Elamur Research⌕
☰
home / papers / 2025 / AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time

AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time

Paper · 2025 · Junyu Zhang, Runpei Dong, Han Wang et al.

Summary

Models like OpenAI o1 and DeepSeek-R1, known as large reasoning models (LRMs), frequently overthink or underthink at inference time. Existing test-time scaling methods either lengthen reasoning (s1) or shorten it (Chain of Draft), but they rarely control the thinking budget and the timing of slow thinking together. AlphaOne (α1) is a training-free framework that handles both. A single parameter α scales the expected thinking length, and the point where generation reaches α times the model's average thinking length is called the "α moment."

Before this point, the framework inserts the transition token "wait" after paragraph breaks ("\n\n"), sampled from a Bernoulli process whose probability follows a user-chosen schedule, such as linear annealing. After the α moment, any further "wait" is swapped for "</think>," which pushes the model to stop deliberating and answer. The setup treats s1 as a special case.

Across three LRMs and six math, coding and science benchmarks, the schedule of slow thinking first and fast thinking later gave better accuracy with fewer tokens. This suggests LRMs benefit from a different pacing than the fast-then-slow pattern typical of humans.

Key points

  • α1 has two parts: Bernoulli(p_wait) insertion of "wait" before the α moment, and replacement of "wait" with "</think>" after it to switch the model to fast thinking.
  • The evaluation covered three LRMs ranging from 1.5B to 32B parameters on six reasoning benchmarks spanning mathematics, code generation and scientific reasoning.
  • α1 inserts "wait" much more densely than s1 (more than 2× as often), yet it improves results and shortens overall token output.
  • In an ablation, cutting the post-α moment step to a single operation clearly hurt performance. The authors attribute this to "slow thinking inertia" left over from the earlier phase.
  • Limitations:
    • The method depends on o1-style transition tokens such as "wait."
    • Computing the α moment requires the model's average thinking length, which the authors estimate cheaply from 10 random samples.

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

🎓University of California, BerkeleyBerkeley · United States175 works · 227,440 citations🎓University of Illinois Urbana-ChampaignUrbana · United States184 works · 69,372 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 1Research subjects and languages the work is about.Reasoning · 1,426 works

Cite

Cite as Junyu Zhang, Runpei Dong, Han Wang, Xuying Ning, Haoran Geng, Peihao Li, Xialin He, Yutong Bai, Jitendra Malik, Saurabh Gupta and Huan Zhang. 2025. AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2025.emnlp-main.570

@inproceedings{zhang2025alphaone,
  title = {{AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time}},
  author = {Junyu Zhang, Runpei Dong, Han Wang, Xuying Ning, Haoran Geng, Peihao Li, Xialin He, Yutong Bai, Jitendra Malik, Saurabh Gupta and Huan Zhang},
  booktitle = {Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing},
  year = {2025},
  doi = {10.18653/v1/2025.emnlp-main.570},
  url = {https://doi.org/10.18653/v1/2025.emnlp-main.570}
}

