---
title: "Beyond Examples — paper by Wu et al. (2026)"
description: "The method has two stages: Offline: the authors define five atomic reasoning actions. 75 references."
authors: ["Jinyang Wu", "Mingkuan Feng", "Shuai Zhang", "Feihu Che", "Zhengqi Wen", "Chonghua Liao", "Ling Yang", "Haoran Luo", "Zheng Lian", "Jianhua Tao"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.135/"
doi: "10.18653/v1/2026.acl-long.135"
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/wu-2026-beyond-examples-automated-thought-level/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wu-2026-beyond-examples-automated-thought-level/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/24/) / Beyond Examples: Towards Automated Thought-level In-Context Reasoning for Large Language Models

# Beyond Examples: Towards Automated Thought-level In-Context Reasoning for Large Language Models

**Authors:** [Jinyang Wu](https://md.research.elamur.ai/free/en/authors/jinyang-wu/), [Mingkuan Feng](https://md.research.elamur.ai/free/en/authors/mingkuan-feng/), [Shuai Zhang](https://md.research.elamur.ai/free/en/authors/shuai-zhang/), [Feihu Che](https://md.research.elamur.ai/free/en/authors/feihu-che/), [Zhengqi Wen](https://md.research.elamur.ai/free/en/authors/zhengqi-wen/), [Chonghua Liao](https://md.research.elamur.ai/free/en/authors/chonghua-liao/), [Ling Yang](https://md.research.elamur.ai/free/en/authors/ling-yang/), [Haoran Luo](https://md.research.elamur.ai/free/en/authors/haoran-luo/), [Zheng Lian](https://md.research.elamur.ai/free/en/authors/zheng-lian/) and [Jianhua Tao](https://md.research.elamur.ai/free/en/authors/jianhua-tao/) · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)) · **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/2026.acl-long.135/) · [PDF](https://aclanthology.org/2026.acl-long.135.pdf) · [DOI 10.18653/v1/2026.acl-long.135](https://doi.org/10.18653/v1/2026.acl-long.135) · [OpenAlex](https://openalex.org/W7166815082)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Standard in-context learning (ICL) teaches LLMs by showing worked examples. The model then copies their surface form, which breaks down on hard multi-step problems. Results also depend heavily on how the demonstrations are chosen and ordered. ThoughtICR swaps concrete examples for abstract reasoning strategies.

The method has two stages:
- **Offline:** the authors define five atomic reasoning actions. Using only 200 seed problems, Monte Carlo Tree Search (MCTS) discovers good sequences of these actions. The sequences are clustered and stored as reusable "thought cards". Each card is described by condition complexity, number of sub-questions and problem semantics.
- **Online:** for a new problem, the closest-matching cards are retrieved to guide reasoning. A process reward model and self-consistency voting pick the final answer.

The approach was tested on nine benchmarks across seven domains, from math to agentic tasks. A 7B Qwen2.5 backbone beats GPT-4o on MATH and AMC. It costs over ten times less compute than tree-search test-time scaling methods, and it can be added on top of post-training such as GRPO. This makes strong reasoning cheaper and more automated.

## Key points
- The five actions are analyzing the problem as a whole system, reasoning in a single step, step-by-step chain-of-thought, splitting the problem into parts to solve separately (divide-and-conquer), and self-reflection with refinement. Combinations of them found by MCTS form the thought cards.
- With Qwen2.5-7B, ThoughtICR scores 80.6% on MATH and 62.5% on AMC, compared with GPT-4o's 77.2% and 57.5%. It uses more than 10× less compute than leading test-time scaling methods.
- Adding ThoughtICR to a GRPO-trained Qwen2.5-7B raises average accuracy from 57.3% to 64.2%.
- Growing the seed set from 100 to 1K samples lifts average accuracy from 56.5% to 65.5%. Using more cards at inference also keeps improving results.
- Ablations show that replacing thought cards, card matching or final verification with random or simpler alternatives lowers performance. Code: github.com/jinyangwu/ThoughtICR.

