---
title: "Writing-RL — paper by Lei et al. (2026) — summary and ideas"
description: "The authors propose Writing-RL, a curriculum-based reinforcement learning framework applied on top… 43 references, cited by 4 papers here."
authors: ["Xuanyu Lei", "Chenliang Li", "Yuning Wu", "Kaiming Liu", "Weizhou Shen", "Peng Li", "Ming Yan", "Fei Huang", "Ya-Qin Zhang", "Yang Liu"]
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.255/"
doi: "10.18653/v1/2026.acl-long.255"
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/lei-2026-writing-rl-advancing-long-form/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/lei-2026-writing-rl-advancing-long-form/)

[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/5/) / Writing-RL: Advancing Long-form Writing via Adaptive Curriculum Reinforcement Learning

# Writing-RL: Advancing Long-form Writing via Adaptive Curriculum Reinforcement Learning

**Authors:** [Xuanyu Lei](https://md.research.elamur.ai/free/en/authors/xuanyu-lei/), [Chenliang Li](https://md.research.elamur.ai/free/en/authors/chenliang-li/), Yuning Wu, Kaiming Liu, [Weizhou Shen](https://md.research.elamur.ai/free/en/authors/weizhou-shen/), [Peng Li](https://md.research.elamur.ai/free/en/authors/peng-li/), [Ming Yan](https://md.research.elamur.ai/free/en/authors/ming-yan/), [Fei Huang](https://md.research.elamur.ai/free/en/authors/fei-huang/), Ya-Qin Zhang and [Yang Liu](https://md.research.elamur.ai/free/en/authors/yang-liu/) · **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.255/) · [PDF](https://aclanthology.org/2026.acl-long.255.pdf) · [DOI 10.18653/v1/2026.acl-long.255](https://doi.org/10.18653/v1/2026.acl-long.255) · [OpenAlex](https://openalex.org/W4417097313)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · [4](https://md.research.elamur.ai/free/en/papers/lei-2026-writing-rl-advancing-long-form/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Large language models can now produce long articles, but further gains are hard to get. Supervised fine-tuning stalls because it can only imitate teacher or human outputs, and the RL recipes that work for math and code need verifiable answers that open-ended writing lacks. The authors propose Writing-RL, a curriculum-based reinforcement learning framework applied on top of SFT-trained 7B writer models. It has three parts:

- **Margin-aware Data Selection** keeps prompts where the policy's answer falls furthest below the best answer from a pool of competing LLMs, as rated by a multi-dimensional LLM judge.
- **Pairwise Comparison Reward** gives reward only when the policy's output beats a reference text.
- **Dynamic Reference Scheduling** assigns each prompt a ladder of references of rising quality and moves up a step once the model wins.

Starting from Qwen2.5-7B-WritingBench-SFT, the method improves scores on writing benchmarks while leaving general ability intact. Unexpectedly, training on short-input, long-output tasks also helps long-input reasoning, which suggests a new way to approach long-context training.

## Key points
- **Main result:** with Qwen-Plus as judge, the average score over WritingBench, Creative and LongBench-Write rises from 82.17 (SFT) to 84.49. Using DeepSeek-V3 as judge gives a similar 84.30, so the gain does not depend on the choice of judge.
- **Static references fall short:** self-generated references saturate the reward too quickly, while a fixed "Best Reference" set makes positive rewards too rare and scores only 82.51. In the curriculum ablation, dynamic scheduling beats both static scheduling and training with no curriculum.
- **Output-to-input generalization:** the RL model was trained on inputs under 1k tokens, yet it improves on long-text reasoning tasks with inputs from 8k to 2M tokens. The SFT model degrades on the same tasks.
- **General ability and cost:** MMLU is roughly unchanged. Constructing the dataset is a one-time expense of roughly $609 for API usage plus 76 hours of GPU compute. Each RL run then needs about $54 for the judge and 24×8 GPU hours.
- **Code:** released at GitHub, Tongyi-Zhiwen/Writing-RL.