References

92 references, 29 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Marah Abdin, Sahaj Agarwal, Ahmed Awadallah, Vidhisha Balachandran, Harkirat Behl, Lingjiao Chen, Gustavo de Rosa, Suriya Gunasekar, Mojan Javaheripi, Neel Joshi, and 1 others. 2025. Phi-4-reasoning technical report. arXiv preprint arXiv:2504.21318. find
  2. Marah Abdin, Jyoti Aneja, Harkirat Behl, Sébastien Bubeck, Ronen Eldan, Suriya Gunasekar, Michael Harrison, Russell J. Hewett, Mojan Javaheripi, Piero Kauffmann, James R. Lee, Yin Tat Lee, Yuanzhi Li, Weishung Liu, Caio C. T. Mendes, Anh Nguyen, Eric Price, Gustavo de Rosa, Olli Saarikivi, and 8 oth… — Phi-4 Technical Report
  3. AI-MO. 2024. AIMO Validation Dataset - AMC. https://huggingface.co/datasets/AI-MO/ aimo-validation-amc. Accessed: 2025-05-19. ↗
  4. Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech, Iain Barr, Yana Hasson, Karel Lenc, Arthur Mensch, Katherine Millican, Malcolm Reynolds, Roman Ring, Eliza Rutherford, Serkan Cabi, Tengda Han, Zhitao Gong, Sina Samangooei, Marianne Monteiro, Jacob L. Menick, Sebastian Borgeaud, and 8… — Flamingo: a Visual Language Model for Few-Shot Learning
  5. Afra Amini, Tim Vieira, Elliott Ash, and Ryan Cotterell. 2025. Variational best-of-n alignment. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenReview.net. find
  6. Maciej Besta, Nils Blach, Ales Kubicek, Robert Gerstenberger, Michal Podstawski, Lukas Gianinazzi, Joanna Gajda, Tomasz Lehmann, Hubert Niewiadomski, Piotr Nyczyk, and Torsten Hoefler. 2024. Graph of thoughts: Solving elaborate problems with large language models. In Thirty-Eighth AAAI Conference on… find
  7. Rishi Bommasani, Drew A. Hudson, Ehsan Adeli, Russ Altman, Simran Arora, Sydney von Arx, Michael S. Bernstein, Jeannette Bohg, Antoine Bosselut, Emma Brunskill, Erik Brynjolfsson, Shyamal Buch, Dallas Card, Rodrigo Castellon, Niladri S. Chatterji, Annie S. Chen, Kathleen Creel, Jared Quincy Davis, D… — On the Opportunities and Risks of Foundation Models
  8. Guoxin Chen, Minpeng Liao, Chengxi Li, and Kai Fan. 2024a. Alphamath almost zero: Process supervision without process. In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, December 10 - 15, 2024…
  9. Xingyu Chen, Jiahao Xu, Tian Liang, Zhiwei He, Jianhui Pang, Dian Yu, Linfeng Song, Qiuzhi Liu, Mengfei Zhou, Zhuosheng Zhang, Rui Wang, Zhaopeng Tu, Haitao Mi, and Dong Yu. 2024b. Do NOT think that much for 2+3=? on the overthinking of o1-like llms. CoRR, abs/2412.21187.
  10. Xinyun Chen, Maxwell Lin, Nathanael Schärli, and Denny Zhou. 2024c. Teaching large language models to self-debug. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. find
  11. Yinlam Chow, Guy Tennenholtz, Izzeddin Gur, Vincent Zhuang, Bo Dai, Aviral Kumar, Rishabh Agarwal, Sridhar Thiagarajan, Craig Boutilier, and Aleksandra Faust. 2025. Inference-aware fine-tuning for best-of-n sampling in large language models. In The Thirteenth International Conference on Learning Rep… find
  12. Paul F. Christiano, Jan Leike, Tom B. Brown, Miljan Martic, Shane Legg, and Dario Amodei. 2017. Deep reinforcement learning from human preferences. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach… find
  13. 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. CoRR, abs/2110.14168.
  14. DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z. F. Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, and 81 others. 2025. Deepseek-r1: Incentivizing reasoning capability in llm…