*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

- [Tsinghua University](https://md.research.elamur.ai/free/en/universities/tsinghua-university/) — University, Beijing, China · 415 works · 94,028 citations
- [Princeton University](https://md.research.elamur.ai/free/en/universities/princeton-university/) — University, Princeton, United States · 113 works · 48,612 citations
- [Nanyang Technological University](https://md.research.elamur.ai/free/en/universities/nanyang-technological-university/) — University, Singapore, Singapore · 184 works · 27,484 citations
- [Chinese Academy of Sciences](https://md.research.elamur.ai/free/en/government/chinese-academy-of-sciences/) — Government body, Beijing, China · 246 works · 24,951 citations
- [Institute of Automation](https://md.research.elamur.ai/free/en/labs/institute-of-automation/) — Research institute, Beijing, China · 87 works · 14,883 citations
- [Beijing National Research Center for Information Science and Technology](https://md.research.elamur.ai/free/en/labs/beijing-national-research-center-for-information-science-and-technology/) — Research institute, Beijing, China · 33 works · 6,706 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works

🧭 Topics (2): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,894 works · [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,685 works

## Cite

Cite as: Jinyang Wu, Mingkuan Feng, Shuai Zhang, Feihu Che, Zhengqi Wen, Chonghua Liao, Ling Yang, Haoran Luo, Zheng Lian and Jianhua Tao. 2026. Beyond Examples: Towards Automated Thought-level In-Context Reasoning for Large Language Models. Proceedings of the 64th 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{wu2026beyond,
  title = {{Beyond Examples: Towards Automated Thought-level In-Context Reasoning for Large Language Models}},
  author = {Jinyang Wu, Mingkuan Feng, Shuai Zhang, Feihu Che, Zhengqi Wen, Chonghua Liao, Ling Yang, Haoran Luo, Zheng Lian and Jianhua Tao},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.135},
  url = {https://doi.org/10.18653/v1/2026.acl-long.135}
}
```

- [← previous Beyond Divergent Creativity: A Human-Based Evaluation of Creativity in Large Language Models](https://md.research.elamur.ai/free/en/papers/nakajima-2026-beyond-divergent-creativity-human-based/)
- [next → Beyond Explicit Refusals: Soft-Failure Attacks on Retrieval-Augmented Generation](https://md.research.elamur.ai/free/en/papers/zhang-2026-beyond-explicit-refusals-soft-failure/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/24/)

## References

75 references, 33 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Ishika Agarwal, Krishnateja Killamsetty, Lucian Popa, and Marina Danilevsky. 2025. DELIFT: Data efficient language model instruction fine-tuning. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Ishika+Agarwal%2C+Krishnateja+Killamsetty%2C+Lucian+Popa%2C+and+Marina+Danilevsky%2E+2025%2E+DELIFT%3A+Data+efficient+language+model+instruction+fine%2Dtuning%2E+In+The+Thirteenth+International+Conference+on+Learning)
2. Rishabh Agarwal, Avi Singh, Lei M Zhang, Bernd Bohnet, and 1 others. 2024. Many-shot in-context Qingxiu Dong, Lei Li, Damai Dai, Ce Zheng, Jingyuan Ma, Rui Li, Heming Xia, Jingjing Xu, Zhiyong Wu, Baobao Chang, Xu Sun, Lei Li, and Zhifang Sui. 2024. [A survey on in-context learning](https://md.research.elamur.ai/free/en/papers/dong-2023-survey-context-learning/). In Proceedings of…
3. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, and 1 others. 2024. [The llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). arXiv preprint arXiv:2407.21783.
4. Luyu Gao, Aman Madaan, Shuyan Zhou, and 1 others. 2023. Pal: program-aided language models. In Proceedings of the 40th International Conference on Machine Learning. JMLR.org. [find](https://scholar.google.com/scholar?q=Luyu+Gao%2C+Aman+Madaan%2C+Shuyan+Zhou%2C+and+1+others%2E+2023%2E+Pal%3A+program%2Daided+language+models%2E+In+Proceedings+of+the+40th+International+Conference+on+Machine+Learning%2E+JMLR%2Eorg%2E)
5. Mor Geva, Daniel Khashabi, Elad Segal, Tushar Khot, Dan Roth, and Jonathan Berant. 2021. Did aristotle use a laptop? a question answering benchmark with implicit reasoning strategies. Transactions of the Association for Computational Linguistics, 9:346– 361. [find](https://scholar.google.com/scholar?q=Mor+Geva%2C+Daniel+Khashabi%2C+Elad+Segal%2C+Tushar+Khot%2C+Dan+Roth%2C+and+Jonathan+Berant%2E+2021%2E+Did+aristotle+use+a+laptop%3F+a+question+answering+benchmark+with+implicit+reasoning+strategies%2E+Transactions+of+)
6. Google DeepMind. 2024. Gemini models. [find](https://scholar.google.com/scholar?q=Google+DeepMind%2E+2024%2E+Gemini+models%2E)
7. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, and 1 others. 2025. [Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-r1-incentivizing-reasoning-capability/). arXiv preprint arXiv:2501.12948.
8. Shibo Hao, Yi Gu, Haodi Ma, Joshua Hong, Zhen Wang, Daisy 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, pages 8154–8173, Singapore. Association for Computational Lingu… [find](https://scholar.google.com/scholar?q=Shibo+Hao%2C+Yi+Gu%2C+Haodi+Ma%2C+Joshua+Hong%2C+Zhen+Wang%2C+Daisy+Wang%2C+and+Zhiting+Hu%2E+2023%2E+Reasoning+with+language+model+is+planning+with+world+model%2E+In+Proceedings+of+the+2023+Conference+on+Empirical+Met)
9. 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/). In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2).
