Elamur Research⌕
☰
home / papers / 2026 / ThinkBooster: A Unified Framework for Seamless Test-Time Scaling of LLM Reasoning

ThinkBooster: A Unified Framework for Seamless Test-Time Scaling of LLM Reasoning

Paper · 2026 · Vladislav Smirnov, Quang-Chieu Nguyen, Sergey Senichev et al.

Summary

Research on test-time compute (TTC) scaling for LLM reasoning is scattered. Methods are tested under different protocols, model setups and budgets. Most papers report accuracy but not cost, and released code is rarely ready for production. ThinkBooster addresses this with a single open-source framework (MIT license) built from three parts. The first is a modular Python library that offers TTC strategies and reasoning scorers through one API. The second is a benchmark that tracks quality together with compute, measured as theoretical TFLOPs and token counts. The third is an OpenAI-compatible proxy that adds a "Pro" reasoning mode to existing applications without changing their code. A visual debugger lets users browse reasoning trajectories, selection decisions and discarded branches.

In a pilot study on math and code, PRM-based scorers were strongest on math. On coding, cheap uncertainty-based scorers matched or beat PRMs, which suggests that PRMs trained mostly on math transfer poorly to code. This matters because researchers get a fair basis for comparing methods, while practitioners get a deployable way to trade compute for reliability.

Key points

  • The library implements nine TTC strategies drawn from over twenty publications. They include Best-of-N, majority voting, beam search (ToT), extended thinking, MUR, DeepConf online/offline, Phi-decoding and Uncertainty CoT.

  • Four scorer families are covered: PRMs, self-verification / LLM-as-a-judge, uncertainty and confidence scores via LM-Polygraph, and ReProbes.

  • Each method is labeled by three properties:

    • offline vs. online scoring;
    • white-box vs. black-box access;
    • whether the provider must support prefill.

    With closed APIs, only a black-box subset of methods is available.

  • Experiments used Qwen2.5-Math-7B on MATH-500, OlympiadBench and Gaokao 2023 EN, and Qwen3-8B on HumanEval-Plus. Beam search consumed much more compute and often trailed BoN, though combined with a PRM it scored highest on math. MUR combined with an uncertainty scorer was best on HumanEval+.

  • With gpt-oss-120b, Offline BoN guided by a PRM produced the following gains:

    • GPQA-Diamond: 70.3 → 72.2;
    • HumanEval+: 83.5 → 85.4;
    • KernelBench CUDA kernels: syntax 82 → 87 and correctness 26 → 30, while compilation slipped slightly from 65 to 64.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓National University of SingaporeSingapore · Singapore180 works · 34,304 citations🎓ETH ZurichZurich · Switzerland72 works · 5,176 citations🎓Imperial College LondonLondon · United Kingdom48 works · 12,181 citations🏢AccentureZurich · Switzerland6 works · 27 citations🎓Innopolis UniversityInnopolis · Russia5 works · 10 citations🏢Accenture (United States)New York · United States5 works · 261 citations

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksComputer Vision and Pattern Recognition · 2,869 works

🧭 Topics 2Research subjects and languages the work is about.Language models & pretraining · 3,320 worksReasoning · 1,426 works

Cite

Cite as Vladislav Smirnov, Quang-Chieu Nguyen, Sergey Senichev, Minh Ngoc Ta, Ekaterina Fadeeva, Artem Vazhentsev, Daria Galimzianova, Nikolai Rozanov, Viktor Mazanov, Jingwei Ni, Tianyi Wu, Igor Kiselev, Mrinmaya Sachan, Iryna Gurevych, Preslav Nakov, Timothy Baldwin and Artem Shelmanov. 2026. ThinkBooster: A Unified Framework for Seamless Test-Time Scaling of LLM Reasoning. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.acl-demo.70

@inproceedings{smirnov2026thinkbooster,
  title = {{ThinkBooster: A Unified Framework for Seamless Test-Time Scaling of LLM Reasoning}},
  author = {Vladislav Smirnov, Quang-Chieu Nguyen, Sergey Senichev, Minh Ngoc Ta, Ekaterina Fadeeva, Artem Vazhentsev, Daria Galimzianova, Nikolai Rozanov, Viktor Mazanov, Jingwei Ni, Tianyi Wu, Igor Kiselev, Mrinmaya Sachan, Iryna Gurevych, Preslav Nakov, Timothy Baldwin and Artem Shelmanov},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-demo.70},
  url = {https://doi.org/10.18653/v1/2026.acl-demo.70}
}

