Elamur Research⌕
☰
home / papers / 2026 / Easy Samples Are All You Need: Self-Evolving LLMs via Data-Efficient Reinforcement Learning

Easy Samples Are All You Need: Self-Evolving LLMs via Data-Efficient Reinforcement Learning

Paper · 2026 · Zhiyin Yu, Bo Zhang, Qibin Hou et al.

Summary

Reinforcement learning for LLM reasoning usually depends either on expensive human-verified answers or on label-free rewards such as majority voting and entropy. The label-free rewards tend to give small gains and risk model collapse or reward hacking. The authors draw on Vygotsky's Zone of Proximal Development, which holds that learners progress from easy to hard. Their framework, EasyRL, starts from a small set of easy labeled problems and a large pool of hard unlabeled ones, with difficulty measured on the AoPS 1–10 scale. It works in three stages:

  1. Supervised GRPO on the easy labeled data produces a warm-up policy.
  2. Hard problems are pseudo-labeled by uncertainty. Low-uncertainty items keep their consistent answers, and medium-uncertainty items go through a reflection prompt that checks or re-solves the candidate answers.
  3. Iterative self-training adds progressively harder pseudo-labeled samples, using a dynamic entropy threshold.

On math and science benchmarks, EasyRL trained with only 10% easy labeled data beats GRPO trained on the full labeled set and also outperforms unsupervised RL baselines. This suggests a cheap route to post-training reasoning models when annotation budgets are limited.

Key points

  • Data efficiency: averaged over five math reasoning datasets, EasyRL with 10% easy labeled data scores higher than supervised GRPO trained on 100% of the labels.
    • Qwen2.5-Math-1.5B: 40.3 vs 39.5.
    • Qwen2.5-Math-7B: 50.6 vs 49.5.
  • Ablations on both Qwen2.5-Math models show an average drop for each removed component:
    • Knowledge Transfer: about 2.8%.
    • Divide and Conquer: about 4.6%.
    • Difficulty-Progressive Self-Training: about 1.9%.
  • Pseudo-label quality and the average difficulty of selected samples rise across self-training iterations. On the hardest unlabeled problems (AoPS 9.0–10.0), the self-evolving model holds up better than a non-iterative baseline.
  • The authors note that the method is limited to tasks with verifiable rewards. Open-ended domains such as creative writing are left for future work.
  • Code is available at github.com/YuZhiyin/EasyRL. The paper appears in Findings of ACL 2026.

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

🎓Peking UniversityBeijing · China244 works · 39,359 citations🔬Shanghai Artificial Intelligence LaboratoryShanghai · China117 works · 11,281 citations🎓University of Wisconsin–MadisonMadison · United States42 works · 48,486 citations🎓Nankai UniversityTianjin · China24 works · 762 citations

 Fields, topics and concepts

📚 Shelves 2The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 works

🧭 Topics 1Research subjects and languages the work is about.Language models & pretraining · 3,320 works

Cite

Cite as Zhiyin Yu, Bo Zhang, Qibin Hou, Zhonghai Wu, Xiao Luo and Lei Bai. 2026. Easy Samples Are All You Need: Self-Evolving LLMs via Data-Efficient Reinforcement Learning. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-acl.773

@inproceedings{yu2026easy,
  title = {{Easy Samples Are All You Need: Self-Evolving LLMs via Data-Efficient Reinforcement Learning}},
  author = {Zhiyin Yu, Bo Zhang, Qibin Hou, Zhonghai Wu, Xiao Luo and Lei Bai},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.773},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.773}
}