10. Keith J Holyoak and Kyunghee Koh. 1987. Surface and structural similarity in analogical transfer. Memory & cognition, 15(4):332–340. [find](https://scholar.google.com/scholar?q=Keith+J+Holyoak+and+Kyunghee+Koh%2E+1987%2E+Surface+and+structural+similarity+in+analogical+transfer%2E+Memory+%26+cognition%2C+15%284%29%3A332%E2%80%93340%2E)
11. P. I. Jaffe, R. A. Poldrack, R. J. Schafer, and et al. 2023. Modelling human behaviour in cognitive tasks with latent dynamical systems. Nature Human Behaviour, 7:986–1000. [find](https://scholar.google.com/scholar?q=P%2E+I%2E+Jaffe%2C+R%2E+A%2E+Poldrack%2C+R%2E+J%2E+Schafer%2C+and+et+al%2E+2023%2E+Modelling+human+behaviour+in+cognitive+tasks+with+latent+dynamical+systems%2E+Nature+Human+Behaviour%2C+7%3A986%E2%80%931000%2E)
12. Daniel Kahneman. 2011. Thinking, Fast and Slow. Farrar, Straus and Giroux, New York, NY. [find](https://scholar.google.com/scholar?q=Daniel+Kahneman%2E+2011%2E+Thinking%2C+Fast+and+Slow%2E+Farrar%2C+Straus+and+Giroux%2C+New+York%2C+NY%2E)
13. 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/). Advances in neural information processing systems, 35:22199– 22213.
14. Samuel Kotz and Norman L. Johnson, editors. 1992. Breakthroughs in Statistics: Methodology and Distribution. Springer New York, New York, NY. [find](https://scholar.google.com/scholar?q=Samuel+Kotz+and+Norman+L%2E+Johnson%2C+editors%2E+1992%2E+Breakthroughs+in+Statistics%3A+Methodology+and+Distribution%2E+Springer+New+York%2C+New+York%2C+NY%2E)
15. Fong-Lok Lee and Rex Heyworth. 2000. Problem complexity: A measure of problem difficulty in algebra by using computer. Education Journal, 28(1):85– 108. [find](https://scholar.google.com/scholar?q=Fong%2DLok+Lee+and+Rex+Heyworth%2E+2000%2E+Problem+complexity%3A+A+measure+of+problem+difficulty+in+algebra+by+using+computer%2E+Education+Journal%2C+28%281%29%3A85%E2%80%93+108%2E)
16. Jia Li, Edward Beeching, Lewis Tunstall, Ben Lipkin, Roman Soletskyi, Shengyi Huang, Kashif Rasul, Longhui Yu, Albert Q. Jiang, Ziju Shen, and 1 others. 2025. Numinamath: The largest public dataset in ai4maths with 860k pairs of competition math problems and solutions. https://huggingface. co/datase… [find](https://scholar.google.com/scholar?q=Jia+Li%2C+Edward+Beeching%2C+Lewis+Tunstall%2C+Ben+Lipkin%2C+Roman+Soletskyi%2C+Shengyi+Huang%2C+Kashif+Rasul%2C+Longhui+Yu%2C+Albert+Q%2E+Jiang%2C+Ziju+Shen%2C+and+1+others%2E+2025%2E+Numinamath%3A+The+largest+public+dataset+in)
17. 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](https://md.research.elamur.ai/free/en/papers/lightman-2023-let-s-verify-step-step/). In The Twelfth International Conference on Learning Representations.
18. Hanmeng Liu, Jian Liu, Leyang Cui, Zhiyang Teng, Nan Duan, Ming Zhou, and Yue Zhang. 2023. Logiqa 2.0 - an improved dataset for logical reasoning in natural language understanding. IEEE ACM Trans. Audio Speech Lang. Process., 31:2947–2962. [find](https://scholar.google.com/scholar?q=Hanmeng+Liu%2C+Jian+Liu%2C+Leyang+Cui%2C+Zhiyang+Teng%2C+Nan+Duan%2C+Ming+Zhou%2C+and+Yue+Zhang%2E+2023%2E+Logiqa+2%2E0+%2D+an+improved+dataset+for+logical+reasoning+in+natural+language+understanding%2E+IEEE+ACM+Trans%2E+Aud)
19. Nelson F. Liu, Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Fabio Petroni, and Percy Liang. 2024. [Lost in the middle: How language models use long contexts](https://md.research.elamur.ai/free/en/papers/liu-2023-lost-middle-language-models-use/). Transactions of the Association for Computational Linguistics, 12:157–173.
20. Jianqiao Lu, Zhiyang Dou, Hongru WANG, and 1 others. 2024. [AutoPSV: Automated process-supervised verifier](https://md.research.elamur.ai/free/en/papers/lu-2024-autopsv-automated-process-supervised-verifier/). In The Thirty-eighth Annual Conference on Neural Information Processing Systems.
21. Man Luo, Xin Xu, Yue Liu, Panupong Pasupat, and Mehran Kazemi. 2024. [In-context learning with retrieved demonstrations for language models: A survey](https://md.research.elamur.ai/free/en/papers/luo-2024-context-learning-retrieved-demonstrations-language/). Transactions on Machine Learning Research. Survey Certification.