  15. Runpei Dong, Chunrui Han, Yuang Peng, Zekun Qi, Zheng Ge, Jinrong Yang, Liang Zhao, Jianjian Sun, Hongyu Zhou, Haoran Wei, Xiangwen Kong, Xiangyu Zhang, Kaisheng Ma, and Li Yi. 2024. Dream-LLM: Synergistic multimodal comprehension and creation. In The Twelfth International Conference on Learning Rep… find
  16. Lizhe Fang, Yifei Wang, Zhaoyang Liu, Chenheng Zhang, Stefanie Jegelka, Jinyang Gao, Bolin Ding, and Yisen Wang. 2025. What is wrong with perplexity for long-context language modeling? In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. Op… find
  17. Li Fei-Fei. 2023. The Worlds I See: Curiosity, Exploration, and Discovery at the Dawn of AI. Flatiron books: a moment of lift book. find
  18. Yichao Fu, Junda Chen, Yonghao Zhuang, Zheyu Fu, Ion Stoica, and Hao Zhang. 2025. Reasoning without self-doubt: More efficient chain-of-thought through certainty probing. In ICLR 2025 Workshop on Foundation Models in the Wild. find
  19. Zitian Gao, Boye Niu, Xuzheng He, Haotian Xu, Hongzhang Liu, Aiwei Liu, Xuming Hu, and Lijie Wen. 2024. Interpretable contrastive monte carlo tree search reasoning. CoRR, abs/2410.01707. — [arXiv:2410.01707](https://arxiv.org/abs/2410.01707) find
  20. Zhibin Gou, Zhihong Shao, Yeyun Gong, Yelong Shen, Yujiu Yang, Nan Duan, and Weizhu Chen. 2024. CRITIC: large language models can self-correct with tool-interactive critiquing. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. Open-Revie…
  21. Lin Gui, Cristina Garbacea, and Victor Veitch. 2024. Bonbon alignment for large language models and the sweetness of best-of-n sampling. In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, Dece… find
  22. 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. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 2023, pages 81… find
  23. Shibo Hao, Sainbayar Sukhbaatar, DiJia Su, Xian Li, Zhiting Hu, Jason Weston, and Yuandong Tian. 2024. Training large language models to reason in a continuous latent space. CoRR, abs/2412.06769. find
  24. Chaoqun He, Renjie Luo, Yuzhuo Bai, Shengding Hu, Zhen Leng 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…
  25. Jie Huang, Xinyun Chen, Swaroop Mishra, Huaixiu Steven Zheng, Adams Wei Yu, Xinying Song, and Denny Zhou. 2024a. Large language models cannot self-correct reasoning yet. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net.
  26. Zhen Huang, Haoyang Zou, Xuefeng Li, Yixiu Liu, Yuxiang Zheng, Ethan Chern, Shijie Xia, Yiwei Qin, Weizhe Yuan, and Pengfei Liu. 2024b. O1 replication journey - part 2: Surpassing o1-preview through simple distillation, big progress or bitter lesson? CoRR, abs/2411.16489. find
  27. Aaron Jaech, Adam Kalai, Adam Lerer, Adam Richardson, Ahmed El-Kishky, Aiden Low, Alec Helyar, Aleksander Madry, Alex Beutel, Alex Carney, Alex Iftimie, Alex Karpenko, Alex Tachard Passos, Alexander Neitz, Alexander Prokofiev, Alexander Wei, Allison Tam, Ally Bennett, Ananya Kumar, and 80 others. 20… — OpenAI o1 System Card
  28. Naman Jain, King Han, Alex Gu, Wen-Ding Li, Fanjia Yan, Tianjun Zhang, Sida Wang, Armando Solar-Lezama, Koushik Sen, and Ion Stoica. 2025. Livecodebench: Holistic and contamination free evaluation of large language models for code. In The Thirteenth International Conference on Learning Representatio…