References

51 references, 30 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Sandhini Agarwal, Lama Ahmad, Jason Ai, Sam Altman, Andy Applebaum, Edwin Arbus, Rahul K. Arora, Yu Bai, Bowen Baker, Haiming Bao, Boaz Barak, Ally Bennett, Tyler Bertao, Nivedita Brett, Eugene Brevdo, Greg Brockman, Sebastien Bubeck, Che Chang, Kai Chen, Mark Chen, Enoch Cheung, Aidan Clark, Dan Co… — gpt-oss-120b & gpt-oss-20b Model Card
  2. Art of Problem Solving. 2026. AIME problems and solutions. https://artofproblemsolving.com/wiki/index.php/AIME_Problems_and_ Solutions. Accessed 2026-05-13. General index containing the 2024 and 2025 AIME pages. ↗
  3. Jacob Austin, Augustus Odena, Maxwell Nye, Maarten Bosma, Henryk Michalewski, David Dohan, Ellen Jiang, Carrie Cai, Michael Terry, Quoc Le, and Charles Sutton. 2021. Program synthesis with large language models. ArXiv preprint, arXiv:2108.07732.
  4. Edward Beeching, Lewis Tunstall, and Sasha Rush. 2024. Scaling test-time compute with open models. https://huggingface.co/spaces/HuggingFaceH4/ blogpost-scaling-test-time-compute. ↗
  5. Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde de Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, Alex Ray, Raul Puri, Gretchen Krueger, Michael Petrov, Heidy Khlaaf, Girish Sastry, Pamela Mishkin, Brooke Chan, Scott Gray, Nick Ryder, Mikhai… — Evaluating Large Language Models Trained on Code
  6. Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, and John Schulman. 2021. Training verifiers to solve math word problems. ArXiv preprint, arXiv:2110.14168.
  7. Ekaterina Fadeeva, Roman Vashurin, Akim Tsvigun, Artem Vazhentsev, Sergey Petrakov, Kirill Fedyanin, Daniil Vasilev, Elizaveta Goncharova, Alexander Panchenko, Maxim Panov, Timothy Baldwin, and Artem Shelmanov. 2023. LM-polygraph: Uncertainty estimation for language models. In Proceedings of the 202… find
  8. Yichao Fu, Xuewei Wang, Hao Zhang, Yuandong Tian, and Jiawei Zhao. 2026. Deep think with confidence. In The Fourteenth International Conference on Learning Representations, ICLR ’26, Rio de Janeiro, Brazil. find
  9. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Peiyi Wang, Qihao Zhu, Runxin Xu, Ruoyu Zhang, Shirong Ma, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z. F. Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, Aixin Liu, Bing Xue, Bingxuan Wang, Bochao Wu, Bei Feng, Chengda Lu, Chenggang Zhao, Che… find
  10. Shibo Hao, Yi Gu, Haotian Luo, Tianyang Liu, Xiyan Shao, Xinyuan Wang, Shuhua Xie, Haodi Ma, Adithya Samavedhi, Qiyue Gao, Zhen Wang, and Zhiting Hu. 2024. LLM reasoners: New evaluation, library, and analysis of step-by-step reasoning with large language models. In Proceedings of the First Conferenc… find
  11. Chaoqun He, Renjie Luo, Yuzhuo Bai, Shengding Hu, Zhen Thai, Junhao Shen, Jinyi Hu, Xu Han, Yujie Huang, Yuxiang Zhang, Jie Liu, Lei Qi, Zhiyuan Liu, and Maosong Sun. 2024. OlympiadBench: A challenging benchmark for promoting AGI with olympiad-level bilingual multimodal scientific problems. In Proce…
  12. Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and Jacob Steinhardt. 2021. Measuring mathematical problem solving with the MATH dataset. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2), Virtua…
  13. Jordan Hoffmann, Sebastian Borgeaud, Arthur Mensch, Elena Buchatskaya, Trevor Cai, Eliza Rutherford, Diego de Las Casas, Lisa Anne Hendricks, Johannes Welbl, Aidan Clark, Thomas Hennigan, Eric Noland, Katherine Millican, George van den Driessche, Bogdan Damoc, Aurelia Guy, Simon Osindero, Karén Simo… find