22. Meta AI. 2024. Llama: Latest models. [find](https://scholar.google.com/scholar?q=Meta+AI%2E+2024%2E+Llama%3A+Latest+models%2E)
23. Mahmoud Mohammadi, Yipeng Li, Jane Lo, and Wendy Yip. 2025. Evaluation and benchmarking of llm agents: A survey. In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 2, pages 6129–6139. [find](https://scholar.google.com/scholar?q=Mahmoud+Mohammadi%2C+Yipeng+Li%2C+Jane+Lo%2C+and+Wendy+Yip%2E+2025%2E+Evaluation+and+benchmarking+of+llm+agents%3A+A+survey%2E+In+Proceedings+of+the+31st+ACM+SIGKDD+Conference+on+Knowledge+Discovery+and+Data+Mining)
24. Marius Muja and David G. Lowe. 2014. Scalable nearest neighbor algorithms for high dimensional data. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(11):2227–2240. [find](https://scholar.google.com/scholar?q=Marius+Muja+and+David+G%2E+Lowe%2E+2014%2E+Scalable+nearest+neighbor+algorithms+for+high+dimensional+data%2E+IEEE+Transactions+on+Pattern+Analysis+and+Machine+Intelligence%2C+36%2811%29%3A2227%E2%80%932240%2E)
25. OpenAI. 2024. Hello gpt-4o. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2024%2E+Hello+gpt%2D4o%2E)
26. Davide Paglieri, Bartłomiej Cupiał, Samuel Coward, Ulyana Piterbarg, Maciej Wolczyk, Akbir Khan, Eduardo Pignatelli, Łukasz Kuciński, Lerrel Pinto, Rob Fergus, Jakob Nicolaus Foerster, Jack Parker-Holder, and Tim Rocktäschel. 2025. BALROG: Benchmarking agentic LLM and VLM reasoning on games. In The… [find](https://scholar.google.com/scholar?q=Davide+Paglieri%2C+Bart%C5%82omiej+Cupia%C5%82%2C+Samuel+Coward%2C+Ulyana+Piterbarg%2C+Maciej+Wolczyk%2C+Akbir+Khan%2C+Eduardo+Pignatelli%2C+%C5%81ukasz+Kucin%CC%81ski%2C+Lerrel+Pinto%2C+Rob+Fergus%2C+Jakob+Nicolaus+Foerster%2C+Jack+Parker%2DHo)
27. Arkil Patel, S. Bhattamishra, and Navin Goyal. 2021. [Are nlp models really able to solve simple math word problems?](https://md.research.elamur.ai/free/en/papers/patel-2021-are-nlp-models-really-able/) In North American Chapter of the Association for Computational Linguistics.
28. Ye Tian, Baolin Peng, Linfeng Song, Lifeng Jin, Dian Yu, Haitao Mi, and Dong Yu. 2024. [Toward self-improvement of llms via imagination, searching, and criticizing](https://md.research.elamur.ai/free/en/papers/tian-2024-toward-self-improvement-llms-imagination/). arXiv preprint arXiv:2404.12253.
29. Zhenting Qi, Mingyuan MA, Jiahang Xu, Li Lyna Zhang, Fan Yang, and Mao Yang. 2025. Mutual reasoning makes smaller LLMs stronger problem-solver. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Zhenting+Qi%2C+Mingyuan+MA%2C+Jiahang+Xu%2C+Li+Lyna+Zhang%2C+Fan+Yang%2C+and+Mao+Yang%2E+2025%2E+Mutual+reasoning+makes+smaller+LLMs+stronger+problem%2Dsolver%2E+In+The+Thirteenth+International+Conference+on+Learning+R)
30. Ante Wang, Linfeng Song, Ye Tian, Baolin Peng, Dian Yu, Haitao Mi, Jinsong Su, and Dong Yu. 2025. Litesearch: Efficient tree search with dynamic exploration budget for math reasoning. Proceedings of the AAAI Conference on Artificial Intelligence, 39(24):25318–25326. [find](https://scholar.google.com/scholar?q=Ante+Wang%2C+Linfeng+Song%2C+Ye+Tian%2C+Baolin+Peng%2C+Dian+Yu%2C+Haitao+Mi%2C+Jinsong+Su%2C+and+Dong+Yu%2E+2025%2E+Litesearch%3A+Efficient+tree+search+with+dynamic+exploration+budget+for+math+reasoning%2E+Proceedings+of+t)
31. Yiwei Qin, Xuefeng Li, Haoyang Zou, Yixiu Liu, Shijie Xia, Zhen Huang, Yixin Ye, Weizhe Yuan, Hector Liu, Yuanzhi Li, and 1 others. 2024. [O1 replication journey: A strategic progress report–part 1](https://md.research.elamur.ai/free/en/papers/qin-2024-o1-replication-journey-strategic-progress/). arXiv preprint arXiv:2410.18982.
32. Yuxiao Qu, Tianjun Zhang, Naman Garg, and Aviral Kumar. 2024. [Recursive introspection: Teaching language model agents how to self-improve](https://md.research.elamur.ai/free/en/papers/qu-2024-recursive-introspection-teaching-language-model/). In The Thirty-eighth Annual Conference on Neural Information Processing Systems.
33. Qwen Team. 2024. Qwen2.5: A party of foundation models. [find](https://scholar.google.com/scholar?q=Qwen+Team%2E+2024%2E+Qwen2%2E5%3A+A+party+of+foundation+models%2E)
34. Kiran Ramnath, Kang Zhou, Sheng Guan, Soumya Smruti Mishra, Xuan Qi, Zhengyuan Shen, Shuai Wang, Sangmin Woo, Sullam Jeoung, Yawei Wang, and 1 others. 2025. [A systematic survey of automatic prompt optimization techniques](https://md.research.elamur.ai/free/en/papers/ramnath-2025-systematic-survey-automatic-prompt-optimization/). arXiv preprint arXiv:2502.16923.