  29. Dongzhi Jiang, Ziyu Guo, Renrui Zhang, Zhuofan Zong, Hao Li, Le Zhuo, Shilin Yan, Pheng-Ann Heng, and Hongsheng Li. 2025. T2i-r1: Reinforcing image generation with collaborative semantic-level and token-level cot. arXiv preprint arXiv:2505.00703. — [arXiv:2505.00703](https://arxiv.org/abs/2505.00703) find
  30. Daniel Kahneman. 2011. macmillan. find
  31. Ryo Kamoi, Yusen Zhang, Nan Zhang, Jiawei Han, and Rui Zhang. 2024. When can llms Actually correct their own mistakes? A critical survey of self-correction of llms. Trans. Assoc. Comput. Linguistics, 12:1417–1440.
  32. Zhewei Kang, Xuandong Zhao, and Dawn Song. 2025. Scalable best-of-n selection for large language models via self-certainty. CoRR, abs/2502.18581. find
  33. Wouter Kool, Herke van Hoof, and Max Welling. 2019. Stochastic beams and where to find them: The gumbel-top-k trick for sampling sequences without replacement. In Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA, volume 97 o… find
  34. Seongyun Lee, Sue Hyun Park, Yongrae Jo, and Minjoon Seo. 2024. Volcano: Mitigating multimodal hallucination through self-feedback guided revision. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volum… find
  35. Aitor Lewkowycz, Anders Andreassen, David Dohan, Ethan Dyer, Henryk Michalewski, Vinay V. Ramasesh, Ambrose Slone, Cem Anil, Imanol Schlag, Theo Gutman-Solo, Yuhuai Wu, Behnam Neyshabur, Guy Gur-Ari, and Vedant Misra. 2022. Solving quantitative reasoning problems with language models. In Advances in…
  36. Dacheng Li, Shiyi Cao, Chengkun Cao, Xiuyu Li, Shangyin Tan, Kurt Keutzer, Jiarong Xing, Joseph E. Gonzalez, and Ion Stoica. 2025. S*: Test time scaling for code generation. CoRR, abs/2502.14382. find
  37. Baohao Liao, Yuhui Xu, Hanze Dong, Junnan Li, Christof Monz, Silvio Savarese, Doyen Sahoo, and Caiming Xiong. 2025. Reward-guided speculative decoding for efficient llm reasoning. arXiv preprint arXiv:2501.19324. — [arXiv:2501.19324](https://arxiv.org/abs/2501.19324) find
  38. 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 The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. Open-Rev…
  39. Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual instruction tuning. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023.
  40. Wenjie Ma, Jingxuan He, Charlie Snell, Tyler Griggs, Sewon Min, and Matei Zaharia. 2025. Reasoning models can be effective without thinking. arXiv preprint arXiv:2504.09858. find
  41. 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
  42. Mathematical Association of America. 2024. American Invitational Mathematics Examination – AIME. American Invitational Mathematics Examination – AIME 2024. Accessed: 2025-05-15. find
  43. Niklas Muennighoff, Zitong Yang, Weijia Shi, Xiang Lisa Li, Li Fei-Fei, Hannaneh Hajishirzi, Luke Zettlemoyer, Percy Liang, Emmanuel J. Candès, and Tatsunori Hashimoto. 2025. s1: Simple test-time scaling. CoRR, abs/2501.19393.
  44. Xuying Ning, Dongqi Fu, Tianxin Wei, Wujiang Xu, and Jingrui He. 2025. Graph4mm: Weaving multimodal learning with structural information. In Forty-second International Conference on Machine Learning. find
  45. OpenAI. 2024. Introducing gpt-4o and more tools to chatgpt free users. find
  46. OpenAI. 2025. Thinking with images. Accessed: 2025-05-25. find
  47. Xiao Pu, Michael Saxon, Wenyue Hua, and William Yang Wang. 2025. Thoughtterminator: Benchmarking, calibrating, and mitigating overthinking in reasoning models. arXiv preprint arXiv:2504.13367. — [arXiv:2504.13367](https://arxiv.org/abs/2504.13367) find
