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Narges</namePart>
        <namePart type="family">Norouzi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Joseph</namePart>
        <namePart type="given">E</namePart>
        <namePart type="family">Gonzalez</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>Language Model (LM)-based agents remain challenging to evaluate systematically in mixed-motive settings where agents must leverage short-term cooperation for long-term competitive goals (e.g., multi-party politics). We introduce Cooperate to Compete (C2C), a multi-agent environment where players can engage in private negotiations while competing to be the first to achieve their secret objective. Players have asymmetric objectives and negotiations are non-binding, allowing alliances to form and break as players’ short-term interests align and diverge. We run AI-only games and conduct a user study pitting human players against AI opponents. We find that humans favor lower-complexity deals and talk to more unique partners over the course of the game. We also find that humans are more aggressive negotiators, closing deals only 73.5% of the time compared to 94.0% for LM-based agents. Interventions inspired by these findings shift agent negotiation behavior and can raise win rates from 22.2% to 32.7%, demonstrating that language coordination strategies in C2C substantially alter negotiation dynamics. We run over 1,300 games with over 20,000 private conversations totaling over 180,000 player actions. By combining multi-party, long-horizon play with partial observability, asymmetric objectives, and non-binding negotiations, C2C provides a controlled, gamified testbed for studying strategic coordination in LM-based agents.</abstract>
    <identifier type="citekey">o-neill-etal-2026-cooperate</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.609/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>14019</start>
            <end>14039</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Cooperate to Compete: Strategic Coordination in Multi-Agent Conquest
%A O’Neill, Abigail
%A Zhu, Alan
%A Miroyan, Mihran
%A Norouzi, Narges
%A Gonzalez, Joseph E.
%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 o-neill-etal-2026-cooperate
%X Language Model (LM)-based agents remain challenging to evaluate systematically in mixed-motive settings where agents must leverage short-term cooperation for long-term competitive goals (e.g., multi-party politics). We introduce Cooperate to Compete (C2C), a multi-agent environment where players can engage in private negotiations while competing to be the first to achieve their secret objective. Players have asymmetric objectives and negotiations are non-binding, allowing alliances to form and break as players’ short-term interests align and diverge. We run AI-only games and conduct a user study pitting human players against AI opponents. We find that humans favor lower-complexity deals and talk to more unique partners over the course of the game. We also find that humans are more aggressive negotiators, closing deals only 73.5% of the time compared to 94.0% for LM-based agents. Interventions inspired by these findings shift agent negotiation behavior and can raise win rates from 22.2% to 32.7%, demonstrating that language coordination strategies in C2C substantially alter negotiation dynamics. We run over 1,300 games with over 20,000 private conversations totaling over 180,000 player actions. By combining multi-party, long-horizon play with partial observability, asymmetric objectives, and non-binding negotiations, C2C provides a controlled, gamified testbed for studying strategic coordination in LM-based agents.
%U https://aclanthology.org/2026.emnlp-main.609/
%P 14019-14039

Markdown (Informal)

[Cooperate to Compete: Strategic Coordination in Multi-Agent Conquest](https://aclanthology.org/2026.emnlp-main.609/) (O’Neill et al., EMNLP 2026)

• Cooperate to Compete: Strategic Coordination in Multi-Agent Conquest (O’Neill et al., EMNLP 2026)

ACL

• Abigail O’Neill, Alan Zhu, Mihran Miroyan, Narges Norouzi, and Joseph E. Gonzalez. 2026. Cooperate to Compete: Strategic Coordination in Multi-Agent Conquest. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 14019–14039, Budapest, Hungary. Association for Computational Linguistics.