*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
- [Alibaba Group](https://md.research.elamur.ai/free/en/companies/alibaba-group/) — Company, Hangzhou, China · 201 works · 17,173 citations

📚 Shelves (6): [🖥️ 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 · [🤝 Social Sciences](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · 1,954 works · [🎓 Education](https://md.research.elamur.ai/free/en/shelves/social-sciences/education/) · 212 works

## Cite

Cite as: Xuanyu Lei, Chenliang Li, Yuning Wu, Kaiming Liu, Weizhou Shen, Peng Li, Ming Yan, Fei Huang, Ya-Qin Zhang and Yang Liu. 2026. Writing-RL: Advancing Long-form Writing via Adaptive Curriculum Reinforcement Learning. 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{lei2026writing,
  title = {{Writing-RL: Advancing Long-form Writing via Adaptive Curriculum Reinforcement Learning}},
  author = {Xuanyu Lei, Chenliang Li, Yuning Wu, Kaiming Liu, Weizhou Shen, Peng Li, Ming Yan, Fei Huang, Ya-Qin Zhang and Yang Liu},
  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.255},
  url = {https://doi.org/10.18653/v1/2026.acl-long.255}
}
```

- [← previous Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets](https://md.research.elamur.ai/free/en/papers/hsiung-2026-why-llm-safety-guardrails-collapse/)
- [next → X-ray Made Simple: Lay Radiology Report Generation and Robust Evaluation](https://md.research.elamur.ai/free/en/papers/zhao-2026-x-ray-made-simple-lay/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/5/)

## References

43 references, 28 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Anthropic Team. 2025. Claude 3.7 sonnet system card. [https://assets.anthropic.com/m/785e231869ea8b3b/original/](https://assets.anthropic.com/m/785e231869ea8b3b/original/) claude-3-7-sonnet-system-card.pdf. [↗](https://assets.anthropic.com/m/785e231869ea8b3b/original/)
2. Sanghwan Bae, Jiwoo Hong, Min Young Lee, Hanbyul Kim, JeongYeon Nam, and Donghyun Kwak. 2025. [Online difficulty filtering for reasoning oriented reinforcement learning](https://md.research.elamur.ai/free/en/papers/bae-2026-online-difficulty-filtering-reasoning-oriented/). arXiv preprint arXiv:2504.03380.
3. Yushi Bai, Shangqing Tu, Jiajie Zhang, Hao Peng, Xiaozhi Wang, Xin Lv, Shulin Cao, Jiazheng Xu, Lei Hou, Yuxiao Dong, Jie Tang, and Juanzi Li. 2024a. [LongBench v2: Towards deeper understanding and reasoning on realistic long-context multitasks](https://md.research.elamur.ai/free/en/papers/bai-2024-longbench-v2-deeper-understanding/). CoRR, abs/2412.15204.
4. Yushi Bai, Jiajie Zhang, Xin Lv, Linzhi Zheng, Siqi Zhu, Lei Hou, Yuxiao Dong, Jie Tang, and Juanzi Li. 2024b. [LongWriter: Unleashing 10,000+ word generation from long context LLMs](https://md.research.elamur.ai/free/en/papers/bai-2024-longwriter-unleashing-10-000/). CoRR, abs/2408.07055.
5. Yoshua Bengio, Jérôme Louradour, Ronan Collobert, and Jason Weston. 2009. [Curriculum learning](https://md.research.elamur.ai/free/en/papers/bengio-2009-curriculum-learning/). In Proceedings of the 26th Annual International Conference on Machine Learning, ICML 2009, Montreal, Quebec, Canada, June 14-18, 2009, volume 382 of ACM International Conference Proceeding Series, pages 41…
6. Yi Cheng, Siyao Li, Bang Liu, Ruihui Zhao, Sujian Li, Chenghua Lin, and Yefeng Zheng. 2021. Guiding the growth: Difficulty-controllable question generation through step-by-step rewriting. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th Internat… [find](https://scholar.google.com/scholar?q=Yi+Cheng%2C+Siyao+Li%2C+Bang+Liu%2C+Ruihui+Zhao%2C+Sujian+Li%2C+Chenghua+Lin%2C+and+Yefeng+Zheng%2E+2021%2E+Guiding+the+growth%3A+Difficulty%2Dcontrollable+question+generation+through+step%2Dby%2Dstep+rewriting%2E+In+Proceedin)
7. Tianzhe Chu, Yuexiang Zhai, Jihan Yang, Shengbang Tong, Saining Xie, Dale Schuurmans, Quoc V. Le, Sergey Levine, and Yi Ma. 2025. [SFT memorizes, RL generalizes: A comparative study of foundation model post-training](https://md.research.elamur.ai/free/en/papers/chu-2025-sft-memorizes-rl-generalizes-comparative/). CoRR, abs/2501.17161.
