---
title: "Dynamic Parallel Tree Search for Efficient LLM Reasoning (2025)"
description: "Tree-of-Thoughts (ToT) style search, often driven by MCTS, improves LLM reasoning, but prior work… 60 references, cited by 10 papers here."
authors: ["Yifu Ding", "Wentao Jiang", "Shunyu Liu", "Yongcheng Jing", "Jinyang Guo", "Yingjie Wang", "Jing Zhang", "Zengmao Wang", "Ziwei Liu", "Bo Du", "Xianglong Liu", "Dacheng Tao"]
year: 2025
venue: "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2025.acl-long.550/"
doi: "10.18653/v1/2025.acl-long.550"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/ding-2025-dynamic-parallel-tree-search-efficient/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/ding-2025-dynamic-parallel-tree-search-efficient/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/6/) / Dynamic Parallel Tree Search for Efficient LLM Reasoning

# Dynamic Parallel Tree Search for Efficient LLM Reasoning

**Authors:** Yifu Ding, Wentao Jiang, [Shunyu Liu](https://md.research.elamur.ai/free/en/authors/shunyu-liu/), [Yongcheng Jing](https://md.research.elamur.ai/free/en/authors/yongcheng-jing/), [Jinyang Guo](https://md.research.elamur.ai/free/en/authors/jinyang-guo/), [Yingjie Wang](https://md.research.elamur.ai/free/en/authors/yingjie-wang/), [Jing Zhang](https://md.research.elamur.ai/free/en/authors/jing-zhang/), Zengmao Wang, [Ziwei Liu](https://md.research.elamur.ai/free/en/authors/ziwei-liu/), Bo Du, [Xianglong Liu](https://md.research.elamur.ai/free/en/authors/xianglong-liu/) and [Dacheng Tao](https://md.research.elamur.ai/free/en/authors/dacheng-tao/) · **Year:** 2025 · **Venue:** [Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2025](https://md.research.elamur.ai/free/en/venues/acl/2025/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2025.acl-long.550/) · [PDF](https://aclanthology.org/2025.acl-long.550.pdf) · [DOI 10.18653/v1/2025.acl-long.550](https://doi.org/10.18653/v1/2025.acl-long.550) · [OpenAlex](https://openalex.org/W4412945401)

**Citations:** 3 citations (OpenAlex, 2026-10-14) · [10](https://md.research.elamur.ai/free/en/papers/ding-2025-dynamic-parallel-tree-search-efficient/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Tree-of-Thoughts (ToT) style search, often driven by MCTS, improves LLM reasoning, but prior work has focused on accuracy rather than cost. The authors identify two sources of inefficiency. First, the search keeps jumping between branches of uneven length, which makes GPU batching hard. Second, weak branches keep being expanded until hitting time or token limits. On Math500, for example, they count about 36.7 focus switches per problem.

Their framework, DPTS, has two parts:
- **Parallelism Streamline** handles the generation phase. It manages and aligns KV caches and padding so that nodes from arbitrary paths can be expanded together in one batch.
- **Search and Transition Mechanism** handles the selection phase. It uses confidence thresholds to move nodes between exploitation and exploration in both directions, via Early Stop and Deep Seek.

Tested with Qwen-2.5 and Llama-3 models, DPTS runs on average 2–4× faster than MCTS, Best-of-N and Beam search, with equal or better accuracy. This makes tree-based reasoning cheaper to scale.

## Key points
- Models evaluated: Qwen2.5-1.5B, Qwen2.5-7B, Llama3-3B and Llama3-8B. Benchmarks shown include GSM8K and Math500. The abstract mentions code datasets, but the Limitations section says validation covered math only.
- Low-confidence nodes ended in suboptimal results 91.3% of the time and were the earliest best path only 6.2% of the time. This motivates pruning them early.
- Transition thresholds switch from a mean-based rule to a max-based one after step t* = 5. Results stay robust for λ values between 0.6 and 0.9.
- The approach is orthogonal to low-level optimizations such as DEFT prefix sharing. Code is available at github.com/yifu-ding/DPTS.

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

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works

🧭 Topics (2): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,320 works · [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,426 works

## Cite

Cite as: Yifu Ding, Wentao Jiang, Shunyu Liu, Yongcheng Jing, Jinyang Guo, Yingjie Wang, Jing Zhang, Zengmao Wang, Ziwei Liu, Bo Du, Xianglong Liu and Dacheng Tao. 2025. Dynamic Parallel Tree Search for Efficient LLM Reasoning. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{ding2025dynamic,
  title = {{Dynamic Parallel Tree Search for Efficient LLM Reasoning}},
  author = {Yifu Ding, Wentao Jiang, Shunyu Liu, Yongcheng Jing, Jinyang Guo, Yingjie Wang, Jing Zhang, Zengmao Wang, Ziwei Liu, Bo Du, Xianglong Liu and Dacheng Tao},
  booktitle = {Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2025},
  doi = {10.18653/v1/2025.acl-long.550},
  url = {https://doi.org/10.18653/v1/2025.acl-long.550}
}
```

- [← previous DRAMA: Diverse Augmentation from Large Language Models to Smaller Dense Retrievers](https://md.research.elamur.ai/free/en/papers/ma-2025-drama-diverse-augmentation-large-language/)
- [next → Efficient Tool Use with Chain-of-Abstraction Reasoning](https://md.research.elamur.ai/free/en/papers/gao-2025-efficient-tool-use-chain-abstraction/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/6/)

## References

60 references, 25 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). arXiv preprint arXiv:2303.08774.