References

73 references, 21 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Shivam Agarwal, Zimin Zhang, Lifan Yuan, Jiawei Han, and Hao Peng. 2025. The unreasonable effectiveness of entropy minimization in llm reasoning. Preprint, arXiv:2505.15134. find
  2. Ganqu Cui, Lifan Yuan, Zefan Wang, Hanbin Wang, Yuchen Zhang, Jiacheng Chen, Wendi Li, Bingxiang He, Yuchen Fan, Tianyu Yu, Qixin Xu, Weize Chen, Jiarui Yuan, Huayu Chen, Kaiyan Zhang, Xingtai Lv, Shuo Wang, Yuan Yao, Xu Han, Hao Peng, Yu Cheng, Zhiyuan Liu, Maosong Sun, Bowen Zhou, and Ning Ding. 2… — Process Reinforcement through Implicit Rewards
  3. Yu Cui, Feng Liu, Pengbo Wang, Bohao Wang, Heng Tang, Yi Wan, Jun Wang, and Jiawei Chen. 2024. Distillation matters: Empowering sequential recommenders to match the performance of large language models. In Proceedings of the 18th ACM Conference on Recommender Systems, RecSys ’24, page 507–517, New Y… find
  4. Haixing Dai, Zhengliang Liu, Wenxiong Liao, Xiaoke Huang, Yihan Cao, Zihao Wu, Lin Zhao, Shaochen Xu, Fang Zeng, Wei Liu, Ninghao Liu, Sheng Li, Dajiang Zhu, Hongmin Cai, Lichao Sun, Quanzheng Li, Dinggang Shen, Tianming Liu, and Xiang Li. 2025. Auggpt: Leveraging chatgpt for text data augmentation.…
  5. DeepSeek-AI. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. Preprint, arXiv:2501.12948.
  6. Huilin Deng, Ding Zou, Rui Ma, Hongchen Luo, Yang Cao, and Yu Kang. 2025. Boosting the generalization and reasoning of vision language models with curriculum reinforcement learning. Preprint, arXiv:2503.07065. — [arXiv:2503.07065](https://arxiv.org/abs/2503.07065) find
  7. Qingxiu Dong, Li Dong, Xingxing Zhang, Zhifang Sui, and Furu Wei. 2024. Self-boosting large language models with synthetic preference data. Preprint, arXiv:2410.06961. — [arXiv:2410.06961](https://arxiv.org/abs/2410.06961) find
  8. Erik Englesson and Hossein Azizpour. 2021. Consistency regularization can improve robustness to label noise. Preprint, arXiv:2110.01242. — [arXiv:2110.01242](https://arxiv.org/abs/2110.01242) find
  9. Wenkai Fang, Shunyu Liu, Yang Zhou, Kongcheng Zhang, Tongya Zheng, Kaixuan Chen, Mingli Song, and Dacheng Tao. 2025. Serl: Self-play reinforcement learning for large language models with limited data. Preprint, arXiv:2505.20347. — [arXiv:2505.20347](https://arxiv.org/abs/2505.20347) find
  10. Mehdi Fatemi, Banafsheh Rafiee, Mingjie Tang, and Kartik Talamadupula. 2025. Concise reasoning via reinforcement learning. Preprint, arXiv:2504.05185. — [arXiv:2504.05185](https://arxiv.org/abs/2504.05185) find
  11. 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. Preprint, arXiv:2503.01307.
  12. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, and et al Ahmad Al-Dahle. 2024. The llama 3 herd of models. Preprint, arXiv:2407.21783.
  13. Xinyu Guan, Li Lyna Zhang, Yifei Liu, Ning Shang, Youran Sun, Yi Zhu, Fan Yang, and Mao Yang. 2025. rstar-math: Small LLMs can master math reasoning with self-evolved deep thinking. In Forty-second International Conference on Machine Learning.
  14. Daya Guo, Qihao Zhu, Dejian Yang, Zhenda Xie, Kai Dong, Wentao Zhang, Guanting Chen, Xiao Bi, Y. Wu, Y. K. Li, Fuli Luo, Yingfei Xiong, and Wenfeng Liang. 2024. Deepseek-coder: When the large language model meets programming – the rise of code intelligence. Preprint, arXiv:2401.14196. find