8. 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…](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-r1-incentivizing-reasoning-capability/)
9. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, Archi Mitra, Archie Sravankumar, Artem Korenev, Arthur Hinsvark, Arun Rao, Aston Zhang, and 82 others. 2024… — [The Llama 3 Herd of Models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/)
10. Kanishk Gandhi, Ayush Chakravarthy, Anikait Singh, Nathan Lile, and Noah D. Goodman. 2025. [Cognitive behaviors that enable self-improving reasoners, or, four habits of highly effective stars](https://md.research.elamur.ai/free/en/papers/gandhi-2025-cognitive-behaviors-that-enable-self/). CoRR, abs/2503.01307.
11. Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2021a. [Measuring massive multitask language understanding](https://md.research.elamur.ai/free/en/papers/hendrycks-2020-measuring-massive-multitask-language-understanding/). In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net.
12. Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and 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/). In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, NeurIPS 5648 10
13. Datasets and Benchmarks 2021, December 2021, virtual. [find](https://scholar.google.com/scholar?q=Datasets+and+Benchmarks+2021%2C+December+2021%2C+virtual%2E)
14. Aaron Hurst, Adam Lerer, Adam P. Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, Aleksander Madry, Alex Baker-Whitcomb, Alex Beutel, Alex Borzunov, Alex Carney, Alex Chow, Alex Kirillov, Alex Nichol, Alex Paino, and 79 others. 2024. [GPT-4o sy…](https://md.research.elamur.ai/free/en/papers/openai-2024-gpt-4o-system-card/)
15. Shanghaoran Quan, Tianyi Tang, Bowen Yu, An Yang, Dayiheng Liu, Bofei Gao, Jianhong Tu, Yichang Zhang, Jingren Zhou, and Junyang Lin. 2024. [Language models can self-lengthen to generate long texts](https://md.research.elamur.ai/free/en/papers/quan-2024-language-models-self-lengthen-generate/). CoRR, abs/2410.23933.
16. Pei Ke, Bosi Wen, Andrew Feng, Xiao Liu, Xuanyu Lei, Jiale Cheng, Shengyuan Wang, Aohan Zeng, Yuxiao Dong, Hongning Wang, Jie Tang, and Minlie Huang. 2024. [CritiqueLLM: Towards an informative critique generation model for evaluation of large language model generation](https://md.research.elamur.ai/free/en/papers/ke-2023-critiquellm-informative-critique-generation/). In Proceedings of the 62nd Annu…
17. Haoran Que, Feiyu Duan, Liqun He, Yutao Mou, Wangchunshu Zhou, Jiaheng Liu, Wenge Rong, Zekun Moore Wang, Jian Yang, Ge Zhang, Junran Peng, Zhaoxiang Zhang, Songyang Zhang, and Kai Chen. 2024. HelloBench: Evaluating long text generation capabilities of large language models. CoRR, abs/2409.16191. — [arXiv:2409.16191](https://arxiv.org/abs/2409.16191) [find](https://scholar.google.com/scholar?q=Haoran+Que%2C+Feiyu+Duan%2C+Liqun+He%2C+Yutao+Mou%2C+Wangchunshu+Zhou%2C+Jiaheng+Liu%2C+Wenge+Rong%2C+Zekun+Moore+Wang%2C+Jian+Yang%2C+Ge+Zhang%2C+Junran+Peng%2C+Zhaoxiang+Zhang%2C+Songyang+Zhang%2C+and+Kai+Chen%2E+2024%2E+HelloBe)
18. Xiao Liu, Xuanyu Lei, Shengyuan Wang, Yue Huang, Andrew Feng, Bosi Wen, Jiale Cheng, Pei Ke, Yifan Xu, Weng Lam Tam, Xiaohan Zhang, Lichao Sun, Xiaotao Gu, Hongning Wang, Jing Zhang, Minlie Huang, Yuxiao Dong, and Jie Tang. 2024. [AlignBench: Benchmarking chinese alignment of large language models](https://md.research.elamur.ai/free/en/papers/liu-2023-alignbench-benchmarking-chinese-alignment/). I…
19. Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Mingchuan Zhang, Y. K. Li, Y. Wu, and Daya Guo. 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/). CoRR, abs/2402.03300.
20. Zijun Liu, Peiyi Wang, Runxin Xu, Shirong Ma, Chong Ruan, Peng Li, Yang Liu, and Yu Wu. 2025. [Inference-time scaling for generalist reward modeling](https://md.research.elamur.ai/free/en/papers/liu-2025-inference-time-scaling-generalist/). Preprint, arXiv:2504.02495.