2. Jinze Bai, Shuai Bai, Yunfei Chu, Zeyu Cui, Kai Dang, Xiaodong Deng, Yang Fan, Wenbin Ge, Yu Han, Fei Huang, et al. 2023. [Qwen technical report](https://md.research.elamur.ai/free/en/papers/bai-2023-qwen-technical-report/). arXiv preprint arXiv:2309.16609.
3. Maciej Besta, Florim Memedi, Zhenyu Zhang, Robert Gerstenberger, Nils Blach, Piotr Nyczyk, Marcin Copik, Grzegorz Kwaśniewski, Jürgen Müller, Lukas Gianinazzi, et al. 2024. Topologies of reasoning: Demystifying chains, trees, and graphs of thoughts. arXiv preprint arXiv:2401.14295. — [arXiv:2401.14295](https://arxiv.org/abs/2401.14295) [find](https://scholar.google.com/scholar?q=Maciej+Besta%2C+Florim+Memedi%2C+Zhenyu+Zhang%2C+Robert+Gerstenberger%2C+Nils+Blach%2C+Piotr+Nyczyk%2C+Marcin+Copik%2C+Grzegorz+Kwas%CC%81niewski%2C+J%C3%BCrgen+M%C3%BCller%2C+Lukas+Gianinazzi%2C+et+al%2E+2024%2E+Topologies+of+reasoning%3A+D)
4. Zhenni Bi, Kai Han, Chuanjian Liu, Yehui Tang, and Yunhe Wang. 2024. [Forest-of-thought: Scaling test-time compute for enhancing llm reasoning](https://md.research.elamur.ai/free/en/papers/bi-2024-forest-thought-scaling-test-time/). arXiv preprint arXiv:2412.09078.
5. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chri… — [Language Models are Few-Shot Learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/)
6. Cameron B Browne, Edward Powley, Daniel Whitehouse, Simon M Lucas, Peter I Cowling, Philipp Rohlfshagen, Stephen Tavener, Diego Perez, Spyridon Samothrakis, and Simon Colton. 2012. A survey of monte carlo tree search methods. IEEE Transactions on Computational Intelligence and AI in games, 4(1):1–43… [find](https://scholar.google.com/scholar?q=Cameron+B+Browne%2C+Edward+Powley%2C+Daniel+Whitehouse%2C+Simon+M+Lucas%2C+Peter+I+Cowling%2C+Philipp+Rohlfshagen%2C+Stephen+Tavener%2C+Diego+Perez%2C+Spyridon+Samothrakis%2C+and+Simon+Colton%2E+2012%2E+A+survey+of+monte+c)
7. Tianle Cai, Yuhong Li, Zhengyang Geng, Hongwu Peng, Jason D Lee, Deming Chen, and Tri Dao. 2024. [Medusa: Simple llm inference acceleration framework with multiple decoding heads](https://md.research.elamur.ai/free/en/papers/cai-2024-medusa-simple-llm-inference-acceleration/). arXiv preprint arXiv:2401.10774.
8. Guillaume Chaslot, Sander Bakkes, Istvan Szita, and Pieter Spronck. 2008. Monte-carlo tree search: A new framework for game ai. In Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, volume 4, pages 216– 217. [find](https://scholar.google.com/scholar?q=Guillaume+Chaslot%2C+Sander+Bakkes%2C+Istvan+Szita%2C+and+Pieter+Spronck%2E+2008%2E+Monte%2Dcarlo+tree+search%3A+A+new+framework+for+game+ai%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligence+and+Int)
9. Pengyu Cheng, Tianhao Hu, Han Xu, Zhisong Zhang, Yong Dai, Lei Han, nan du, and Xiaolong Li. 2024. Self-playing adversarial language game enhances llm reasoning. In Advances in Neural Information Processing Systems, volume 37, pages 126515–126543. Curran Associates, Inc. [find](https://scholar.google.com/scholar?q=Pengyu+Cheng%2C+Tianhao+Hu%2C+Han+Xu%2C+Zhisong+Zhang%2C+Yong+Dai%2C+Lei+Han%2C+nan+du%2C+and+Xiaolong+Li%2E+2024%2E+Self%2Dplaying+adversarial+language+game+enhances+llm+reasoning%2E+In+Advances+in+Neural+Information+Proc)
10. Zheng Chu, Jingchang Chen, Qianglong Chen, Weijiang Yu, Tao He, Haotian Wang, Weihua Peng, Ming Liu, Bing Qin, and Ting Liu. 2023. A survey of chain of thought reasoning: Advances, frontiers and future. arXiv preprint arXiv:2309.15402. [find](https://scholar.google.com/scholar?q=Zheng+Chu%2C+Jingchang+Chen%2C+Qianglong+Chen%2C+Weijiang+Yu%2C+Tao+He%2C+Haotian+Wang%2C+Weihua+Peng%2C+Ming+Liu%2C+Bing+Qin%2C+and+Ting+Liu%2E+2023%2E+A+survey+of+chain+of+thought+reasoning%3A+Advances%2C+frontiers+and+futur)
11. Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, et al. 2021. [Training verifiers to solve math word problems](https://md.research.elamur.ai/free/en/papers/cobbe-2021-training-verifiers-solve-math-word/). arXiv preprint arXiv:2110.14168.