35. 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](https://md.research.elamur.ai/free/en/papers/rein-2023-gpqa-graduate-level-google-proof/). In First Conference on Language Modeling.
36. Stuart Russell and Eric Wefald. 1991. Principles of metareasoning. Artificial Intelligence, 49(1):361– 395. [find](https://scholar.google.com/scholar?q=Stuart+Russell+and+Eric+Wefald%2E+1991%2E+Principles+of+metareasoning%2E+Artificial+Intelligence%2C+49%281%29%3A361%E2%80%93+395%2E)
37. Fobo Shi, Peijun Qing, Dong Yang, Nan Wang, Youbo Lei, Haonan Lu, Xiaodong Lin, and Duantengchuan Li. 2024. Prompt space optimizing few-shot reasoning success with large language models. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 1836–1862, Mexico City, Mexico. A… [find](https://scholar.google.com/scholar?q=Fobo+Shi%2C+Peijun+Qing%2C+Dong+Yang%2C+Nan+Wang%2C+Youbo+Lei%2C+Haonan+Lu%2C+Xiaodong+Lin%2C+and+Duantengchuan+Li%2E+2024%2E+Prompt+space+optimizing+few%2Dshot+reasoning+success+with+large+language+models%2E+In+Findings+o)
38. Zayne Rea Sprague, Fangcong Yin, Juan Diego Rodriguez, and 1 others. 2025. [To cot or not to cot? chain-of-thought helps mainly on math and symbolic reasoning](https://md.research.elamur.ai/free/en/papers/sprague-2024-cot-cot-chain-thought-helps/). In The Thirteenth International Conference on Learning Representations.
39. Linzhuang Sun, Hao Liang, Jingxuan Wei, Bihui Yu, Conghui He, Zenan Zhou, and Wentao Zhang. 2024. Beats: Optimizing llm mathematical capabilities with backverify and adaptive disambiguate based efficient tree search. arXiv preprint arXiv:2409.17972. — [arXiv:2409.17972](https://arxiv.org/abs/2409.17972) [find](https://scholar.google.com/scholar?q=Linzhuang+Sun%2C+Hao+Liang%2C+Jingxuan+Wei%2C+Bihui+Yu%2C+Conghui+He%2C+Zenan+Zhou%2C+and+Wentao+Zhang%2E+2024%2E+Beats%3A+Optimizing+llm+mathematical+capabilities+with+backverify+and+adaptive+disambiguate+based+effici)
40. Mirac Suzgun and Adam Tauman Kalai. 2024. [Meta-prompting: Enhancing language models with task-agnostic scaffolding](https://md.research.elamur.ai/free/en/papers/suzgun-2024-meta-prompting-enhancing-language-models/). arXiv preprint arXiv:2401.12954.
41. Jindong Wang, Xixu Hu, Wenxin Hou, Hao Chen, Runkai Zheng, Yidong Wang, Linyi Yang, Wei Ye, Haojun Huang, Xiubo Geng, Binxing Jiao, Yue Zhang, and Xing Xie. 2024a. [On the robustness of chatgpt: An adversarial and out-of-distribution perspective](https://md.research.elamur.ai/free/en/papers/wang-2023-robustness-chatgpt-adversarial-out-distribution/). IEEE Data Eng. Bull., 47(1):48–62.
42. Lean Wang, Lei Li, Damai Dai, Deli Chen, Hao Zhou, Fandong Meng, Jie Zhou, and Xu Sun. 2023a. [Label words are anchors: An information flow perspective for understanding in-context learning](https://md.research.elamur.ai/free/en/papers/wang-2023-label-words-anchors-information-flow/). In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 9840–9855, Si…
43. Peiyi Wang, Lei Li, Zhihong Shao, Runxin Xu, Damai Dai, Yifei Li, Deli Chen, Yu Wu, and Zhifang Sui. 2024b. [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/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Pape…
44. Peiyi Wang, Lei Li, Zhihong Shao, and 1 others. 2024c. [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/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 9426–9439.
45. Song Wang, Zihan Chen, Chengshuai Shi, Cong Shen, and Jundong Li. 2024d. Mixture of demonstrations for in-context learning. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Song+Wang%2C+Zihan+Chen%2C+Chengshuai+Shi%2C+Cong+Shen%2C+and+Jundong+Li%2E+2024d%2E+Mixture+of+demonstrations+for+in%2Dcontext+learning%2E+In+The+Thirty%2Deighth+Annual+Conference+on+Neural+Information+Processing+Syst)
46. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V Le, Ed H. Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2023b. [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/). In The Eleventh International Conference on Learning Representations.
47. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, and 1 others. 2022. [Chain-of-thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). Advances in neural information processing systems, 35:24824– 24837.
