@inproceedings{wu-etal-2026-ase,
title = "{ASE}-{MCTS}: Asynchronous Self-Evaluated {M}onte {C}arlo Tree Search for Efficient {LLM} Reasoning",
author = "Wu, Yang and
Liu, Yuyang and
Zhang, Zhicheng and
Zheng, Xiaolong",
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.973/",
pages = "20572--20591",
ISBN = "979-8-89176-462-0",
abstract = "Monte Carlo Tree Search (MCTS) is a promising test-time method for improving LLMs on hard reasoning problems, where correct trajectories are often sparse. Self-evaluated MCTS is attractive because it avoids external reward models, verifiers, and stronger judges, but it faces a central paradox: MCTS depends on reliable intermediate rewards, while LLM self-evaluation is noisy and unstable. We propose ASE-MCTS, an Asynchronous Self-Evaluated MCTS framework. ASE-MCTS uses search-oriented reward analysis to derive an effective composition of rollout, process, and pairwise rewards from their global and local search roles. It further combines flexible search-space control with dependency-aware asynchronous execution, reducing redundant exploration and latency. Experiments on mathematical and scientific reasoning benchmarks show that ASE-MCTS improves reasoning without external supervision, especially on hard sparse-trajectory problems, and achieves up to a 6{\texttimes} wall-clock speedup over Sync-MCTS in the branch-factor scalability experiment."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2026-ase">
<titleInfo>
<title>ASE-MCTS: Asynchronous Self-Evaluated Monte Carlo Tree Search for Efficient LLM Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuyang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhicheng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaolong</namePart>
<namePart type="family">Zheng</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>Monte Carlo Tree Search (MCTS) is a promising test-time method for improving LLMs on hard reasoning problems, where correct trajectories are often sparse. Self-evaluated MCTS is attractive because it avoids external reward models, verifiers, and stronger judges, but it faces a central paradox: MCTS depends on reliable intermediate rewards, while LLM self-evaluation is noisy and unstable. We propose ASE-MCTS, an Asynchronous Self-Evaluated MCTS framework. ASE-MCTS uses search-oriented reward analysis to derive an effective composition of rollout, process, and pairwise rewards from their global and local search roles. It further combines flexible search-space control with dependency-aware asynchronous execution, reducing redundant exploration and latency. Experiments on mathematical and scientific reasoning benchmarks show that ASE-MCTS improves reasoning without external supervision, especially on hard sparse-trajectory problems, and achieves up to a 6× wall-clock speedup over Sync-MCTS in the branch-factor scalability experiment.</abstract>
<identifier type="citekey">wu-etal-2026-ase</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.973/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>20572</start>
<end>20591</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ASE-MCTS: Asynchronous Self-Evaluated Monte Carlo Tree Search for Efficient LLM Reasoning
%A Wu, Yang
%A Liu, Yuyang
%A Zhang, Zhicheng
%A Zheng, Xiaolong
%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 wu-etal-2026-ase
%X Monte Carlo Tree Search (MCTS) is a promising test-time method for improving LLMs on hard reasoning problems, where correct trajectories are often sparse. Self-evaluated MCTS is attractive because it avoids external reward models, verifiers, and stronger judges, but it faces a central paradox: MCTS depends on reliable intermediate rewards, while LLM self-evaluation is noisy and unstable. We propose ASE-MCTS, an Asynchronous Self-Evaluated MCTS framework. ASE-MCTS uses search-oriented reward analysis to derive an effective composition of rollout, process, and pairwise rewards from their global and local search roles. It further combines flexible search-space control with dependency-aware asynchronous execution, reducing redundant exploration and latency. Experiments on mathematical and scientific reasoning benchmarks show that ASE-MCTS improves reasoning without external supervision, especially on hard sparse-trajectory problems, and achieves up to a 6× wall-clock speedup over Sync-MCTS in the branch-factor scalability experiment.
%U https://aclanthology.org/2026.findings-emnlp.973/
%P 20572-20591
Markdown (Informal)
[ASE-MCTS: Asynchronous Self-Evaluated Monte Carlo Tree Search for Efficient LLM Reasoning](https://aclanthology.org/2026.findings-emnlp.973/) (Wu et al., Findings 2026)
ACL