---
title: "Crossing the Reward Bridge — paper by Su et al. (2026)"
description: "The paper replaces the rule with a generative verifier. 48 references. Among them: 0."
authors: ["Yi Su", "Dian Yu", "Linfeng Song", "Juntao Li", "Haitao Mi", "Zhaopeng Tu", "Min Zhang", "Dong Yu"]
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.178/"
doi: "10.18653/v1/2026.acl-long.178"
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/su-2026-crossing-reward-bridge-expanding-reinforcement/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/su-2026-crossing-reward-bridge-expanding-reinforcement/)

[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/28/) / Crossing the Reward Bridge: Expanding Reinforcement Learning with Verifiable Rewards Across Diverse Domains

# Crossing the Reward Bridge: Expanding Reinforcement Learning with Verifiable Rewards Across Diverse Domains

**Authors:** [Yi Su](https://md.research.elamur.ai/free/en/authors/yi-su/), [Dian Yu](https://md.research.elamur.ai/free/en/authors/dian-yu/), [Linfeng Song](https://md.research.elamur.ai/free/en/authors/linfeng-song/), [Juntao Li](https://md.research.elamur.ai/free/en/authors/juntao-li/), [Haitao Mi](https://md.research.elamur.ai/free/en/authors/haitao-mi/), [Zhaopeng Tu](https://md.research.elamur.ai/free/en/authors/zhaopeng-tu/), [Min Zhang](https://md.research.elamur.ai/free/en/authors/min-zhang/) and [Dong Yu](https://md.research.elamur.ai/free/en/authors/dong-yu/) · **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.178/) · [PDF](https://aclanthology.org/2026.acl-long.178.pdf) · [DOI 10.18653/v1/2026.acl-long.178](https://doi.org/10.18653/v1/2026.acl-long.178) · [OpenAlex](https://openalex.org/W7166887355)

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

## Summary

RLVR works well for math and code, where a simple rule can check whether an answer is right. Such checkers fail on free-form answers, and the authors show that rule-based rewards can even get worse as more mixed-domain training data is added. The paper replaces the rule with a generative verifier. An LLM compares the policy's final answer line with an expert reference, and the probability it assigns to "correct" becomes a soft reward between 0 and 1.

The approach rests on an observation: strong LLMs agree closely with each other and with human annotators on reference-guided correctness judgments, so reward labels can be produced automatically. The authors collect judgments from Qwen2.5-72B-Instruct on responses generated during RL exploration and distill them into a 7B reward model. They then train a Qwen2.5-7B policy on ExamQA, a Chinese multi-subject exam dataset that they rewrote as free-form English QA. The resulting policy beats far larger instruction-tuned models and transfers to out-of-distribution benchmarks. This suggests RLVR can reach fields like medicine, law and economics without human reward annotation.

## Key points

- **Data:** ExamQA (Yu et al., 2021) has 638K college-level questions across 48+ subjects. The authors removed the distractor options, translated the questions with GPT-4o-mini and held out 6,000 of them as a test set. They plan to release a 570K-example multi-domain training set.
- **Judge agreement:** GPT-4o and strong open LLMs reach Cohen's κ > 0.81 with each other and with humans when judging answers against a reference.
- **Reward model training:** The authors ran RLOO on 40K examples with four samples per prompt. Qwen2.5-72B-Instruct labeled the responses, producing 160K examples that were used to fine-tune Qwen2.5-7B-Instruct with SFT. The 40K prompts were then excluded from later training.
- **Results:** With soft rewards, the 7B policy outperforms rule-based reward baselines by 7.0%, Qwen2.5-72B-Instruct by 8.6% and DeepSeek-R1-Distill-Qwen-32B by 9.5%. The gains generalize to seven OOD benchmarks, including MATH500 and MMLU_Pro.
- **Robustness and limits:** Trends held with WebInstruct (web-user answers), NaturalReasoning (LLM-generated answers) and DeepSeek-7B. However, all training was done at 7B scale, and the agreement study covered only short reference answers.