  48. Zekun Qi, Runpei Dong, Shaochen Zhang, Haoran Geng, Chunrui Han, Zheng Ge, Li Yi, and Kaisheng Ma. 2024. Shapellm: Universal 3d object understanding for embodied interaction. In Computer Vision - ECCV 2024 - 18th European Conference, Milan, Italy, September 29-October 4, 2024, Proceedings, Part XLII… find
  49. Zekun Qi, Wenyao Zhang, Yufei Ding, Runpei Dong, Xinqiang Yu, Jingwen Li, Lingyun Xu, Baoyu Li, Xialin He, Guofan Fan, Jiazhao Zhang, Jiawei He, Jiayuan Gu, Xin Jin, Kaisheng Ma, Zhizheng Zhang, He Wang, and Li Yi. 2025. Sofar: Language-grounded orientation bridges spatial reasoning and object manip… — [arXiv:2502.13143](https://arxiv.org/abs/2502.13143) find
  50. Jiahao Qiu, Yifu Lu, Yifan Zeng, Jiacheng Guo, Jiayi Geng, Huazheng Wang, Kaixuan Huang, Yue Wu, and Mengdi Wang. 2024. Treebon: Enhancing inference-time alignment with speculative tree-search and best-of-n sampling. CoRR, abs/2410.16033. find
  51. Yuxiao Qu, Matthew Y. R. Yang, Amrith Setlur, Lewis Tunstall, Edward Emanuel Beeching, Ruslan Salakhutdinov, and Aviral Kumar. 2025. Optimizing test-time compute via meta reinforcement fine-tuning. CoRR, abs/2503.07572. find
  52. Qwen Team. 2025. Preview of qwen qwen1.5-32b. https://qwenlm.github.io/blog/ qwq-32b-preview/. Accessed: 2025-03-20. ↗
  53. John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. CoRR, abs/1707.06347. find
  54. Pier Giuseppe Sessa, Robert Dadashi-Tazehozi, Léonard Hussenot, Johan Ferret, Nino Vieillard, Alexandre Ramé, Bobak Shahriari, Sarah Perrin, Abram L. Friesen, Geoffrey Cideron, Sertan Girgin, Piotr Stanczyk, Andrea Michi, Danila Sinopalnikov, Sabela Ramos Garea, Amélie Héliou, Aliaksei Severyn, Matt… find
  55. Hao Shao, Shengju Qian, Han Xiao, Guanglu Song, Zhuofan Zong, Letian Wang, Yu Liu, and Hongsheng Li. 2024a. Visual cot: Advancing multi-modal language models with a comprehensive dataset and benchmark for chain-of-thought reasoning. In The Thirty-eight Conference on Neural Information Processing Sys… find
  56. Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Mingchuan Zhang, Y. K. Li, Y. Wu, and Daya Guo. 2024b. Deepseekmath: Pushing the limits of mathematical reasoning in open language models. CoRR, abs/2402.03300.
  57. Freda Shi, Mirac Suzgun, Markus Freitag, Xuezhi Wang, Suraj Srivats, Soroush Vosoughi, Hyung Won Chung, Yi Tay, Sebastian Ruder, Denny Zhou, Dipanjan Das, and Jason Wei. 2023. Language models are multilingual chain-of-thought reasoners. In The Eleventh International Conference on Learning Representa…
  58. Jinyan Su, Jennifer Healey, Preslav Nakov, and Claire Cardie. 2025. Between underthinking and overthinking: An empirical study of reasoning length and correctness in llms. arXiv preprint arXiv:2505.00127. — [arXiv:2505.00127](https://arxiv.org/abs/2505.00127) find
  59. Yang Sui, Yu-Neng Chuang, Guanchu Wang, Jiamu Zhang, Tianyi Zhang, Jiayi Yuan, Hongyi Liu, Andrew Wen, Shaochen Zhong, Hanjie Chen, and Xia Ben Hu. 2025. Stop overthinking: A survey on efficient reasoning for large language models. CoRR, abs/2503.16419.
  60. 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. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. find
  61. Chameleon Team. 2024. Chameleon: modal early-fusion foundation models. abs/2405.09818.
  62. Mixed-CoRR, Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. 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 35: Annual Conference on Neural Informat…