12. Linger Deng, Yuliang Liu, Bohan Li, Dongliang Luo, Liang Wu, Chengquan Zhang, Pengyuan Lyu, Ziyang Zhang, Gang Zhang, Errui Ding, et al. 2024. Rcot: Reverse chain-of-thought problem generation for geometric reasoning in large multimodal models. arXiv preprint arXiv:2410.17885. — [arXiv:2410.17885](https://arxiv.org/abs/2410.17885) [find](https://scholar.google.com/scholar?q=Linger+Deng%2C+Yuliang+Liu%2C+Bohan+Li%2C+Dongliang+Luo%2C+Liang+Wu%2C+Chengquan+Zhang%2C+Pengyuan+Lyu%2C+Ziyang+Zhang%2C+Gang+Zhang%2C+Errui+Ding%2C+et+al%2E+2024%2E+Rcot%3A+Reverse+chain%2Dof%2Dthought+problem+generation+for+geo)
13. Luciano Floridi and Massimo Chiriatti. 2020. Gpt-3: Its nature, scope, limits, and consequences. Minds and Machines, 30:681–694. [find](https://scholar.google.com/scholar?q=Luciano+Floridi+and+Massimo+Chiriatti%2E+2020%2E+Gpt%2D3%3A+Its+nature%2C+scope%2C+limits%2C+and+consequences%2E+Minds+and+Machines%2C+30%3A681%E2%80%93694%2E)
14. Yichao Fu, Peter Bailis, Ion Stoica, and Hao Zhang. 2024. [Break the sequential dependency of llm inference using lookahead decoding](https://md.research.elamur.ai/free/en/papers/fu-2024-break-sequential-dependency-llm-inference/). arXiv preprint arXiv:2402.02057.
15. Tingxu Han, Chunrong Fang, Shiyu Zhao, Shiqing Ma, Zhenyu Chen, and Zhenting Wang. 2024. [Token-budget-aware llm reasoning](https://md.research.elamur.ai/free/en/papers/han-2024-token-budget-aware-llm-reasoning/). arXiv preprint arXiv:2412.18547.
16. Shibo Hao, Yi Gu, Haodi Ma, Joshua Jiahua Hong, Zhen Wang, Daisy Zhe Wang, and Zhiting Hu. 2023. Reasoning with language model is planning with world model. arXiv preprint arXiv:2305.14992. [find](https://scholar.google.com/scholar?q=Shibo+Hao%2C+Yi+Gu%2C+Haodi+Ma%2C+Joshua+Jiahua+Hong%2C+Zhen+Wang%2C+Daisy+Zhe+Wang%2C+and+Zhiting+Hu%2E+2023%2E+Reasoning+with+language+model+is+planning+with+world+model%2E+arXiv+preprint+arXiv%3A2305%2E14992%2E)
17. 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](https://md.research.elamur.ai/free/en/papers/hendrycks-2021-measuring-mathematical-problem-solving-math/). arXiv preprint arXiv:2103.03874.
18. Ke Hong, Guohao Dai, Jiaming Xu, Qiuli Mao, Xiuhong Li, Jun Liu, Yuhan Dong, Yu Wang, et al. 2024. Flashdecoding++: Faster large language model inference with asynchronization, flat gemm optimization, and heuristics. Proceedings of Machine Learning and Systems, 6:148–161. [find](https://scholar.google.com/scholar?q=Ke+Hong%2C+Guohao+Dai%2C+Jiaming+Xu%2C+Qiuli+Mao%2C+Xiuhong+Li%2C+Jun+Liu%2C+Yuhan+Dong%2C+Yu+Wang%2C+et+al%2E+2024%2E+Flashdecoding%2B%2B%3A+Faster+large+language+model+inference+with+asynchronization%2C+flat+gemm+optimization%2C)
19. Arian Hosseini, Xingdi Yuan, Nikolay Malkin, Aaron Courville, Alessandro Sordoni, and Rishabh Agarwal. 2024. [V-star: Training verifiers for self-taught reasoners](https://md.research.elamur.ai/free/en/papers/hosseini-2024-v-star-training-verifiers-self/). arXiv preprint arXiv:2402.06457.