21. Guangming Sheng, Chi Zhang, Zilingfeng Ye, Xibin Wu, Wang Zhang, Ru Zhang, Yanghua Peng, Haibin Lin, and Chuan Wu. 2024. [HybridFlow: A flexible and efficient RLHF framework](https://md.research.elamur.ai/free/en/papers/sheng-2024-hybridflow-flexible-efficient-rlhf-framework/). arXiv preprint arXiv: 2409.19256.
22. Michael Luo, Sijun Tan, Justin Wong, Xiaoxiang Shi, William Y. Tang, Manan Roongta, Colin Cai, Jeffrey Luo, 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+Li+Erran+Li%2C+Raluca+Ada+Popa%2C+and+Ion+Stoica%2E+2025%2E+DeepScaleR%3A+Surpassing+O1%2DPreview+with+a)
23. Taiwei Shi, Yiyang Wu, Linxin Song, Tianyi Zhou, and Jieyu Zhao. 2025. Efficient reinforcement finetuning via adaptive curriculum learning. arXiv preprint arXiv:2504.05520. — [arXiv:2504.05520](https://arxiv.org/abs/2504.05520) [find](https://scholar.google.com/scholar?q=Taiwei+Shi%2C+Yiyang+Wu%2C+Linxin+Song%2C+Tianyi+Zhou%2C+and+Jieyu+Zhao%2E+2025%2E+Efficient+reinforcement+finetuning+via+adaptive+curriculum+learning%2E+arXiv+preprint+arXiv%3A2504%2E05520%2E+%E2%80%94+%5BarXiv%3A2504%2E05520%5D%28https%3A)
24. Pratyush Maini, Skyler Seto, Richard He Bai, David Grangier, Yizhe Zhang, and Navdeep Jaitly. 2024. [Rephrasing the web: A recipe for compute and data-efficient language modeling](https://md.research.elamur.ai/free/en/papers/maini-2024-rephrasing-web-recipe-compute-data/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2…
25. OpenAI. 2023. [GPT-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). abs/2303.08774.
26. CoRR, Samuel J. Paech. 2023. [EQ-Bench: An emotional intelligence benchmark for large language models](https://md.research.elamur.ai/free/en/papers/paech-2023-eq-bench-emotional-intelligence-benchmark/). CoRR, abs/2312.06281.
27. Chau Pham, Simeng Sun, and Mohit Iyyer. 2024. Suri: Multi-constraint instruction following in long-form John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. CoRR, abs/1707.06347. [find](https://scholar.google.com/scholar?q=Chau+Pham%2C+Simeng+Sun%2C+and+Mohit+Iyyer%2E+2024%2E+Suri%3A+Multi%2Dconstraint+instruction+following+in+long%2Dform+John+Schulman%2C+Filip+Wolski%2C+Prafulla+Dhariwal%2C+Alec+Radford%2C+and+Oleg+Klimov%2E+2017%2E+Proximal+po)
28. Haozhan Shen, Peng Liu, Jingcheng Li, Chunxin Fang, Yibo Ma, Jiajia Liao, Qiaoli Shen, Zilun Zhang, Kangjia Zhao, Qianqian Zhang, and 1 others. 2025. [Vlm-r1: A stable and generalizable r1-style large vision-language model](https://md.research.elamur.ai/free/en/papers/shen-2025-vlm-r1-stable-generalizable-r1/). arXiv preprint arXiv:2504.07615.