  63. Yana Wei, Liang Zhao, Kangheng Lin, En Yu, Yuang Peng, Runpei Dong, Jianjian Sun, Haoran Wei, Zheng Ge, Xiangyu Zhang, and Vishal M. Patel. 2025. Perception in reflection. CoRR, abs/2504.07165. — [arXiv:2504.07165](https://arxiv.org/abs/2504.07165) find
  64. Penghao Wu and Saining Xie. 2024. V*: Guided visual search as a core mechanism in multimodal llms. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024, Seattle, WA, USA, June 16-22, 2024, pages 13084–13094. IEEE. find
  65. Jonathan Uesato, Nate Kushman, Ramana Kumar, H. Francis Song, Noah Y. Siegel, Lisa Wang, Antonia Creswell, Geoffrey Irving, and Irina Higgins. 2022. Solving math word problems with process- and outcome-based feedback. CoRR, abs/2211.14275.
  66. Yuxi Xie, Kenji Kawaguchi, Yiran Zhao, James Xu Zhao, Min-Yen Kan, Junxian He, and Michael Qizhe Xie. 2023. Self-evaluation guided beam search for reasoning. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Or…
  67. Guangya Wan, Yuqi Wu, Jie Chen, and Sheng Li. 2024a. Dynamic self-consistency: Leveraging reasoning paths for efficient LLM sampling. CoRR, abs/2408.17017. — [arXiv:2408.17017](https://arxiv.org/abs/2408.17017) find
  68. Tianyi Xiong, Xiyao Wang, Dong Guo, Qinghao Ye, Haoqi Fan, Quanquan Gu, Heng Huang, and Chunyuan Li. 2024. Llava-critic: Learning to evaluate multimodal models. CoRR, abs/2410.02712. — [arXiv:2410.02712](https://arxiv.org/abs/2410.02712) find
  69. 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, ICML 2024, Vienna, Austria, July 21-27, 2024. Open-Rev… find
  70. Silei Xu, Wenhao Xie, Lingxiao Zhao, and Pengcheng He. 2025a. Chain of draft: Thinking faster by writing less. CoRR, abs/2502.18600. find
  71. Han Wang, Gang Wang, and Huan Zhang. 2024. Steering away from harm: An adaptive approach to defending vision language model against jailbreaks. CoRR, abs/2411.16721. — [arXiv:2411.16721](https://arxiv.org/abs/2411.16721) find
  72. 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, May 1-5,…
  73. Yue Wang, Qiuzhi Liu, Jiahao Xu, Tian Liang, Xingyu Chen, Zhiwei He, Linfeng Song, Dian Yu, Juntao Li, Zhuosheng Zhang, Rui Wang, Zhaopeng Tu, Haitao Mi, and Dong Yu. 2025. Thoughts are all over the place: On the underthinking of o1-like llms. CoRR, abs/2501.18585. find
  74. Haoran Wei, Youyang Yin, Yumeng Li, Jia Wang, Liang Zhao, Jianjian Sun, Zheng Ge, and Xiangyu Zhang. 2024. Slow perception: Let’s perceive geometric figures step-by-step. CoRR, abs/2412.20631. — [arXiv:2412.20631](https://arxiv.org/abs/2412.20631) find
  75. Yuhui Xu, Hanze Dong, Lei Wang, Doyen Sahoo, Junnan Li, and Caiming Xiong. 2025b. Scalable chain of thoughts via elastic reasoning. arXiv preprint arXiv:2505.05315. — [arXiv:2505.05315](https://arxiv.org/abs/2505.05315) find
  76. Chenxu Yang, Qingyi Si, Yongjie Duan, Zheliang Zhu, Chenyu Zhu, Zheng Lin, Li Cao, and Weiping Wang. 2025a. Dynamic early exit in reasoning models. arXiv preprint arXiv:2504.15895. find
  77. Rui Yang, Hanyang Chen, Junyu Zhang, Mark Zhao, Cheng Qian, Kangrui Wang, Qineng Wang, Teja Venkat Koripella, Marziyeh Movahedi, Manling Li, Heng Ji, Huan Zhang, and Tong Zhang. 2025b. Embodiedbench: Comprehensive benchmarking multi-modal large language models for vision-driven embodied agents. CoRR… — [arXiv:2502.09560](https://arxiv.org/abs/2502.09560) find
