<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2026-online">
    <titleInfo>
        <title>Online Strategic Reasoning for LLM-Based Negotiation via Opponent-Aware Monte Carlo Tree Search</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Chen-Cheng</namePart>
        <namePart type="family">Huang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yi-Cheng</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hung-Lin</namePart>
        <namePart type="family">Hu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yi-Ren</namePart>
        <namePart type="family">Yeh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chu-song</namePart>
        <namePart type="family">Chen</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>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>Large language models (LLMs) have shown strong reasoning abilities in mathematical reasoning, commonsense reasoning, and code generation. However, negotiation requires interactive reasoning, where each action can influence the opponent’s future behavior. Agents must therefore look beyond the current dialogue state and consider the long-term effects of their actions. Existing LLM-based negotiation agents often rely on prompting or fine-tuning from self-play trajectories. These methods can produce fluent responses and help models learn useful bargaining patterns. Yet at decision time, they often remain reactive, responding mainly to the current dialogue without reasoning about how different actions may shape future negotiation paths. We introduce an online strategic reasoning method that combines Monte Carlo Tree Search (MCTS)-based lookahead planning with opponent simulation. Before responding, our agent uses a proxy opponent agent to simulate future interactions and evaluate candidate strategies by their expected long-term outcomes. To make opponent simulation more precise, we proposed a Theory-of-Mind-inspired opponent modeling module that infers latent opponent attributes from dialogue history and conditions the proxy opponent agent during search. Experiments on CraigslistBargain and A2A-NT show that our method improves negotiation efficiency and profitability.</abstract>
    <identifier type="citekey">huang-etal-2026-online</identifier>
    <identifier type="doi">10.18653/2026.findings-emnlp.2277</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.2277/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>48740</start>
            <end>48756</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Online Strategic Reasoning for LLM-Based Negotiation via Opponent-Aware Monte Carlo Tree Search
%A Huang, Chen-Cheng
%A Wang, Yi-Cheng
%A Hu, Hung-Lin
%A Yeh, Yi-Ren
%A Chen, Chu-song
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F huang-etal-2026-online
%X Large language models (LLMs) have shown strong reasoning abilities in mathematical reasoning, commonsense reasoning, and code generation. However, negotiation requires interactive reasoning, where each action can influence the opponent’s future behavior. Agents must therefore look beyond the current dialogue state and consider the long-term effects of their actions. Existing LLM-based negotiation agents often rely on prompting or fine-tuning from self-play trajectories. These methods can produce fluent responses and help models learn useful bargaining patterns. Yet at decision time, they often remain reactive, responding mainly to the current dialogue without reasoning about how different actions may shape future negotiation paths. We introduce an online strategic reasoning method that combines Monte Carlo Tree Search (MCTS)-based lookahead planning with opponent simulation. Before responding, our agent uses a proxy opponent agent to simulate future interactions and evaluate candidate strategies by their expected long-term outcomes. To make opponent simulation more precise, we proposed a Theory-of-Mind-inspired opponent modeling module that infers latent opponent attributes from dialogue history and conditions the proxy opponent agent during search. Experiments on CraigslistBargain and A2A-NT show that our method improves negotiation efficiency and profitability.
%R 10.18653/2026.findings-emnlp.2277
%U https://aclanthology.org/2026.findings-emnlp.2277/
%U https://doi.org/10.18653/2026.findings-emnlp.2277
%P 48740-48756

Markdown (Informal)

[Online Strategic Reasoning for LLM-Based Negotiation via Opponent-Aware Monte Carlo Tree Search](https://aclanthology.org/2026.findings-emnlp.2277/) (Huang et al., Findings 2026)

• Online Strategic Reasoning for LLM-Based Negotiation via Opponent-Aware Monte Carlo Tree Search (Huang et al., Findings 2026)

ACL

• Chen-Cheng Huang, Yi-Cheng Wang, Hung-Lin Hu, Yi-Ren Yeh, and Chu-song Chen. 2026. Online Strategic Reasoning for LLM-Based Negotiation via Opponent-Aware Monte Carlo Tree Search. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 48740–48756, Budapest, Hungary. Association for Computational Linguistics.