29. Mingyang Song, Mao Zheng, Zheng Li, Wenjie Yang, Xuan Luo, Yue Pan, and Feng Zhang. 2025. FastCuRL: Curriculum reinforcement learning with progressive context extension for efficient training R1-like reasoning models. CoRR, abs/2503.17287. — [arXiv:2503.17287](https://arxiv.org/abs/2503.17287) [find](https://scholar.google.com/scholar?q=Mingyang+Song%2C+Mao+Zheng%2C+Zheng+Li%2C+Wenjie+Yang%2C+Xuan+Luo%2C+Yue+Pan%2C+and+Feng+Zhang%2E+2025%2E+FastCuRL%3A+Curriculum+reinforcement+learning+with+progressive+context+extension+for+efficient+training+R1%2Dlike+)
30. Kimi Team, Angang Du, Bofei Gao, Bowei Xing, Changjiu Jiang, Cheng Chen, Cheng Li, Chenjun Xiao, Chenzhuang Du, Chonghua Liao, Chuning Tang, Congcong Wang, Dehao Zhang, Enming Yuan, Enzhe Lu, Fengxiang Tang, Flood Sung, Guangda Wei, Guokun Lai, and 75 others. 2025. [Kimi k1.5: Scaling reinforcement l…](https://md.research.elamur.ai/free/en/papers/kimi-team-2025-kimi-k1-5-scaling-reinforcement/)
31. Shangqing Tu, Yucheng Wang, Daniel Zhang-Li, Yushi Bai, Jifan Yu, Yuhao Wu, Lei Hou, Huiqin Liu, Zhiyuan Liu, Bin Xu, and Juanzi Li. 2025. LongWriter-V: Enabling ultra-long and high-fidelity 5649 11 generation in vision-language models. abs/2502.14834. — [arXiv:2502.14834](https://arxiv.org/abs/2502.14834) [find](https://scholar.google.com/scholar?q=Shangqing+Tu%2C+Yucheng+Wang%2C+Daniel+Zhang%2DLi%2C+Yushi+Bai%2C+Jifan+Yu%2C+Yuhao+Wu%2C+Lei+Hou%2C+Huiqin+Liu%2C+Zhiyuan+Liu%2C+Bin+Xu%2C+and+Juanzi+Li%2E+2025%2E+LongWriter%2DV%3A+Enabling+ultra%2Dlong+and+high%2Dfidelity+5649+11+g)
32. CoRR, learning for advanced reasoning tasks. arXiv preprint arXiv:2504.05118. Tiannan Wang, Jiamin Chen, Qingrui Jia, Shuai Wang, Ruoyu Fang, Huilin Wang, Zhaowei Gao, Chunzhao Xie, Chuou Xu, Jihong Dai, Yibin Liu, Jialong Wu, Shengwei Ding, Long Li, Zhiwei Huang, Xinle Deng, Teng Yu, Gangan Ma, Han… — [VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks](https://md.research.elamur.ai/free/en/papers/yue-2025-vapo-efficient-reliable-reinforcement-learning/)
33. Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, Yifan Du, Chen Yang, Yushuo Chen, Zhipeng Chen, Jinhao Jiang, Ruiyang Ren, Yifan Li, Xinyu Tang, Zikang Liu, and 3 others. 2023. [A survey of large language models](https://md.research.elamur.ai/free/en/papers/zhao-2023-survey-large-language-models/). CoRR,…
34. Liang Wen, Yunke Cai, Fenrui Xiao, Xin He, Qi An, Zhenyu Duan, Yimin Du, Junchen Liu, Lifu Tang, Xiaowei Lv, Haosheng Zou, Yongchao Deng, Shousheng Jia, and Xiangzheng Zhang. 2025. [Light-R1: Curriculum SFT, DPO and RL for long COT from scratch and beyond](https://md.research.elamur.ai/free/en/papers/wen-2025-light-r1-curriculum-sft-dpo/). CoRR, abs/2503.10460.
35. Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric P. Xing, Hao Zhang, Joseph E. Gonzalez, and Ion Stoica. 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/). In Advances in Neural Information Processing Systems 36: A…
36. Yuhao Wu, Yushi Bai, Zhiqiang Hu, Roy Ka-Wei Lee, and Juanzi Li. 2025a. Longwriter-zero: Mastering ultra-long text generation via reinforcement learning. CoRR, abs/2506.18841. — [arXiv:2506.18841](https://arxiv.org/abs/2506.18841) [find](https://scholar.google.com/scholar?q=Yuhao+Wu%2C+Yushi+Bai%2C+Zhiqiang+Hu%2C+Roy+Ka%2DWei+Lee%2C+and+Juanzi+Li%2E+2025a%2E+Longwriter%2Dzero%3A+Mastering+ultra%2Dlong+text+generation+via+reinforcement+learning%2E+CoRR%2C+abs%2F2506%2E18841%2E+%E2%80%94+%5BarXiv%3A2506%2E18841%5D%28htt)
