@inproceedings{huang-etal-2026-mcts,
title = "{MCTS}-Debater: {M}onte {C}arlo Tree Search based Rebuttal Generation for Competitive Debate",
author = "Huang, Xiaoyong and
Huang, Yuting and
Yue, Guanlan and
Wang, Hao and
Sun, Heli and
Wu, Jiaruo and
Wang, Zejun and
He, Liang",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.599/",
pages = "12640--12656",
ISBN = "979-8-89176-462-0",
abstract = "Competitive debate is a multi-turn, zero-sum adversarial task with opposing stances that requires debaters to anticipate opponents' counterarguments in real-time interactions and select strategies yielding long-term advantages. Existing large language model debate methods predominantly adopt a greedy generation paradigm that optimizes only the immediate effectiveness of the current rebuttal while lacking forward-looking planning for the overall debate trajectory. To address this limitation, we propose MCTS-Debater, a Monte Carlo Tree Search framework that models competitive debate as a Markov Decision Process. Rather than selecting a single locally optimal response, MCTS-Debater systematically simulates multi-step adversarial interactions under diverse rebuttal strategies, estimates their long-term expected win rates via tree search, and synthesizes the top-performing strategies into a coherent final rebuttal through multi-strategy fusion. Experimental results on the ORCHID and IQ2 datasets demonstrate that MCTS-Debater significantly outperforms existing baselines in logical validity, factual accuracy, and overall persuasiveness. Source code is provided in the supplementary material."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2026-mcts">
<titleInfo>
<title>MCTS-Debater: Monte Carlo Tree Search based Rebuttal Generation for Competitive Debate</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaoyong</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuting</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guanlan</namePart>
<namePart type="family">Yue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heli</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaruo</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zejun</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">He</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>Competitive debate is a multi-turn, zero-sum adversarial task with opposing stances that requires debaters to anticipate opponents’ counterarguments in real-time interactions and select strategies yielding long-term advantages. Existing large language model debate methods predominantly adopt a greedy generation paradigm that optimizes only the immediate effectiveness of the current rebuttal while lacking forward-looking planning for the overall debate trajectory. To address this limitation, we propose MCTS-Debater, a Monte Carlo Tree Search framework that models competitive debate as a Markov Decision Process. Rather than selecting a single locally optimal response, MCTS-Debater systematically simulates multi-step adversarial interactions under diverse rebuttal strategies, estimates their long-term expected win rates via tree search, and synthesizes the top-performing strategies into a coherent final rebuttal through multi-strategy fusion. Experimental results on the ORCHID and IQ2 datasets demonstrate that MCTS-Debater significantly outperforms existing baselines in logical validity, factual accuracy, and overall persuasiveness. Source code is provided in the supplementary material.</abstract>
<identifier type="citekey">huang-etal-2026-mcts</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.599/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>12640</start>
<end>12656</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MCTS-Debater: Monte Carlo Tree Search based Rebuttal Generation for Competitive Debate
%A Huang, Xiaoyong
%A Huang, Yuting
%A Yue, Guanlan
%A Wang, Hao
%A Sun, Heli
%A Wu, Jiaruo
%A Wang, Zejun
%A He, Liang
%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-mcts
%X Competitive debate is a multi-turn, zero-sum adversarial task with opposing stances that requires debaters to anticipate opponents’ counterarguments in real-time interactions and select strategies yielding long-term advantages. Existing large language model debate methods predominantly adopt a greedy generation paradigm that optimizes only the immediate effectiveness of the current rebuttal while lacking forward-looking planning for the overall debate trajectory. To address this limitation, we propose MCTS-Debater, a Monte Carlo Tree Search framework that models competitive debate as a Markov Decision Process. Rather than selecting a single locally optimal response, MCTS-Debater systematically simulates multi-step adversarial interactions under diverse rebuttal strategies, estimates their long-term expected win rates via tree search, and synthesizes the top-performing strategies into a coherent final rebuttal through multi-strategy fusion. Experimental results on the ORCHID and IQ2 datasets demonstrate that MCTS-Debater significantly outperforms existing baselines in logical validity, factual accuracy, and overall persuasiveness. Source code is provided in the supplementary material.
%U https://aclanthology.org/2026.findings-emnlp.599/
%P 12640-12656
Markdown (Informal)
[MCTS-Debater: Monte Carlo Tree Search based Rebuttal Generation for Competitive Debate](https://aclanthology.org/2026.findings-emnlp.599/) (Huang et al., Findings 2026)
ACL
- Xiaoyong Huang, Yuting Huang, Guanlan Yue, Hao Wang, Heli Sun, Jiaruo Wu, Zejun Wang, and Liang He. 2026. MCTS-Debater: Monte Carlo Tree Search based Rebuttal Generation for Competitive Debate. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 12640–12656, Budapest, Hungary. Association for Computational Linguistics.