@inproceedings{akbudak-etal-2026-treethink,
title = "{T}ree{T}hink: A Modular Tree Search Library for Mathematical Reasoning with {LLM}s",
author = {Akbudak, Burak Sina and
Ulu{\c{s}}an, Zeynel Abidin and
Erer, Salih Can and
{\c{S}}ahin, G{\"o}zde G{\"u}l},
editor = "Agrawal, Sweta and
Abad, Alberto",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-demos.57/",
pages = "593--603",
ISBN = "979-8-89176-461-3",
abstract = "Tree search algorithms enable systematic exploration of the proof space in neural theorem proving. Existing LLM tree search libraries primarily target natural language reasoning and do not provide native integration with formal verifiers, while theorem proving systems often rely on task-specific search implementations. We introduce TreeThink, an open-source Python library for modular, fully asynchronous tree search in neural theorem proving. It integrates established tree search methods with vLLM-based inference pipelines and diverse node evaluation techniques, ranging from lightweight heuristics to neural evaluators. We support Lean{~}4, Rocq, and Isabelle/HOL alongside natural language. It connects directly to each language{'}s Read-Eval-Print Loop (REPL) server for real-time verification and proof state extraction. We evaluate TreeThink on miniF2F and MATH500, demonstrating cross-language formal proof search, natural language reasoning support, and up to 8.0$\times$ wall-clock speedup from asynchronous execution. Source code is released under the MIT license at https://github.com/GGLAB-KU/treethink, and the library is accessible as a downloadable package at https://pypi.org/project/treethink/."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="akbudak-etal-2026-treethink">
<titleInfo>
<title>TreeThink: A Modular Tree Search Library for Mathematical Reasoning with LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Burak</namePart>
<namePart type="given">Sina</namePart>
<namePart type="family">Akbudak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeynel</namePart>
<namePart type="given">Abidin</namePart>
<namePart type="family">Uluşan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salih</namePart>
<namePart type="given">Can</namePart>
<namePart type="family">Erer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gözde</namePart>
<namePart type="given">Gül</namePart>
<namePart type="family">Şahin</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: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sweta</namePart>
<namePart type="family">Agrawal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Abad</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">979-8-89176-461-3</identifier>
</relatedItem>
<abstract>Tree search algorithms enable systematic exploration of the proof space in neural theorem proving. Existing LLM tree search libraries primarily target natural language reasoning and do not provide native integration with formal verifiers, while theorem proving systems often rely on task-specific search implementations. We introduce TreeThink, an open-source Python library for modular, fully asynchronous tree search in neural theorem proving. It integrates established tree search methods with vLLM-based inference pipelines and diverse node evaluation techniques, ranging from lightweight heuristics to neural evaluators. We support Lean 4, Rocq, and Isabelle/HOL alongside natural language. It connects directly to each language’s Read-Eval-Print Loop (REPL) server for real-time verification and proof state extraction. We evaluate TreeThink on miniF2F and MATH500, demonstrating cross-language formal proof search, natural language reasoning support, and up to 8.0\times wall-clock speedup from asynchronous execution. Source code is released under the MIT license at https://github.com/GGLAB-KU/treethink, and the library is accessible as a downloadable package at https://pypi.org/project/treethink/.</abstract>
<identifier type="citekey">akbudak-etal-2026-treethink</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-demos.57/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>593</start>
<end>603</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TreeThink: A Modular Tree Search Library for Mathematical Reasoning with LLMs
%A Akbudak, Burak Sina
%A Uluşan, Zeynel Abidin
%A Erer, Salih Can
%A Şahin, Gözde Gül
%Y Agrawal, Sweta
%Y Abad, Alberto
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-461-3
%F akbudak-etal-2026-treethink
%X Tree search algorithms enable systematic exploration of the proof space in neural theorem proving. Existing LLM tree search libraries primarily target natural language reasoning and do not provide native integration with formal verifiers, while theorem proving systems often rely on task-specific search implementations. We introduce TreeThink, an open-source Python library for modular, fully asynchronous tree search in neural theorem proving. It integrates established tree search methods with vLLM-based inference pipelines and diverse node evaluation techniques, ranging from lightweight heuristics to neural evaluators. We support Lean 4, Rocq, and Isabelle/HOL alongside natural language. It connects directly to each language’s Read-Eval-Print Loop (REPL) server for real-time verification and proof state extraction. We evaluate TreeThink on miniF2F and MATH500, demonstrating cross-language formal proof search, natural language reasoning support, and up to 8.0\times wall-clock speedup from asynchronous execution. Source code is released under the MIT license at https://github.com/GGLAB-KU/treethink, and the library is accessible as a downloadable package at https://pypi.org/project/treethink/.
%U https://aclanthology.org/2026.emnlp-demos.57/
%P 593-603
Markdown (Informal)
[TreeThink: A Modular Tree Search Library for Mathematical Reasoning with LLMs](https://aclanthology.org/2026.emnlp-demos.57/) (Akbudak et al., EMNLP 2026)
ACL