*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

- [Tencent](https://md.research.elamur.ai/free/en/companies/tencent/) — Company, Shenzhen, China · 163 works · 21,032 citations
- [Soochow University](https://md.research.elamur.ai/free/en/universities/soochow-university/) — University, Suzhou, China · 69 works · 4,815 citations

📚 Shelves (4): [🖥️ 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

## Cite

Cite as: Yi Su, Dian Yu, Linfeng Song, Juntao Li, Haitao Mi, Zhaopeng Tu, Min Zhang and Dong Yu. 2026. Crossing the Reward Bridge: Expanding Reinforcement Learning with Verifiable Rewards Across Diverse Domains. 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{su2026crossing,
  title = {{Crossing the Reward Bridge: Expanding Reinforcement Learning with Verifiable Rewards Across Diverse Domains}},
  author = {Yi Su, Dian Yu, Linfeng Song, Juntao Li, Haitao Mi, Zhaopeng Tu, Min Zhang and Dong Yu},
  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.178},
  url = {https://doi.org/10.18653/v1/2026.acl-long.178}
}
```

- [← previous CrossGuard: Safeguarding MLLMs against Joint-Modal Implicit Malicious Attacks](https://md.research.elamur.ai/free/en/papers/zhang-2026-crossguard-safeguarding-mllms-against-joint/)
- [next → CrossOracle: An Agentic Framework for Real-Time Expert Personas with Parallelized Acoustic Synthesis](https://md.research.elamur.ai/free/en/papers/singh-2026-crossoracle-agentic-framework-real-time/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/28/)

## References

48 references, 32 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Marah Abdin, Jyoti Aneja, Harkirat Behl, Sébastien Bubeck, Ronen Eldan, Suriya Gunasekar, Michael Harrison, Russell J Hewett, Mojan Javaheripi, Piero Kauffmann, and 1 others. 2024. [Phi-4 technical report](https://md.research.elamur.ai/free/en/papers/abdin-2024-phi-4-technical-report/). arXiv preprint arXiv:2412.08905.
2. Arash Ahmadian, Chris Cremer, Matthias Gallé, Marzieh Fadaee, Julia Kreutzer, Olivier Pietquin, Ahmet Üstün, and Sara Hooker. 2024. Back to basics: Revisiting reinforce style optimization for learning from human feedback in llms. arXiv preprint arXiv:2402.14740. [find](https://scholar.google.com/scholar?q=Arash+Ahmadian%2C+Chris+Cremer%2C+Matthias+Gall%C3%A9%2C+Marzieh+Fadaee%2C+Julia+Kreutzer%2C+Olivier+Pietquin%2C+Ahmet+%C3%9Cst%C3%BCn%2C+and+Sara+Hooker%2E+2024%2E+Back+to+basics%3A+Revisiting+reinforce+style+optimization+for+learning)
3. Jacob Austin, Augustus Odena, Maxwell Nye, Maarten Bosma, Henryk Michalewski, David Dohan, Ellen Jiang, Carrie Cai, Michael Terry, Quoc Le, and 1 others. 2021. [Program synthesis with large language models](https://md.research.elamur.ai/free/en/papers/austin-2021-program-synthesis-large-language-models/). arXiv preprint arXiv:2108.07732.
4. Junying Chen, Zhenyang Cai, Ke Ji, Xidong Wang, Wanlong Liu, Rongsheng Wang, Jianye Hou, and Benyou Wang. 2024. [Huatuogpt-o1, towards medical complex reasoning with llms](https://md.research.elamur.ai/free/en/papers/chen-2024-huatuogpt-o1-towards-medical-complex/). arXiv preprint arXiv:2412.18925.
5. Mingyang Chen, Tianpeng Li, Haoze Sun, Yijie Zhou, Chenzheng Zhu, Fan Yang, Zenan Zhou, Weipeng Chen, Haofen Wang, Jeff Z Pan, and 1 others. 2025. [Learning to reason with search for llms via reinforcement learning](https://md.research.elamur.ai/free/en/papers/chen-2025-research-learning-reason-search-llms/). arXiv preprint arXiv:2503.19470.
6. Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, and 1 others. 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.
7. Jacob Steinhardt. 2021b. [Measuring mathematical problem solving with the math dataset](https://md.research.elamur.ai/free/en/papers/hendrycks-2021-measuring-mathematical-problem-solving-math/). Preprint, arXiv:2103.03874.
8. Jian Hu. 2025. [Reinforce++: A simple and efficient approach for aligning large language models](https://md.research.elamur.ai/free/en/papers/hu-2025-reinforce-stabilizing-critic-free-policy/). arXiv preprint arXiv:2501.03262.
9. Wouter Kool, Herke van Hoof, and Max Welling. 2019. Buy 4 reinforce samples, get a baseline for free! [find](https://scholar.google.com/scholar?q=Wouter+Kool%2C+Herke+van+Hoof%2C+and+Max+Welling%2E+2019%2E+Buy+4+reinforce+samples%2C+get+a+baseline+for+free%21)
10. Nathan Lambert, Jacob Morrison, Valentina Pyatkin, Shengyi Huang, Hamish Ivison, Faeze Brahman, Lester James V Miranda, Alisa Liu, Nouha Dziri, Shane Lyu, and 1 others. 2024. [T\\" ulu 3: Pushing frontiers in open language model post-training](https://md.research.elamur.ai/free/en/papers/lambert-2024-tulu-3-pushing-frontiers-open/). arXiv preprint arXiv:2411.15124.
11. Xinrun Du, Yifan Yao, Kaijing Ma, Bingli Wang, Tianyu Zheng, King Zhu, Minghao Liu, Yiming Liang, Xiaolong Jin, Zhenlin Wei, and 1 others. 2025. [Supergpqa: Scaling llm evaluation across 285 graduate disciplines](https://md.research.elamur.ai/free/en/papers/team-2025-supergpqa-scaling-llm-evaluation-across/). arXiv preprint arXiv:2502.14739.
12. Aitor Lewkowycz, Anders Andreassen, David Dohan, Ethan Dyer, Henryk Michalewski, Vinay Ramasesh, Ambrose Slone, Cem Anil, Imanol Schlag, Theo Gutman-Solo, and 1 others. 2022. [Solving quantitative reasoning problems with language models](https://md.research.elamur.ai/free/en/papers/lewkowycz-2022-solving-quantitative-reasoning-problems-language/). Advances in Neural Information Processing Systems, 35:3843–3857…
13. Kanishk Gandhi, Denise HJ Lee, Gabriel Grand, Muxin Liu, Winson Cheng, Archit Sharma, and Noah Goodman. 2024. Stream of search (sos): Learning to search in language. In First Conference on Language Modeling. [find](https://scholar.google.com/scholar?q=Kanishk+Gandhi%2C+Denise+HJ+Lee%2C+Gabriel+Grand%2C+Muxin+Liu%2C+Winson+Cheng%2C+Archit+Sharma%2C+and+Noah+Goodman%2E+2024%2E+Stream+of+search+%28sos%29%3A+Learning+to+search+in+language%2E+In+First+Conference+on+Language+Mo)
14. Long Li, Xuzheng He, Haozhe Wang, Linlin Wang, and Liang He. 2024. How do humans write code? large models do it the same way too. arXiv preprint arXiv:2402.15729. [find](https://scholar.google.com/scholar?q=Long+Li%2C+Xuzheng+He%2C+Haozhe+Wang%2C+Linlin+Wang%2C+and+Liang+He%2E+2024%2E+How+do+humans+write+code%3F+large+models+do+it+the+same+way+too%2E+arXiv+preprint+arXiv%3A2402%2E15729%2E)
15. Jonas Gehring, Kunhao Zheng, Jade Copet, Vegard Mella, Taco Cohen, and Gabriel Synnaeve. 2024. [Rlef: Grounding code llms in execution feedback with reinforcement learning](https://md.research.elamur.ai/free/en/papers/gehring-2024-rlef-grounding-code-llms-execution/). arXiv preprint arXiv:2410.02089.
16. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, 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.
17. 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.