  78. Wang Yang, Xiang Yue, Vipin Chaudhary, and Xiaotian Han. 2025c. Speculative thinking: Enhancing small-model reasoning with large model guidance at inference time. arXiv preprint arXiv:2504.12329. — [arXiv:2504.12329](https://arxiv.org/abs/2504.12329) find
  79. Wenkai Yang, Shuming Ma, Yankai Lin, and Furu Wei. 2025d. Towards thinking-optimal scaling of test-time compute for LLM reasoning. CoRR, abs/2502.18080.
  80. 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 36: Annual Conference on Neural Information Processing Systems 2023,… find
  81. En Yu, Kangheng Lin, Liang Zhao, Jisheng Yin, Yana Wei, Yuang Peng, Haoran Wei, Jianjian Sun, Chunrui Han, Zheng Ge, Xiangyu Zhang, Daxin Jiang, Jingyu Wang, and Wenbing Tao. 2025. Perception-r1: Pioneering perception policy with reinforcement learning. CoRR, abs/2504.07954. for effective and effici… — [arXiv:2504.07954](https://arxiv.org/abs/2504.07954) find
  82. Chengke Zou, Xingang Guo, Rui Yang, Junyu Zhang, Bin Hu, and Huan Zhang. 2025. Dynamath: A dynamic visual benchmark for evaluating mathematical reasoning robustness of vision language models. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2… find
  83. Yuxin Zuo, Kaiyan Zhang, Shang Qu, Li Sheng, Xuekai Zhu, Biqing Qi, Youbang Sun, Ganqu Cui, Ning Ding, and Bowen Zhou. 2025. Ttrl: Test-time reinforcement learning. CoRR, abs/2504.16084. find
  84. Fei Yu, Anningzhe Gao, and Benyou Wang. 2024. Ovm, outcome-supervised value models for planning in mathematical reasoning. In Findings of the Association for Computational Linguistics: NAACL 2024, Mexico City, Mexico, June 16-21, 2024, pages 858– 875. Association for Computational Linguistics. find
  85. Jiayi Yuan, Hao Li, Xinheng Ding, Wenya Xie, Yu-Jhe Li, Wentian Zhao, Kun Wan, Jing Shi, Xia Hu, and Zirui Liu. 2025. Give me fp32 or give me death? challenges and solutions for reproducible reasoning. arXiv preprint arXiv:2506.09501. find
  86. Eric Zelikman, Yuhuai Wu, Jesse Mu, and Noah D. Goodman. 2022. Star: Bootstrapping reasoning with reasoning. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022.
  87. Zhiyuan Zeng, Qinyuan Cheng, Zhangyue Yin, Yunhua Zhou, and Xipeng Qiu. 2025. Revisiting the test-time scaling of o1-like models: Do they truly possess test-time scaling capabilities? CoRR, abs/2502.12215.
  88. Shun Zhang, Zhenfang Chen, Yikang Shen, Mingyu Ding, Joshua B. Tenenbaum, and Chuang Gan. 2023a. Planning with large language models for code generation. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net. find
  89. Xiaotian Zhang, Chunyang Li, Yi Zong, Zhengyu Ying, Liang He, and Xipeng Qiu. 2023b. Evaluating the performance of large language models on GAOKAO benchmark. CoRR, abs/2305.12474.
  90. Jingnan Zheng, Han Wang, An Zhang, Tai D. Nguyen, Jun Sun, and Tat-Seng Chua. 2024. Ali-agent: Assessing llms’ alignment with human values via agent-based evaluation. In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 202… find
  91. Zhi Zhou, Tan Yuhao, Zenan Li, Yuan Yao, Lan-Zhe Guo, Xiaoxing Ma, and Yu-Feng Li. 2025. Bridging internal probability and self-consistency A PPENDIX A.3 find
  92. A Additional Implementation Details A.1 Computaional Budget . . . . . . . A.2 Hyper-parameters & Parameters . A.3 Benchmarks . . . . . . . . . . . . 15 15 15 15 B Additional Results B.1 Additional Models Results . . . . B.2 Scheduling Strategy . . . . . . . . B.3 Scaling Efficiency Analysis . . . .… find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/zhang-2025-alphaone-reasoning-models-thinking-slow/