20. Aaron Jaech, Adam Kalai, Adam Lerer, Adam Richardson, Ahmed El-Kishky, Aiden Low, Alec Helyar, Aleksander Madry, Alex Beutel, Alex Carney, et al. 2024. [Openai o1 system card](https://md.research.elamur.ai/free/en/papers/openai-2024-openai-o1-system-card/). arXiv preprint arXiv:2412.16720.
21. Fangkai Jiao, Chengwei Qin, Zhengyuan Liu, Nancy F Chen, and Shafiq Joty. 2024. [Learning planning-based reasoning by trajectories collection and process reward synthesizing](https://md.research.elamur.ai/free/en/papers/jiao-2024-learning-planning-based-reasoning-trajectories/). arXiv preprint arXiv:2402.00658.
22. Yongcheng Jing, Chongbin Yuan, Li Ju, Yiding Yang, Xinchao Wang, and Dacheng Tao. 2023. Deep graph reprogramming. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 24345–24354. [find](https://scholar.google.com/scholar?q=Yongcheng+Jing%2C+Chongbin+Yuan%2C+Li+Ju%2C+Yiding+Yang%2C+Xinchao+Wang%2C+and+Dacheng+Tao%2E+2023%2E+Deep+graph+reprogramming%2E+In+Proceedings+of+the+IEEE%2FCVF+Conference+on+Computer+Vision+and+Pattern+Recognition%2C+)
23. Levente Kocsis, Csaba Szepesvári, and Jan Willemson. 2006. Improved monte-carlo search. Univ. Tartu, Estonia, Tech. Rep, 1:1–22. [find](https://scholar.google.com/scholar?q=Levente+Kocsis%2C+Csaba+Szepesv%C3%A1ri%2C+and+Jan+Willemson%2E+2006%2E+Improved+monte%2Dcarlo+search%2E+Univ%2E+Tartu%2C+Estonia%2C+Tech%2E+Rep%2C+1%3A1%E2%80%9322%2E)
24. Takeshi Kojima, Shixiang (Shane) Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. [Large language models are zero-shot reasoners](https://md.research.elamur.ai/free/en/papers/kojima-2022-large-language-models-zero-shot/). In Advances in Neural Information Processing Systems, volume 35, pages 22199–22213. Curran Associates, Inc.
25. Yaniv Leviathan, Matan Kalman, and Yossi Matias. 2023. Fast inference from transformers via speculative decoding. In International Conference on Machine Learning, pages 19274–19286. [find](https://scholar.google.com/scholar?q=Yaniv+Leviathan%2C+Matan+Kalman%2C+and+Yossi+Matias%2E+2023%2E+Fast+inference+from+transformers+via+speculative+decoding%2E+In+International+Conference+on+Machine+Learning%2C+pages+19274%E2%80%9319286%2E)
26. Jinhao Li, Jiaming Xu, Shan Huang, Yonghua Chen, Wen Li, Jun Liu, Yaoxiu Lian, Jiayi Pan, Li Ding, Hao Zhou, et al. 2024a. Large language model inference acceleration: A comprehensive hardware perspective. arXiv preprint arXiv:2410.04466. [find](https://scholar.google.com/scholar?q=Jinhao+Li%2C+Jiaming+Xu%2C+Shan+Huang%2C+Yonghua+Chen%2C+Wen+Li%2C+Jun+Liu%2C+Yaoxiu+Lian%2C+Jiayi+Pan%2C+Li+Ding%2C+Hao+Zhou%2C+et+al%2E+2024a%2E+Large+language+model+inference+acceleration%3A+A+comprehensive+hardware+perspec)
27. Yiwei Li, Peiwen Yuan, Shaoxiong Feng, Boyuan Pan, Xinglin Wang, Bin Sun, Heda Wang, and Kan Li. 2024b. Escape sky-high cost: Early-stopping self-consistency for multi-step reasoning. In The Twelfth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Yiwei+Li%2C+Peiwen+Yuan%2C+Shaoxiong+Feng%2C+Boyuan+Pan%2C+Xinglin+Wang%2C+Bin+Sun%2C+Heda+Wang%2C+and+Kan+Li%2E+2024b%2E+Escape+sky%2Dhigh+cost%3A+Early%2Dstopping+self%2Dconsistency+for+multi%2Dstep+reasoning%2E+In+The+Twelfth+I)
28. Hunter Lightman, Vineet Kosaraju, Yura Burda, Harri Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. 2023. [Let’s verify step by step](https://md.research.elamur.ai/free/en/papers/lightman-2023-let-s-verify-step-step/). arXiv preprint arXiv:2305.20050.