  14. Yuichi Inoue, Kou Misaki, Yuki Imajuku, So Kuroki, Taishi Nakamura, and Takuya Akiba. 2025. Wider or deeper? scaling llm inference-time compute with adaptive branching tree search. In Advances in Neural Information Processing Systems, volume 38, pages 35448–35484, San Diego, CA, USA. Curran Associat… find
  15. Saurav Kadavath, Tom Conerly, Amanda Askell, Tom Henighan, Dawn Drain, Ethan Perez, Nicholas Schiefer, Zac Hatfield-Dodds, Nova DasSarma, Eli Tran-Johnson, Scott Johnston, Sheer El-Showk, Andy Jones, Nelson Elhage, Tristan Hume, Anna Chen, Yuntao Bai, Sam Bowman, Stanislav Fort, Deep Ganguli, Danny… find
  16. Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B. Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. 2020. Scaling laws for neural language models. ArXiv preprint, arXiv:2001.08361.
  17. Takeshi Kojima, Shixiang (Shane) Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. Large language models are zero-shot reasoners. In Advances in Neural Information Processing Systems, volume 35, pages 22199–22213, New Orleans, LA, USA. Curran Associates, Inc.
  18. Aviral Kumar, Vincent Zhuang, Rishabh Agarwal, Yi Su, JD Co-Reyes, Avi Singh, Kate Baumli, Shariq Iqbal, Colton Bishop, Rebecca Roelofs, Lei Zhang, Kay McKinney, Disha Shrivastava, Cosmin Paduraru, George Tucker, Doina Precup, Feryal Behbahani, and Aleksandra Faust. 2025. Training language models to…
  19. Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph Gonzalez, Hao Zhang, and Ion Stoica. 2023. Efficient memory management for large language model serving with pagedattention. In Proceedings of the 29th Symposium on Operating Systems Principles, SOSP ’23, pages 61…
  20. Yifei Li, Zeqi Lin, Shizhuo Zhang, Qiang Fu, Bei Chen, Jian-Guang Lou, and Weizhu Chen. 2023. Making language models better reasoners with step-aware verifier. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, pages 5315–5333, Toronto, Canada. Association fo…
  21. Zongqian Li, Ehsan Shareghi, and Nigel Collier. 2025. ReasonGraph: Visualization of reasoning methods and extended inference paths. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), pages 140–147, Vienna, Austria. Associatio… find
  22. Hunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. 2024. Let's verify step by step. In International Conference on Learning Representations, volume 2024 of ICLR ’24, pages 39578–39601, Vienna, Austria.
  23. Jiawei Liu, Chunqiu Steven Xia, Yuyao Wang, and LINGMING ZHANG. 2023. Is your code generated by ChatGPT really correct? Rigorous evaluation of large language models for code generation. In Advances in Neural Information Processing Systems, volume 36, pages 21558–21572, New Orleans, Louisiana, USA. C…
  24. Xiaoyuan Liu, Tian Liang, Zhiwei He, Jiahao Xu, Wenxuan Wang, Pinjia He, Zhaopeng Tu, Haitao Mi, and Dong Yu. 2025. Trust, but verify: A self-verification approach to reinforcement learning with verifiable rewards. In Advances in Neural Information Processing Systems, volume 38 of NeurIPS ’25, pages… find
  25. Chris Lu, Cong Lu, Robert Tjarko Lange, Yutaro Yamada, Shengran Hu, Jakob Foerster, David Ha, and Jeff Clune. 2026. Towards end-to-end automation of AI research. Nature, 651(8107):914–919. find
  26. Liangchen Luo, Yinxiao Liu, Rosanne Liu, Samrat Phatale, Meiqi Guo, Harsh Lara, Yunxuan Li, Lei Shu, Yun Zhu, Lei Meng, Jiao Sun, and Abhinav Rastogi. 2024. Improve mathematical reasoning in language models by automated process supervision. ArXiv preprint, arXiv:2406.06592.