37. Yuhao Wu, Yushi Bai, Zhiqing Hu, Shangqing Tu, Ming Shan Hee, Juanzi Li, and Roy Ka-Wei Lee. 2025b. Shifting long-context LLMs research from input to output. CoRR, abs/2503.04723. — [arXiv:2503.04723](https://arxiv.org/abs/2503.04723) [find](https://scholar.google.com/scholar?q=Yuhao+Wu%2C+Yushi+Bai%2C+Zhiqing+Hu%2C+Shangqing+Tu%2C+Ming+Shan+Hee%2C+Juanzi+Li%2C+and+Roy+Ka%2DWei+Lee%2E+2025b%2E+Shifting+long%2Dcontext+LLMs+research+from+input+to+output%2E+CoRR%2C+abs%2F2503%2E04723%2E+%E2%80%94+%5BarXiv%3A2503%2E04723%5D)
38. Yuning Wu, Jiahao Mei, Ming Yan, Chenliang Li, Shaopeng Lai, Yuran Ren, Zijia Wang, Ji Zhang, Mengyue Wu, Qin Jin, and Fei Huang. 2025c. WritingBench: A comprehensive benchmark for generative writing. CoRR, abs/2503.05244. — [arXiv:2503.05244](https://arxiv.org/abs/2503.05244) [find](https://scholar.google.com/scholar?q=Yuning+Wu%2C+Jiahao+Mei%2C+Ming+Yan%2C+Chenliang+Li%2C+Shaopeng+Lai%2C+Yuran+Ren%2C+Zijia+Wang%2C+Ji+Zhang%2C+Mengyue+Wu%2C+Qin+Jin%2C+and+Fei+Huang%2E+2025c%2E+WritingBench%3A+A+comprehensive+benchmark+for+generative+writing%2E)
39. 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/). CoRR, abs/2502.14768.
40. An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, Junyang Lin, Kai Dang, and 22 others. 2024. Qwen2.5 technical report. CoRR, abs/2412.1511… [find](https://scholar.google.com/scholar?q=An+Yang%2C+Baosong+Yang%2C+Beichen+Zhang%2C+Binyuan+Hui%2C+Bo+Zheng%2C+Bowen+Yu%2C+Chengyuan+Li%2C+Dayiheng+Liu%2C+Fei+Huang%2C+Haoran+Wei%2C+Huan+Lin%2C+Jian+Yang%2C+Jianhong+Tu%2C+Jianwei+Zhang%2C+Jianxin+Yang%2C+Jiaxi+Yang%2C+Jin)
41. Shuxun Yang, Cunxiang Wang, Yidong Wang, Xiaotao Gu, Minlie Huang, and Jie Tang. 2025. Step-MathAgent: A step-wise agent for evaluating mathematical processes through tree-of-error. CoRR, abs/2503.10105. — [arXiv:2503.10105](https://arxiv.org/abs/2503.10105) [find](https://scholar.google.com/scholar?q=Shuxun+Yang%2C+Cunxiang+Wang%2C+Yidong+Wang%2C+Xiaotao+Gu%2C+Minlie+Huang%2C+and+Jie+Tang%2E+2025%2E+Step%2DMathAgent%3A+A+step%2Dwise+agent+for+evaluating+mathematical+processes+through+tree%2Dof%2Derror%2E+CoRR%2C+abs%2F2503%2E101)
42. Qiying Yu, Zheng Zhang, Ruofei Zhu, Yufeng Yuan, Xiaochen Zuo, Yu Yue, Tiantian Fan, Gaohong Liu, Lingjun Liu, Xin Liu, Haibin Lin, Zhiqi Lin, Bole Ma, Guangming Sheng, Yuxuan Tong, Chi Zhang, Mofan Zhang, Wang Zhang, Hang Zhu, and 16 others. 2025. [DAPO: an open-source LLM reinforcement learning sys…](https://md.research.elamur.ai/free/en/papers/yu-2025-dapo-open-source-llm-reinforcement/)
43. Yufeng Yuan, Qiying Yu, Xiaochen Zuo, Ruofei Zhu, Wenyuan Xu, Jiaze Chen, Chengyi Wang, TianTian Fan, Zhengyin Du, Xiangpeng Wei, and 1 others. 2025. VAPO: Efficient and reliable reinforcement 5650 12 [find](https://scholar.google.com/scholar?q=Yufeng+Yuan%2C+Qiying+Yu%2C+Xiaochen+Zuo%2C+Ruofei+Zhu%2C+Wenyuan+Xu%2C+Jiaze+Chen%2C+Chengyi+Wang%2C+TianTian+Fan%2C+Zhengyin+Du%2C+Xiangpeng+Wei%2C+and+1+others%2E+2025%2E+VAPO%3A+Efficient+and+reliable+reinforcement+5650+12)

*Updated 2 November 2026*