29. Ji Lin, Jiaming Tang, Haotian Tang, Shang Yang, Wei-Ming Chen, Wei-Chen Wang, Guangxuan Xiao, Xingyu Dang, Chuang Gan, and Song Han. 2024. Awq: Activation-aware weight quantization for on-device llm compression and acceleration. Proceedings of Machine Learning and Systems, 6:87–100. [find](https://scholar.google.com/scholar?q=Ji+Lin%2C+Jiaming+Tang%2C+Haotian+Tang%2C+Shang+Yang%2C+Wei%2DMing+Chen%2C+Wei%2DChen+Wang%2C+Guangxuan+Xiao%2C+Xingyu+Dang%2C+Chuang+Gan%2C+and+Song+Han%2E+2024%2E+Awq%3A+Activation%2Daware+weight+quantization+for+on%2Ddevice+llm+c)
30. Shunyu Liu, Wenkai Fang, Zetian Hu, Junjie Zhang, Yang Zhou, Kongcheng Zhang, Rongcheng Tu, Ting-En Lin, Fei Huang, Mingli Song, and Dacheng Tao. 2025. A survey of direct preference optimization. arXiv preprint arXiv:2503.11701. — [arXiv:2503.11701](https://arxiv.org/abs/2503.11701) [find](https://scholar.google.com/scholar?q=Shunyu+Liu%2C+Wenkai+Fang%2C+Zetian+Hu%2C+Junjie+Zhang%2C+Yang+Zhou%2C+Kongcheng+Zhang%2C+Rongcheng+Tu%2C+Ting%2DEn+Lin%2C+Fei+Huang%2C+Mingli+Song%2C+and+Dacheng+Tao%2E+2025%2E+A+survey+of+direct+preference+optimization%2E+arXi)
31. Alex Gu Wen-Ding Li Fanjia Yan Tianjun Zhang Sida Wang Armando Solar-Lezama Koushik Sen Ion Stoica Naman Jain, King Han. 2024. [Livecodebench: Holistic and contamination free evaluation of large language models for code](https://md.research.elamur.ai/free/en/papers/jain-2024-livecodebench-holistic-contamination-free-evaluation/). arXiv preprint.
32. Sania Nayab, Giulio Rossolini, Marco Simoni, Andrea Saracino, Giorgio Buttazzo, Nicolamaria Manes, and Fabrizio Giacomelli. 2024. Concise thoughts: Impact of output length on llm reasoning and cost. arXiv preprint arXiv:2407.19825. — [arXiv:2407.19825](https://arxiv.org/abs/2407.19825) [find](https://scholar.google.com/scholar?q=Sania+Nayab%2C+Giulio+Rossolini%2C+Marco+Simoni%2C+Andrea+Saracino%2C+Giorgio+Buttazzo%2C+Nicolamaria+Manes%2C+and+Fabrizio+Giacomelli%2E+2024%2E+Concise+thoughts%3A+Impact+of+output+length+on+llm+reasoning+and+cost%2E+a)
33. Xuefei Ning, Zinan Lin, Zixuan Zhou, Zifu Wang, Huazhong Yang, and Yu Wang. 2024. Skeleton-of-thought: Prompting llms for efficient parallel generation. In The Twelfth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Xuefei+Ning%2C+Zinan+Lin%2C+Zixuan+Zhou%2C+Zifu+Wang%2C+Huazhong+Yang%2C+and+Yu+Wang%2E+2024%2E+Skeleton%2Dof%2Dthought%3A+Prompting+llms+for+efficient+parallel+generation%2E+In+The+Twelfth+International+Conference+on+Lear)
34. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul F Christiano, Jan Leike, and Ryan Lowe. 2022. Tra… — [Training language models to follow instructions with human feedback](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/)
35. Aske Plaat, Annie Wong, Suzan Verberne, Joost Broekens, Niki van Stein, and Thomas Back. 2024. [Reasoning with large language models, a survey](https://md.research.elamur.ai/free/en/papers/minaee-2024-large-language-models-survey/). arXiv preprint arXiv:2407.11511.
36. Charlie Snell, Jaehoon Lee, Kelvin Xu, and Aviral Kumar. 2024. [Scaling llm test-time compute optimally can be more effective than scaling model parameters](https://md.research.elamur.ai/free/en/papers/snell-2024-scaling-llm-test-time-compute/). arXiv preprint arXiv:2408.03314.
