Merge pull request #75 from GGLAB-KU/74-contentadd-treethink

Refactor code structure for improved readability and maintainability

Author: fattahsafa

_bibliography/papers.bib

@@ -1,5 +1,18 @@
 ---
 ---
+@misc{akbudak2026treethink,
+      abbr = {arXiv},
+      bibtex_show  = {true},
+      pdf={2607.11258v1.pdf},
+      title={TreeThink: A Modular Tree Search Library for Mathematical Reasoning with LLMs},
+      author={Burak S. Akbudak and Zeynel A. Uluşan and Can S. Erer and Gözde Gül Şahin},
+      year={2026},
+      eprint={2607.11258},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2607.11258},
+      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 6.3x 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/.}
+}
 @misc{ulusan2026formalrewardbench,
       abbr = {arXiv},
       bibtex_show  = {true},

_news/2026-07-13-paper-arxiv.md

@@ -0,0 +1,14 @@
+---
+layout: post
+date: 2026-07-13
+inline: true
+---
+
+Introducing TreeThink: an open-source Python library combining LLM generation with symbolic tree search for neural theorem proving!
+
+***
+Our paper entitled [TreeThink: A Modular Tree Search Library for Mathematical Reasoning with LLMs]({{ '/assets/pdf/2607.11258v1.pdf' | relative_url }}) is available on [arXiv](https://arxiv.org/abs/2607.11258). We introduce TreeThink, an open-source Python library for modular, fully asynchronous tree search in neural theorem proving, supporting Lean 4, Rocq, and Isabelle/HOL. Check out the [package](https://pypi.org/project/treethink/) and [code](https://github.com/GGLAB-KU/treethink)!
+
+<div style="text-align: center;">
+    <img title="TreeThink tree search process" alt="TreeThink tree search process: Select, Expand, Evaluate, Verify" src="{{ '/assets/img/news/treethink-figure1.png' | relative_url }}" style="max-width: 500px; height: auto; width: 100%;">
+</div>