48. Jinyang Wu, Chonghua Liao, Mingkuan Feng, Shuai Zhang, Zhengqi Wen, Haoran Luo, Ling Yang, Huazhe Xu, and Jianhua Tao. 2025. [Templaterl: Structured template-guided reinforcement learning for llm reasoning](https://md.research.elamur.ai/free/en/papers/wu-2026-templaterl-structured-template-guided-reinforcement/). arXiv preprint arXiv:2505.15692.
49. Haiteng Zhao, Qika Lin, and 1 others. 2025. [Mur: Momentum uncertainty guided reasoning for large language models](https://md.research.elamur.ai/free/en/papers/yan-2026-mur-momentum-uncertainty-guided-reasoning/). arXiv preprint arXiv:2507.14958.
50. Jinyang Wu, Shuo Yang, Changpeng Yang, Yuhao Shen, Shuai Zhang, Zhengqi Wen, and Jianhua Tao. 2026a. [Spark: Strategic policy-aware exploration via dynamic branching for long-horizon agentic learning](https://md.research.elamur.ai/free/en/papers/wu-2026-spark-strategic-policy-aware-exploration/). arXiv preprint arXiv:2601.20209.
51. An Yang, Baosong Yang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Zhou, Chengpeng Li, Chengyuan Li, Dayiheng Liu, Fei Huang, and 1 others. 2024a. Qwen2 technical report. arXiv preprint arXiv:2407.10671. [find](https://scholar.google.com/scholar?q=An+Yang%2C+Baosong+Yang%2C+Binyuan+Hui%2C+Bo+Zheng%2C+Bowen+Yu%2C+Chang+Zhou%2C+Chengpeng+Li%2C+Chengyuan+Li%2C+Dayiheng+Liu%2C+Fei+Huang%2C+and+1+others%2E+2024a%2E+Qwen2+technical+report%2E+arXiv+preprint+arXiv%3A2407%2E10671%2E)
52. Jinyang Wu, Guocheng Zhai, Ruihan Jin, Jiahao Yuan, Yuhao Shen, Shuai Zhang, Zhengqi Wen, and Jianhua Tao. 2026b. [Atlas: Orchestrating heterogeneous models and tools for multi-domain complex reasoning](https://md.research.elamur.ai/free/en/papers/wu-2026-atlas-orchestrating-heterogeneous-models-tools/). arXiv preprint arXiv:2601.03872.
53. Haoran Yang, Yumeng Zhang, Jiaqi Xu, Hongyuan Lu, Pheng-Ann Heng, and Wai Lam. 2024b. Unveiling the generalization power of fine-tuned large language models. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technolog… [find](https://scholar.google.com/scholar?q=Haoran+Yang%2C+Yumeng+Zhang%2C+Jiaqi+Xu%2C+Hongyuan+Lu%2C+Pheng%2DAnn+Heng%2C+and+Wai+Lam%2E+2024b%2E+Unveiling+the+generalization+power+of+fine%2Dtuned+large+language+models%2E+In+Proceedings+of+the+2024+Conference+of+t)
54. Siwei Wu, Zhongyuan Peng, Xinrun Du, Tuney Zheng, Minghao Liu, Jialong Wu, Jiachen Ma, Yizhi Li, Jian Yang, Wangchunshu Zhou, and 1 others. 2024a. A comparative study on reasoning patterns of openai’s o1 model. arXiv preprint arXiv:2410.13639. — [arXiv:2410.13639](https://arxiv.org/abs/2410.13639) [find](https://scholar.google.com/scholar?q=Siwei+Wu%2C+Zhongyuan+Peng%2C+Xinrun+Du%2C+Tuney+Zheng%2C+Minghao+Liu%2C+Jialong+Wu%2C+Jiachen+Ma%2C+Yizhi+Li%2C+Jian+Yang%2C+Wangchunshu+Zhou%2C+and+1+others%2E+2024a%2E+A+comparative+study+on+reasoning+patterns+of+openai%E2%80%99s)
55. Zhuofeng Wu, Richard He Bai, Aonan Zhang, Jiatao Gu, V.G.Vinod Vydiswaran, Navdeep Jaitly, and Yizhe Zhang. 2024b. Divide-or-conquer? which part should you distill your LLM? In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 2572–2585, Miami, Florida, USA. Association fo… [find](https://scholar.google.com/scholar?q=Zhuofeng+Wu%2C+Richard+He+Bai%2C+Aonan+Zhang%2C+Jiatao+Gu%2C+V%2EG%2EVinod+Vydiswaran%2C+Navdeep+Jaitly%2C+and+Yizhe+Zhang%2E+2024b%2E+Divide%2Dor%2Dconquer%3F+which+part+should+you+distill+your+LLM%3F+In+Findings+of+the+Associa)
56. Zhiheng Xi, Wenxiang Chen, Boyang Hong, Senjie Jin, Rui Zheng, Wei He, Yiwen Ding, Shichun Liu, Xin Guo, Junzhe Wang, Honglin Guo, Wei Shen, Xiaoran Fan, Yuhao Zhou, Shihan Dou, Xiao Wang, Xinbo Zhang, peng sun, Tao Gui, and 2 others. 2024. Training large language models for reasoning through revers… [find](https://scholar.google.com/scholar?q=Zhiheng+Xi%2C+Wenxiang+Chen%2C+Boyang+Hong%2C+Senjie+Jin%2C+Rui+Zheng%2C+Wei+He%2C+Yiwen+Ding%2C+Shichun+Liu%2C+Xin+Guo%2C+Junzhe+Wang%2C+Honglin+Guo%2C+Wei+Shen%2C+Xiaoran+Fan%2C+Yuhao+Zhou%2C+Shihan+Dou%2C+Xiao+Wang%2C+Xinbo+Zhang)