37. Henry W Sprueill, Carl Edwards, Mariefel V Olarte, Udishnu Sanyal, Heng Ji, and Sutanay Choudhury. 2023. Monte carlo thought search: Large language model querying for complex scientific reasoning in catalyst design. arXiv preprint arXiv:2310.14420. and Denny Zhou. 2022. Chain-of-thought prompting el… [find](https://scholar.google.com/scholar?q=Henry+W+Sprueill%2C+Carl+Edwards%2C+Mariefel+V+Olarte%2C+Udishnu+Sanyal%2C+Heng+Ji%2C+and+Sutanay+Choudhury%2E+2023%2E+Monte+carlo+thought+search%3A+Large+language+model+querying+for+complex+scientific+reasoning+in+c)
38. Hanshi Sun, Momin Haider, Ruiqi Zhang, Huitao Yang, Jiahao Qiu, Ming Yin, Mengdi Wang, Peter Bartlett, and Andrea Zanette. 2024. Fast best-of-n decoding via speculative rejection. arXiv preprint arXiv:2410.20290. [find](https://scholar.google.com/scholar?q=Hanshi+Sun%2C+Momin+Haider%2C+Ruiqi+Zhang%2C+Huitao+Yang%2C+Jiahao+Qiu%2C+Ming+Yin%2C+Mengdi+Wang%2C+Peter+Bartlett%2C+and+Andrea+Zanette%2E+2024%2E+Fast+best%2Dof%2Dn+decoding+via+speculative+rejection%2E+arXiv+preprint+arXiv)
39. Yangzhen Wu, Zhiqing Sun, Shanda Li, Sean Welleck, and Yiming Yang. 2024. [Inference scaling laws: An empirical analysis of compute-optimal inference for problem-solving with language models](https://md.research.elamur.ai/free/en/papers/wu-2024-inference-scaling-laws-empirical-analysis/). arXiv preprint arXiv:2408.00724.
40. Ganchao Tan, Daqing Liu, Meng Wang, and Zheng-Jun Zha. 2020. Learning to discretely compose reasoning module networks for video captioning. arXiv preprint arXiv:2007.09049. — [arXiv:2007.09049](https://arxiv.org/abs/2007.09049) [find](https://scholar.google.com/scholar?q=Ganchao+Tan%2C+Daqing+Liu%2C+Meng+Wang%2C+and+Zheng%2DJun+Zha%2E+2020%2E+Learning+to+discretely+compose+reasoning+module+networks+for+video+captioning%2E+arXiv+preprint+arXiv%3A2007%2E09049%2E+%E2%80%94+%5BarXiv%3A2007%2E09049%5D%28https%3A)
41. Yuxi Xie, Anirudh Goyal, Wenyue Zheng, Min-Yen Kan, Timothy P Lillicrap, Kenji Kawaguchi, and Michael Shieh. 2024. Monte carlo tree search boosts reasoning via iterative preference learning. arXiv preprint arXiv:2405.00451. [find](https://scholar.google.com/scholar?q=Yuxi+Xie%2C+Anirudh+Goyal%2C+Wenyue+Zheng%2C+Min%2DYen+Kan%2C+Timothy+P+Lillicrap%2C+Kenji+Kawaguchi%2C+and+Michael+Shieh%2E+2024%2E+Monte+carlo+tree+search+boosts+reasoning+via+iterative+preference+learning%2E+arXiv+pre)
42. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. [Llama: Open and efficient foundation language models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-open-efficient-foundation-language/). arXiv preprint arXiv:2302.13971.
43. Guangya Wan, Yuqi Wu, Jie Chen, and Sheng Li. 2024a. Dynamic self-consistency: Leveraging reasoning paths for efficient llm sampling. arXiv preprint arXiv:2408.17017. — [arXiv:2408.17017](https://arxiv.org/abs/2408.17017) [find](https://scholar.google.com/scholar?q=Guangya+Wan%2C+Yuqi+Wu%2C+Jie+Chen%2C+and+Sheng+Li%2E+2024a%2E+Dynamic+self%2Dconsistency%3A+Leveraging+reasoning+paths+for+efficient+llm+sampling%2E+arXiv+preprint+arXiv%3A2408%2E17017%2E+%E2%80%94+%5BarXiv%3A2408%2E17017%5D%28https%3A%2F%2Farxi)
44. Ziyu Wan, Xidong Feng, Muning Wen, Stephen Marcus McAleer, Ying Wen, Weinan Zhang, and Jun Wang. 2024b. Alphazero-like tree-search can guide large language model decoding and training. In Forty-first International Conference on Machine Learning. [find](https://scholar.google.com/scholar?q=Ziyu+Wan%2C+Xidong+Feng%2C+Muning+Wen%2C+Stephen+Marcus+McAleer%2C+Ying+Wen%2C+Weinan+Zhang%2C+and+Jun+Wang%2E+2024b%2E+Alphazero%2Dlike+tree%2Dsearch+can+guide+large+language+model+decoding+and+training%2E+In+Forty%2Dfirst+)
45. Chaojie Wang, Yanchen Deng, Zhiyi Lyu, Liang Zeng, Jujie He, Shuicheng Yan, and Bo An. 2024a. Q*: Improving multi-step reasoning for llms with deliberative planning. arXiv preprint arXiv:2406.14283. [find](https://scholar.google.com/scholar?q=Chaojie+Wang%2C+Yanchen+Deng%2C+Zhiyi+Lyu%2C+Liang+Zeng%2C+Jujie+He%2C+Shuicheng+Yan%2C+and+Bo+An%2E+2024a%2E+Q%2A%3A+Improving+multi%2Dstep+reasoning+for+llms+with+deliberative+planning%2E+arXiv+preprint+arXiv%3A2406%2E14283%2E)
46. Peiyi Wang, Lei Li, Zhihong Shao, RX Xu, Damai Dai, Yifei Li, Deli Chen, Yu Wu, and Zhifang Sui. 2023. [Math-shepherd: Verify and reinforce llms step-by-step without human annotations](https://md.research.elamur.ai/free/en/papers/wang-2024-math-shepherd-verify-reinforce-llms/). arXiv preprint arXiv:2312.08935.
47. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2022. [Self-consistency improves chain of thought reasoning in language models](https://md.research.elamur.ai/free/en/papers/wang-2022-self-consistency-improves-chain-thought/). arXiv preprint arXiv:2203.11171.
48. Yue Wang, Qiuzhi Liu, Jiahao Xu, Tian Liang, Xingyu Chen, Zhiwei He, Linfeng Song, Dian Yu, Juntao Li, Zhuosheng Zhang, et al. 2025. Thoughts are all over the place: On the underthinking of o1-like llms. arXiv preprint arXiv:2501.18585. [find](https://scholar.google.com/scholar?q=Yue+Wang%2C+Qiuzhi+Liu%2C+Jiahao+Xu%2C+Tian+Liang%2C+Xingyu+Chen%2C+Zhiwei+He%2C+Linfeng+Song%2C+Dian+Yu%2C+Juntao+Li%2C+Zhuosheng+Zhang%2C+et+al%2E+2025%2E+Thoughts+are+all+over+the+place%3A+On+the+underthinking+of+o1%2Dlike+ll)
49. Zhenglin Wang, Jialong Wu, Yilong Lai, Congzhi Zhang, and Deyu Zhou. 2024b. [Seed: Accelerating reasoning tree construction via scheduled speculative decoding](https://md.research.elamur.ai/free/en/papers/wang-2025-seed-accelerating-reasoning-tree-construction/). arXiv preprint arXiv:2406.18200.
50. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, brian ichter, Fei Xia, Ed Chi, Quoc V Le, An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, et al. 2024. Qwen2. 5 technical report. arXiv preprint arXiv:2412.15115. [find](https://scholar.google.com/scholar?q=Jason+Wei%2C+Xuezhi+Wang%2C+Dale+Schuurmans%2C+Maarten+Bosma%2C+brian+ichter%2C+Fei+Xia%2C+Ed+Chi%2C+Quoc+V+Le%2C+An+Yang%2C+Baosong+Yang%2C+Beichen+Zhang%2C+Binyuan+Hui%2C+Bo+Zheng%2C+Bowen+Yu%2C+Chengyuan+Li%2C+Dayiheng+Liu%2C+Fei)
51. Huanjin Yao, Jiaxing Huang, Wenhao Wu, Jingyi Zhang, Yibo Wang, Shunyu Liu, Yingjie Wang, Yuxin Song, Haocheng Feng, Li Shen, and Dacheng Tao. 2024a. Mulberry: Empowering mllm with o1-like reasoning and reflection via collective monte carlo tree search. arXiv preprint arXiv:2412.18319. — [arXiv:2412.18319](https://arxiv.org/abs/2412.18319) [find](https://scholar.google.com/scholar?q=Huanjin+Yao%2C+Jiaxing+Huang%2C+Wenhao+Wu%2C+Jingyi+Zhang%2C+Yibo+Wang%2C+Shunyu+Liu%2C+Yingjie+Wang%2C+Yuxin+Song%2C+Haocheng+Feng%2C+Li+Shen%2C+and+Dacheng+Tao%2E+2024a%2E+Mulberry%3A+Empowering+mllm+with+o1%2Dlike+reasoning+a)
52. Jinwei Yao, Kaiqi Chen, Kexun Zhang, Jiaxuan You, Binhang Yuan, Zeke Wang, and Tao Lin. 2024b. Deft: Flash tree-attention with io-awareness for efficient tree-search-based llm inference. arXiv preprint arXiv:2404.00242. [find](https://scholar.google.com/scholar?q=Jinwei+Yao%2C+Kaiqi+Chen%2C+Kexun+Zhang%2C+Jiaxuan+You%2C+Binhang+Yuan%2C+Zeke+Wang%2C+and+Tao+Lin%2E+2024b%2E+Deft%3A+Flash+tree%2Dattention+with+io%2Dawareness+for+efficient+tree%2Dsearch%2Dbased+llm+inference%2E+arXiv+preprin)
53. 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. Curran Associates, Inc. [find](https://scholar.google.com/scholar?q=Shunyu+Yao%2C+Dian+Yu%2C+Jeffrey+Zhao%2C+Izhak+Shafran%2C+Tom+Griffiths%2C+Yuan+Cao%2C+and+Karthik+Narasimhan%2E+2023%2E+Tree+of+thoughts%3A+Deliberate+problem+solving+with+large+language+models%2E+In+Advances+in+Neural+)
54. Yuan Yao, Lorenzo Rosasco, and Andrea Caponnetto. 2007. On early stopping in gradient descent learning. Constructive Approximation, 26(2):289–315. [find](https://scholar.google.com/scholar?q=Yuan+Yao%2C+Lorenzo+Rosasco%2C+and+Andrea+Caponnetto%2E+2007%2E+On+early+stopping+in+gradient+descent+learning%2E+Constructive+Approximation%2C+26%282%29%3A289%E2%80%93315%2E)
55. Dan Zhang, Sining Zhoubian, Ziniu Hu, Yisong Yue, Yuxiao Dong, and Jie Tang. 2024a. [Rest-mcts*: Llm self-training via process reward guided tree search](https://md.research.elamur.ai/free/en/papers/zhang-2024-rest-mcts-llm-self-training/). arXiv preprint arXiv:2406.03816.