18. Chaoqun He, Renjie Luo, Yuzhuo Bai, Shengding Hu, Zhen Leng Thai, Junhao Shen, Jinyi Hu, Xu Han, Yujie Huang, Yuxiang Zhang, and 1 others. 2024. [Olympiadbench: A challenging benchmark for promoting agi with olympiad-level bilingual multimodal scientific problems](https://md.research.elamur.ai/free/en/papers/he-2024-olympiadbench-challenging-benchmark-promoting-agi/). arXiv preprint arXiv:2402.14008.
19. Dan Hendrycks, Steven Basart, Saurav Kadavath, Mantas Mazeika, Akul Arora, Ethan Guo, Collin Burns, Samir Puranik, Horace He, Dawn Song, and 1 others. 2021a. [Measuring coding challenge competence with apps](https://md.research.elamur.ai/free/en/papers/hendrycks-2021-measuring-coding-challenge-competence-apps/). arXiv preprint arXiv:2105.09938.
20. Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and 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…
21. Jiawei Liu and Lingming Zhang. 2025. Code-r1: Reproducing r1 for code with reliable rewards. [find](https://scholar.google.com/scholar?q=Jiawei+Liu+and+Lingming+Zhang%2E+2025%2E+Code%2Dr1%3A+Reproducing+r1+for+code+with+reliable+rewards%2E)
22. Michael Luo, Sijun Tan, Justin Wong, Xiaoxiang Shi, William Y. Tang, Manan Roongta, Colin Cai, Jeffrey Luo, Tianjun Zhang, Li Erran Li, Raluca Ada Popa, and Ion Stoica. 2025. Deepscaler: Surpassing o1-preview with a 1.5b model by scaling rl. Notion Blog. [find](https://scholar.google.com/scholar?q=Michael+Luo%2C+Sijun+Tan%2C+Justin+Wong%2C+Xiaoxiang+Shi%2C+William+Y%2E+Tang%2C+Manan+Roongta%2C+Colin+Cai%2C+Jeffrey+Luo%2C+Tianjun+Zhang%2C+Li+Erran+Li%2C+Raluca+Ada+Popa%2C+and+Ion+Stoica%2E+2025%2E+Deepscaler%3A+Surpassing+o1)
23. Trung Quoc Luong, Xinbo Zhang, Zhanming Jie, Peng Sun, Xiaoran Jin, and Hang Li. 2024. [Reft: Reasoning with reinforced fine-tuning](https://md.research.elamur.ai/free/en/papers/trung-2024-reft-reasoning-reinforced-fine-tuning/). arXiv preprint arXiv:2401.08967.
24. Ruotian Ma, Peisong Wang, Cheng Liu, Xingyan Liu, Jiaqi Chen, Bang Zhang, Xin Zhou, Nan Du, and Jia Li. 2025a. S2r: Teaching llms to self-verify and self-correct via reinforcement learning. arXiv preprint arXiv:2502.12853. — [arXiv:2502.12853](https://arxiv.org/abs/2502.12853) [find](https://scholar.google.com/scholar?q=Ruotian+Ma%2C+Peisong+Wang%2C+Cheng+Liu%2C+Xingyan+Liu%2C+Jiaqi+Chen%2C+Bang+Zhang%2C+Xin+Zhou%2C+Nan+Du%2C+and+Jia+Li%2E+2025a%2E+S2r%3A+Teaching+llms+to+self%2Dverify+and+self%2Dcorrect+via+reinforcement+learning%2E+arXiv+prep)
25. Zexiong Ma, Chao Peng, Pengfei Gao, Xiangxin Meng, Yanzhen Zou, and Bing Xie. 2025b. Sorft: Issue resolving with subtask-oriented reinforced fine-tuning. arXiv preprint arXiv:2502.20127. [find](https://scholar.google.com/scholar?q=Zexiong+Ma%2C+Chao+Peng%2C+Pengfei+Gao%2C+Xiangxin+Meng%2C+Yanzhen+Zou%2C+and+Bing+Xie%2E+2025b%2E+Sorft%3A+Issue+resolving+with+subtask%2Doriented+reinforced+fine%2Dtuning%2E+arXiv+preprint+arXiv%3A2502%2E20127%2E)
26. Youssef Mroueh. 2025. Reinforcement learning with verifiable rewards: Grpo’s effective loss, dynamics, and success amplification. arXiv preprint arXiv:2503.06639. — [arXiv:2503.06639](https://arxiv.org/abs/2503.06639) [find](https://scholar.google.com/scholar?q=Youssef+Mroueh%2E+2025%2E+Reinforcement+learning+with+verifiable+rewards%3A+Grpo%E2%80%99s+effective+loss%2C+dynamics%2C+and+success+amplification%2E+arXiv+preprint+arXiv%3A2503%2E06639%2E+%E2%80%94+%5BarXiv%3A2503%2E06639%5D%28https%3A%2F%2Farxiv%2Eor)
27. Maxwell Nye, Anders Johan Andreassen, Guy Gur-Ari, Henryk Michalewski, Jacob Austin, David Bieber, David Dohan, Aitor Lewkowycz, Maarten Bosma, David Luan, and 1 others. 2021. [Show your work: Scratchpads for intermediate computation with language models](https://md.research.elamur.ai/free/en/papers/al-2021-show-your-work-scratchpads-intermediate/).
28. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, and 1 others. 2022. [Training language models to follow instructions with human feedback](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/). Advances in neural information processing systems, 35:27730–27744.
29. 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.
30. Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, YK Li, Y Wu, and 1 others. 2024. [Deepseekmath: Pushing the limits of mathematical reasoning in open language models](https://md.research.elamur.ai/free/en/papers/shao-2024-deepseekmath-pushing-limits-mathematical-reasoning/). arXiv preprint arXiv:2402.03300.
31. Nisan Stiennon, Long Ouyang, Jeffrey Wu, Daniel Ziegler, Ryan Lowe, Chelsea Voss, Alec Radford, Dario Amodei, and Paul F Christiano. 2020. Learning to summarize with human feedback. Advances in Neural Information Processing Systems, 33:3008– 3021. [find](https://scholar.google.com/scholar?q=Nisan+Stiennon%2C+Long+Ouyang%2C+Jeffrey+Wu%2C+Daniel+Ziegler%2C+Ryan+Lowe%2C+Chelsea+Voss%2C+Alec+Radford%2C+Dario+Amodei%2C+and+Paul+F+Christiano%2E+2020%2E+Learning+to+summarize+with+human+feedback%2E+Advances+in+Neural)
32. Kimi Team, Angang Du, Bofei Gao, Bowei Xing, Changjiu Jiang, Cheng Chen, Cheng Li, Chenjun Xiao, Chenzhuang Du, Chonghua Liao, and 1 others. 2025. Kimi k1. 5: Scaling reinforcement learning with llms. arXiv preprint arXiv:2501.12599. — [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://md.research.elamur.ai/free/en/papers/kimi-team-2025-kimi-k1-5-scaling-reinforcement/)
33. Ronald J Williams. 1992. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning, 8:229–256. [find](https://scholar.google.com/scholar?q=Ronald+J+Williams%2E+1992%2E+Simple+statistical+gradient%2Dfollowing+algorithms+for+connectionist+reinforcement+learning%2E+Machine+learning%2C+8%3A229%E2%80%93256%2E)
34. Tian Xie, Zitian Gao, Qingnan Ren, Haoming Luo, Yuqian Hong, Bryan Dai, Joey Zhou, Kai Qiu, Zhirong Wu, and Chong Luo. 2025. [Logic-rl: Unleashing llm reasoning with rule-based reinforcement learning](https://md.research.elamur.ai/free/en/papers/xie-2025-logic-rl-unleashing-llm/). arXiv preprint arXiv:2502.14768.
35. Wei Xiong, Hanning Zhang, Chenlu Ye, Lichang Chen, Nan Jiang, and Tong Zhang. 2025. Self-rewarding correction for mathematical reasoning. Preprint, arXiv:2502.19613. — [arXiv:2502.19613](https://arxiv.org/abs/2502.19613) [find](https://scholar.google.com/scholar?q=Wei+Xiong%2C+Hanning+Zhang%2C+Chenlu+Ye%2C+Lichang+Chen%2C+Nan+Jiang%2C+and+Tong+Zhang%2E+2025%2E+Self%2Drewarding+correction+for+mathematical+reasoning%2E+Preprint%2C+arXiv%3A2502%2E19613%2E+%E2%80%94+%5BarXiv%3A2502%2E19613%5D%28https%3A%2F%2Farxiv)
36. Dian Yu, Kai Sun, Dong Yu, and Claire Cardie. 2021. Self-teaching machines to read and comprehend with large-scale multi-subject question-answering data. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 56–68, Punta Cana, Dominican Republic. Association for Computation… [find](https://scholar.google.com/scholar?q=Dian+Yu%2C+Kai+Sun%2C+Dong+Yu%2C+and+Claire+Cardie%2E+2021%2E+Self%2Dteaching+machines+to+read+and+comprehend+with+large%2Dscale+multi%2Dsubject+question%2Danswering+data%2E+In+Findings+of+the+Association+for+Computation)