  27. Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, Shashank Gupta, Bodhisattwa Prasad Majumder, Katherine Hermann, Sean Welleck, Amir Yazdanbakhsh, and Peter Clark. 2023. SELF-REFINE: iterative refinement with… find
  28. Niklas Muennighoff, Zitong Yang, Weijia Shi, Xiang Lisa Li, Li Fei-Fei, Hannaneh Hajishirzi, Luke Zettlemoyer, Percy Liang, Emmanuel Candès, and Tatsunori Hashimoto. 2025. s1: Simple test-time scaling. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, EMNLP ’…
  29. Jingwei Ni, Ekaterina Fadeeva, Tianyi Wu, Mubashara Akhtar, Jiaheng Zhang, Elliott Ash, Markus Leippold, Timothy Baldwin, See-Kiong Ng, Artem Shelmanov, and Mrinmaya Sachan. 2026. ReProbe: Efficient test-time scaling of multi-step reasoning by probing internal states of large language models. In Pro…
  30. Anne Ouyang, Simon Guo, Simran Arora, Alex L Zhang, William Hu, Christopher Re, and Azalia Mirhoseini. 2025. KernelBench: Can LLMs write efficient GPU kernels? In Proceedings of the 42nd International Conference on Machine Learning, volume 267 of Proceedings of Machine Learning Research, pages 47356…
  31. David Rein, Betty Li Hou, Asa Cooper Stickland, Jackson Petty, Richard Yuanzhe Pang, Julien Dirani, Julian Michael, and Samuel R. Bowman. 2024. GPQA: A graduate-level google-proof q&a benchmark. In First Conference on Language Modeling, Philadelphia, PA, USA.
  32. Bernardino Romera-Paredes, Mohammadamin Barekatain, Alexander Novikov, Matej Balog, M. Pawan Kumar, Emilien Dupont, Francisco J. R. Ruiz, Jordan S. Ellenberg, Pengming Wang, Omar Fawzi, Pushmeet Kohli, and Alhussein Fawzi. 2024. Mathematical discoveries from program search with large language models…
  33. Asankhaya Sharma. 2024. OptiLLM: Optimizing inference proxy for LLMs. Accessed: 2026-05-16. find
  34. Artem Shelmanov, Ekaterina Fadeeva, Akim Tsvigun, Ivan Tsvigun, Zhuohan Xie, Igor Kiselev, Nico Daheim, Caiqi Zhang, Artem Vazhentsev, Mrinmaya Sachan, Preslav Nakov, and Timothy Baldwin. 2025. A head to predict and a head to question: Pre-trained uncertainty quantification heads for hallucination d… find
  35. Charlie Snell, Jaehoon Lee, Kelvin Xu, and Aviral Kumar. 2025. Scaling LLM test-time compute optimally can be more effective than scaling parameters for reasoning. In International Conference on Learning Representations, volume 2025, pages 10131–10165, Singapore. find
  36. Jonathan Uesato, Nate Kushman, Ramana Kumar, Francis Song, Noah Siegel, Lisa Wang, Antonia Creswell, Geoffrey Irving, and Irina Higgins. 2022. Solving Math word problems with process- and outcome-based feedback. ArXiv preprint, arXiv:2211.14275.
  37. Roman Vashurin, Ekaterina Fadeeva, Artem Vazhentsev, Lyudmila Rvanova, Daniil Vasilev, Akim Tsvigun, Sergey Petrakov, Rui Xing, Abdelrahman Sadallah, Kirill Grishchenkov, Alexander Panchenko, Timothy Baldwin, Preslav Nakov, Maxim Panov, and Artem Shelmanov. 2025. Benchmarking uncertainty quantificat…
  38. Jun Wang, Meng Fang, Ziyu Wan, Muning Wen, Jiachen Zhu, Anjie Liu, Ziqin Gong, Yan Song, Lei Chen, Lionel M. Ni, Linyi Yang, Ying Wen, and Weinan Zhang. 2024. OpenR: An open source framework for advanced reasoning with large language models. ArXiv preprint, arXiv:2410.09671. find
  39. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V. Le, Ed H. Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2023. Self-consistency improves chain of thought reasoning in language models. In The Eleventh International Conference on Learning Representations, ICLR ’2023, Kigali, Rwanda. OpenRev…