56. Di Zhang, Xiaoshui Huang, Dongzhan Zhou, Yuqiang Li, and Wanli Ouyang. 2024b. Accessing gpt-4 level mathematical olympiad solutions via monte carlo tree self-refine with llama-3 8b. arXiv preprint arXiv:2406.07394. [find](https://scholar.google.com/scholar?q=Di+Zhang%2C+Xiaoshui+Huang%2C+Dongzhan+Zhou%2C+Yuqiang+Li%2C+and+Wanli+Ouyang%2E+2024b%2E+Accessing+gpt%2D4+level+mathematical+olympiad+solutions+via+monte+carlo+tree+self%2Drefine+with+llama%2D3+8b%2E+arXiv+preprint+arX)
57. Kongcheng Zhang, Qi Yao, Baisheng Lai, Jiaxing Huang, Wenkai Fang, Dacheng Tao, Mingli Song, and Shunyu Liu. 2025. Reasoning with reinforced functional token tuning. arXiv preprint arXiv:2502.13389. — [arXiv:2502.13389](https://arxiv.org/abs/2502.13389) [find](https://scholar.google.com/scholar?q=Kongcheng+Zhang%2C+Qi+Yao%2C+Baisheng+Lai%2C+Jiaxing+Huang%2C+Wenkai+Fang%2C+Dacheng+Tao%2C+Mingli+Song%2C+and+Shunyu+Liu%2E+2025%2E+Reasoning+with+reinforced+functional+token+tuning%2E+arXiv+preprint+arXiv%3A2502%2E13389%2E+%E2%80%94)
58. Zhuosheng Zhang, Aston Zhang, Mu Li, and Alex Smola. 2022. [Automatic chain of thought prompting in large language models](https://md.research.elamur.ai/free/en/papers/zhang-2022-automatic-chain-thought-prompting-large/). arXiv preprint arXiv:2210.03493.
59. Yu Zhao, Huifeng Yin, Bo Zeng, Hao Wang, Tianqi Shi, Chenyang Lyu, Longyue Wang, Weihua Luo, and Kaifu Zhang. 2024. Marco-o1: Towards open reasoning models for open-ended solutions. arXiv preprint arXiv:2411.14405. [find](https://scholar.google.com/scholar?q=Yu+Zhao%2C+Huifeng+Yin%2C+Bo+Zeng%2C+Hao+Wang%2C+Tianqi+Shi%2C+Chenyang+Lyu%2C+Longyue+Wang%2C+Weihua+Luo%2C+and+Kaifu+Zhang%2E+2024%2E+Marco%2Do1%3A+Towards+open+reasoning+models+for+open%2Dended+solutions%2E+arXiv+preprint+arX)
60. Zixuan Zhou, Xuefei Ning, Ke Hong, Tianyu Fu, Jiaming Xu, Shiyao Li, Yuming Lou, Luning Wang, Zhihang Yuan, Xiuhong Li, et al. 2024. A survey on efficient inference for large language models. arXiv preprint arXiv:2404.14294. [find](https://scholar.google.com/scholar?q=Zixuan+Zhou%2C+Xuefei+Ning%2C+Ke+Hong%2C+Tianyu+Fu%2C+Jiaming+Xu%2C+Shiyao+Li%2C+Yuming+Lou%2C+Luning+Wang%2C+Zhihang+Yuan%2C+Xiuhong+Li%2C+et+al%2E+2024%2E+A+survey+on+efficient+inference+for+large+language+models%2E+arXiv+pr)

*Updated 31 October 2026*