57. Fanzeng Xia, Yidong Luo, Tinko Sebastian Bartels, Yaqi Xu, and Tongxin Li. 2025. Rethinking the unsolvable: When in-context search meets test-time scaling. arXiv preprint arXiv:2505.22290. — [arXiv:2505.22290](https://arxiv.org/abs/2505.22290) [find](https://scholar.google.com/scholar?q=Fanzeng+Xia%2C+Yidong+Luo%2C+Tinko+Sebastian+Bartels%2C+Yaqi+Xu%2C+and+Tongxin+Li%2E+2025%2E+Rethinking+the+unsolvable%3A+When+in%2Dcontext+search+meets+test%2Dtime+scaling%2E+arXiv+preprint+arXiv%3A2505%2E22290%2E+%E2%80%94+%5BarXiv%3A25)
58. Peng Xia, Jianwen Chen, Hanyang Wang, Jiaqi Liu, Kaide Zeng, Yu Wang, Siwei Han, Yiyang Zhou, Xujiang Zhao, Haifeng Chen, and 1 others. 2026. Skillrl: Evolving agents via recursive skill-augmented reinforcement learning. arXiv preprint arXiv:2602.08234. — [arXiv:2602.08234](https://arxiv.org/abs/2602.08234) [find](https://scholar.google.com/scholar?q=Peng+Xia%2C+Jianwen+Chen%2C+Hanyang+Wang%2C+Jiaqi+Liu%2C+Kaide+Zeng%2C+Yu+Wang%2C+Siwei+Han%2C+Yiyang+Zhou%2C+Xujiang+Zhao%2C+Haifeng+Chen%2C+and+1+others%2E+2026%2E+Skillrl%3A+Evolving+agents+via+recursive+skill%2Daugmented+rei)
59. Yuxi Xie, Anirudh Goyal, Wenyue Zheng, and 1 others. 2024. Monte carlo tree search boosts reasoning via iterative preference learning. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Yuxi+Xie%2C+Anirudh+Goyal%2C+Wenyue+Zheng%2C+and+1+others%2E+2024%2E+Monte+carlo+tree+search+boosts+reasoning+via+iterative+preference+learning%2E+In+The+Thirty%2Deighth+Annual+Conference+on+Neural+Information+Proc)
60. Weihao Xuan, Rui Yang, Heli Qi, Qingcheng Zeng, Yunze Xiao, Aosong Feng, Dairui Liu, Yun Xing, Junjue Wang, Fan Gao, and 1 others. 2025. [Mmlu-prox: A multilingual benchmark for advanced large language model evaluation](https://md.research.elamur.ai/free/en/papers/xuan-2025-mmlu-prox-multilingual-benchmark-advanced/). arXiv preprint arXiv:2503.10497.
61. Hang Yan, Fangzhi Xu, Rongman Xu, Yifei Li, Jian Zhang, Haoran Luo, Xiaobao Wu, Luu Anh Tuan, Ling Yang, Zhaochen Yu, Tianjun Zhang, Shiyi Cao, Minkai Xu, Wentao Zhang, Joseph E Gonzalez, and Bin Cui. 2024c. [Buffer of thoughts: Thought-augmented reasoning with large language models](https://md.research.elamur.ai/free/en/papers/yang-2024-buffer-thoughts-thought-augmented-reasoning/). Advances in Neur…
62. Ling Yang, Zhaochen Yu, Tianjun Zhang, Minkai Xu, Joseph E. Gonzalez, Bin CUI, and Shuicheng YAN. 2025. Supercorrect: Advancing small LLM reasoning with thought template distillation and self-correction. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Ling+Yang%2C+Zhaochen+Yu%2C+Tianjun+Zhang%2C+Minkai+Xu%2C+Joseph+E%2E+Gonzalez%2C+Bin+CUI%2C+and+Shuicheng+YAN%2E+2025%2E+Supercorrect%3A+Advancing+small+LLM+reasoning+with+thought+template+distillation+and+self%2Dcorrecti)
63. Yuqing Yang, Yan Ma, and Pengfei Liu. 2024d. Weak-to-strong reasoning. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 8350–8367, Miami, Florida, USA. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Yuqing+Yang%2C+Yan+Ma%2C+and+Pengfei+Liu%2E+2024d%2E+Weak%2Dto%2Dstrong+reasoning%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+EMNLP+2024%2C+pages+8350%E2%80%938367%2C+Miami%2C+Florida%2C+USA%2E+Association+for+C)
64. 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+)
65. Alex Young, Bei Chen, Chao Li, Chengen Huang, Ge Zhang, Guanwei Zhang, Heng Li, Jiangcheng Zhu, Jianqun Chen, Jing Chang, and 1 others. 2024. [Yi: Open foundation models by 01](https://md.research.elamur.ai/free/en/papers/ai-2024-yi-open-foundation-models-01/). ai. arXiv preprint arXiv:2403.04652.