  40. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed Chi, Quoc V Le, and Denny Zhou. 2022. Chain-of-thought prompting elicits reasoning in large language models. In Advances in Neural Information Processing Systems, volume 35, pages 24824–24837, New Orleans, LA, USA. Cur…
  41. Yixuan Weng, Minjun Zhu, Fei Xia, Bin Li, Shizhu He, Shengping Liu, Bin Sun, Kang Liu, and Jun Zhao. 2023. Large language models are better reasoners with self-verification. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 2550–2575, Singapore. Association for Computat…
  42. Yuxi Xie, Kenji Kawaguchi, Yiran Zhao, James Xu Zhao, Min-Yen Kan, Junxian He, and Michael Xie. 2023. Self-evaluation guided beam search for reasoning. In Advances in Neural Information Processing Systems, volume 36, pages 41618–41650, New Orleans, LA, USA. Curran Associates, Inc.
  43. Fangzhi Xu, Hang Yan, Chang Ma, Haiteng Zhao, Jun Liu, Qika Lin, and Zhiyong Wu. 2025. φ-decoding: Adaptive foresight sampling for balanced inference-time exploration and exploitation. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers),… find
  44. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, Chujie Zheng, Dayiheng Liu, Fan Zhou, Fei Huang, Feng Hu, Hao Ge, Haoran Wei, Huan Lin, Jialong Tang, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jing Zhou, Jin… — Qwen3 Technical Report
  45. An Yang, Beichen Zhang, Binyuan Hui, Bofei Gao, Bowen Yu, Chengpeng Li, Dayiheng Liu, Jianhong Tu, Jingren Zhou, Junyang Lin, Keming Lu, Mingfeng Xue, Runji Lin, Tianyu Liu, Xingzhang Ren, and Zhenru Zhang. 2024. Qwen2.5-Math technical report: Toward mathematical expert model via self-improvement. A…
  46. Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, and Karthik Narasimhan. 2023. Tree of thoughts: Deliberate problem solving with large language models. In Advances in Neural Information Processing Systems, volume 36, pages 11809–11822, New Orleans, LA, USA. Curran Associate… find
  47. Jinghan Zhang, Xiting Wang, Fengran Mo, Yeyang Zhou, Wanfu Gao, and Kunpeng Liu. 2025a. Entropy-based exploration conduction for multi-step reasoning. In Findings of the Association for Computational Linguistics: ACL 2025, pages 3895–3906, Vienna, Austria. Association for Computational Linguistics. find
  48. Xiaotian Zhang, Chunyang Li, Yi Zong, Zhengyu Ying, Liang He, and Xipeng Qiu. 2023. Evaluating the performance of large language models on GAOKAO benchmark. ArXiv preprint, arXiv:2305.12474.
  49. Zhenru Zhang, Chujie Zheng, Yangzhen Wu, Beichen Zhang, Runji Lin, Bowen Yu, Dayiheng Liu, Jingren Zhou, and Junyang Lin. 2025b. The lessons of developing process reward models in mathematical reasoning. In Findings of the Association for Computational Linguistics: ACL 2025, pages 10495–10516, Vienn…
  50. Yuqi Zhu, Ge Li, Xue Jiang, Jia Li, Hong Mei, Zhi Jin, and Yihong Dong. 2025. Uncertainty-guided chain-of-thought for code generation with LLMs. ArXiv preprint, arXiv:2503.15341. — [arXiv:2503.15341](https://arxiv.org/abs/2503.15341) find
  51. Hang Yan, Fangzhi Xu, Rongman Xu, Yifei Li, Jian Zhang, Haoran Luo, Xiaobao Wu, Luu Anh Tuan, Haiteng Zhao, Qika Lin, and Jun Liu. 2025. MUR: Momentum uncertainty guided reasoning for large language models. ArXiv preprint, arXiv:2507.14958.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/smirnov-2026-thinkbooster-unified-framework-seamless-test/