37. Qiying Yu, Zheng Zhang, Ruofei Zhu, Yufeng Yuan, Xiaochen Zuo, Yu Yue, Tiantian Fan, Gaohong Liu, Lingjun Liu, Xin Liu, and 1 others. 2025. [Dapo: An open-source llm reinforcement learning system at scale](https://md.research.elamur.ai/free/en/papers/yu-2025-dapo-open-source-llm-reinforcement/). arXiv preprint arXiv:2503.14476.
38. Weizhe Yuan, Jane Yu, Song Jiang, Karthik Padthe, Yang Li, Dong Wang, Ilia Kulikov, Kyunghyun Cho, Yuandong Tian, Jason E Weston, and 1 others. 2025. Naturalreasoning: Reasoning in the wild with 2.8 m challenging questions. arXiv preprint arXiv:2502.13124. [find](https://scholar.google.com/scholar?q=Weizhe+Yuan%2C+Jane+Yu%2C+Song+Jiang%2C+Karthik+Padthe%2C+Yang+Li%2C+Dong+Wang%2C+Ilia+Kulikov%2C+Kyunghyun+Cho%2C+Yuandong+Tian%2C+Jason+E+Weston%2C+and+1+others%2E+2025%2E+Naturalreasoning%3A+Reasoning+in+the+wild+with+2%2E8+m)
39. Xiang Yue, Tuney Zheng, Ge Zhang, and Wenhu Chen. 2024. [Mammoth2: Scaling instructions from the web](https://md.research.elamur.ai/free/en/papers/yue-2024-mammoth2-scaling-instructions-web/). arXiv preprint arXiv:2405.03548.
40. 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)
41. Eric Zelikman, Yuhuai Wu, Jesse Mu, and Noah Goodman. 2022. [Star: Bootstrapping reasoning with reasoning](https://md.research.elamur.ai/free/en/papers/zelikman-2022-star-bootstrapping-reasoning-reasoning/). Advances in Neural Information Processing Systems, 35:15476–15488.
42. Ye Tian, Baolin Peng, Linfeng Song, Lifeng Jin, Dian Yu, Lei Han, 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/). In Advances in Neural Information Processing Systems, volume 37, pages 52723–52748. Curran Associates, Inc.
43. Weihao Zeng, Yuzhen Huang, Qian Liu, Wei Liu, Keqing He, Zejun Ma, and Junxian He. 2025. [Simplerl-zoo: Investigating and taming zero reinforcement learning for open base models in the wild](https://md.research.elamur.ai/free/en/papers/zeng-2025-simplerl-zoo-investigating-taming-zero/). Preprint, arXiv:2503.18892.
44. Yubo Wang, Xueguang Ma, Ge Zhang, Yuansheng Ni, Abhranil Chandra, Shiguang Guo, Weiming Ren, Aaran Arulraj, Xuan He, Ziyan Jiang, and 1 others. 2024. [Mmlu-pro: A more robust and challenging multi-task language understanding benchmark](https://md.research.elamur.ai/free/en/papers/wang-2024-mmlu-pro-more-robust-challenging/). In The Thirty-eight Conference on Neural Information Processing S…
45. 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.
46. Lunjun Zhang, Arian Hosseini, Hritik Bansal, Mehran Kazemi, Aviral Kumar, and Rishabh Agarwal. 2024a. [Generative verifiers: Reward modeling as next-token prediction](https://md.research.elamur.ai/free/en/papers/zhang-2024-generative-verifiers-reward-modeling-as/). arXiv preprint arXiv:2408.15240.
47. Yuxiang Zhang, Yuqi Yang, Jiangming Shu, Yuhang Wang, Jinlin Xiao, and Jitao Sang. 2024b. Openrft: Adapting reasoning foundation model for domain-specific tasks with reinforcement fine-tuning. arXiv preprint arXiv:2412.16849. — [arXiv:2412.16849](https://arxiv.org/abs/2412.16849) [find](https://scholar.google.com/scholar?q=Yuxiang+Zhang%2C+Yuqi+Yang%2C+Jiangming+Shu%2C+Yuhang+Wang%2C+Jinlin+Xiao%2C+and+Jitao+Sang%2E+2024b%2E+Openrft%3A+Adapting+reasoning+foundation+model+for+domain%2Dspecific+tasks+with+reinforcement+fine%2Dtuning%2E+arXiv+p)
48. Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric Xing, and 1 others. 2023. [Judging llm-as-a-judge with mt-bench and chatbot arena](https://md.research.elamur.ai/free/en/papers/zheng-2023-judging-llm-judge-mt-bench/). Advances in Neural Information Processing Systems, 36:46595–46623.

*Updated 2 November 2026*