66. Lifan Yuan, Yangyi Chen, Ganqu Cui, Hongcheng Gao, FangYuan Zou, Xingyi Cheng, Heng Ji, Zhiyuan Liu, and Maosong Sun. 2023. Revisiting out-of-distribution robustness in NLP: Benchmarks, analysis, and LLMs evaluations. In Thirty-seventh Conference on Neural Information Processing Systems Datasets and… [find](https://scholar.google.com/scholar?q=Lifan+Yuan%2C+Yangyi+Chen%2C+Ganqu+Cui%2C+Hongcheng+Gao%2C+FangYuan+Zou%2C+Xingyi+Cheng%2C+Heng+Ji%2C+Zhiyuan+Liu%2C+and+Maosong+Sun%2E+2023%2E+Revisiting+out%2Dof%2Ddistribution+robustness+in+NLP%3A+Benchmarks%2C+analysis%2C+and+)
67. Yang Yue, Zhiqi Chen, Rui Lu, Andrew Zhao, Zhaokai Wang, Shiji Song, and Gao Huang. 2025. [Does reinforcement learning really incentivize reasoning capacity in llms beyond the base model?](https://md.research.elamur.ai/free/en/papers/yue-2025-reinforcement-learning-really-incentivize-reasoning/) arXiv preprint arXiv:2504.13837.
68. 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/). Advances in Neural Information Processing Systems.
69. Di Zhang, Jiatong Li, 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+Jiatong+Li%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+)
70. Di Zhang, Jianbo Wu, Jingdi Lei, Tong Che, and 1 others. 2025. LLaMA-berry: Pairwise optimization for olympiad-level mathematical reasoning via o1-like Monte Carlo tree search. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguisti… [find](https://scholar.google.com/scholar?q=Di+Zhang%2C+Jianbo+Wu%2C+Jingdi+Lei%2C+Tong+Che%2C+and+1+others%2E+2025%2E+LLaMA%2Dberry%3A+Pairwise+optimization+for+olympiad%2Dlevel+mathematical+reasoning+via+o1%2Dlike+Monte+Carlo+tree+search%2E+In+Proceedings+of+the+2)
71. Xuan Zhang, Chao Du, Tianyu Pang, Qian Liu, Wei Gao, and Min Lin. 2024c. Chain of preference optimization: Improving chain-of-thought reasoning in LLMs. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Xuan+Zhang%2C+Chao+Du%2C+Tianyu+Pang%2C+Qian+Liu%2C+Wei+Gao%2C+and+Min+Lin%2E+2024c%2E+Chain+of+preference+optimization%3A+Improving+chain%2Dof%2Dthought+reasoning+in+LLMs%2E+In+The+Thirty%2Deighth+Annual+Conference+on+Neura)
72. Anhao Zhao, Fanghua Ye, Jinlan Fu, and Xiaoyu Shen. 2024. Unveiling in-context learning: A coordinate system to understand its working mechanism. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 12375– 12400, Miami, Florida, USA. Association for Comput… [find](https://scholar.google.com/scholar?q=Anhao+Zhao%2C+Fanghua+Ye%2C+Jinlan+Fu%2C+and+Xiaoyu+Shen%2E+2024%2E+Unveiling+in%2Dcontext+learning%3A+A+coordinate+system+to+understand+its+working+mechanism%2E+In+Proceedings+of+the+2024+Conference+on+Empirical+Met)
73. Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, and 1 others. 2023. [A survey of large language models](https://md.research.elamur.ai/free/en/papers/zhao-2023-survey-large-language-models/). arXiv preprint arXiv:2303.18223.
74. Andy Zhou, Kai Yan, Michal Shlapentokh-Rothman, Haohan Wang, and Yu-Xiong Wang. 2024a. Language agent tree search unifies reasoning, acting, and planning in language models. In Forty-first International Conference on Machine Learning. [find](https://scholar.google.com/scholar?q=Andy+Zhou%2C+Kai+Yan%2C+Michal+Shlapentokh%2DRothman%2C+Haohan+Wang%2C+and+Yu%2DXiong+Wang%2E+2024a%2E+Language+agent+tree+search+unifies+reasoning%2C+acting%2C+and+planning+in+language+models%2E+In+Forty%2Dfirst+Internation)
75. Yuxiang Zhou, Jiazheng Li, Yanzheng Xiang, Hanqi Yan, Lin Gui, and Yulan He. 2024b. The mystery of in-context learning: A comprehensive survey on interpretation and analysis. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 14365–14378, Miami, Florida,… [find](https://scholar.google.com/scholar?q=Yuxiang+Zhou%2C+Jiazheng+Li%2C+Yanzheng+Xiang%2C+Hanqi+Yan%2C+Lin+Gui%2C+and+Yulan+He%2E+2024b%2E+The+mystery+of+in%2Dcontext+learning%3A+A+comprehensive+survey+on+interpretation+and+analysis%2E+In+Proceedings+of+the+202)

*Updated 2 November 2026*