  15. Chaoqun He, Renjie Luo, Yuzhuo Bai, Shengding Hu, Zhen 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 Proce…
  16. Zhiwei He, Tian Liang, Jiahao Xu, Qiuzhi Liu, Xingyu Chen, Yue Wang, Linfeng Song, Dian Yu, Zhenwen Liang, Wenxuan Wang, Zhuosheng Zhang, Rui Wang, Zhaopeng Tu, Haitao Mi, and Dong Yu. 2025. Deepmath-103k: A large-scale, challenging, decontaminated, and verifiable mathematical dataset for advancing… find
  17. Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and Jacob Steinhardt. 2021. Measuring mathematical problem solving with the math dataset. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, volume 1.
  18. Maggie Huan, Yuetai Li, Tuney Zheng, Xiaoyu Xu, Seungone Kim, Minxin Du, Radha Poovendran, Graham Neubig, and Xiang Yue. 2025. Does math reasoning improve general llm capabilities? understanding transferability of llm reasoning. Preprint, arXiv:2507.00432. find
  19. Daniel P Jeong, Zachary Chase Lipton, and Pradeep Kumar Ravikumar. 2025. LLM-select: Feature selection with large language models. Transactions on Machine Learning Research. find
  20. Brenden M. Lake, Tomer D. Ullman, Joshua B. Tenenbaum, and Samuel J. Gershman. 2016. Building machines that learn and think like people. Preprint, arXiv:1604.00289. find
  21. Nathan Lambert, Jacob Morrison, Valentina Pyatkin, Shengyi Huang, Hamish Ivison, Faeze Brahman, Lester James V. Miranda, Alisa Liu, Nouha Dziri, Shane Lyu, Yuling Gu, Saumya Malik, Victoria Graf, Jena D. Hwang, Jiangjiang Yang, Ronan Le Bras, Oyvind Tafjord, Chris Wilhelm, Luca Soldaini, Noah A. Smi… — Tulu 3: Pushing Frontiers in Open Language Model Post-Training
  22. Bruce W Lee, Hyunsoo Cho, and Kang Min Yoo. 2024. Instruction tuning with human curriculum. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 1281–1309, Mexico City, Mexico. Association for Computational Linguistics. find
  23. Aitor Lewkowycz, Anders Andreassen, David Dohan, Ethan Dyer, Henryk Michalewski, Vinay 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 Ne…
  24. Pengyi Li, Matvey Skripkin, Alexander Zubrey, Andrey Kuznetsov, and Ivan Oseledets. 2025a. Confidence is all you need: Few-shot rl fine-tuning of language models. Preprint, arXiv:2506.06395. — [arXiv:2506.06395](https://arxiv.org/abs/2506.06395) find
  25. Xinjin Li, Yu Ma, Yangchen Huang, Xingqi Wang, Yuzhen Lin, and Chenxi Zhang. 2024. Synergized data efficiency and compression (sec) optimization for large language models. In 2024 4th International Conference on Electronic Information Engineering and Computer Science (EIECS), pages 586–591. find
  26. Xuefeng Li, Haoyang Zou, and Pengfei Liu. 2025b. Limr: Less is more for rl scaling. Preprint, arXiv:2502.11886. find
  27. Xuefeng Li, Haoyang Zou, and Pengfei Liu. 2025c. Torl: Scaling tool-integrated rl. Preprint, arXiv:2503.23383. find
  28. Zhiheng Li, Zongyang Ma, Yuntong Pan, Ziqi Zhang, Xiaolei Lv, Bo Li, Jun Gao, Jianing Zhang, Chunfeng Yuan, Bing Li, and Weiming Hu. 2026. Making mllms blind: Adversarial smuggling attacks in mllm content moderation. Preprint, arXiv:2604.06950. find
  29. Shunyu Liu, Wenkai Fang, Zetian Hu, Junjie Zhang, Yang Zhou, Kongcheng Zhang, Rongcheng Tu, Ting-En Lin, Fei Huang, Mingli Song, Yongbin Li, and Dacheng Tao. 2025. A survey of direct preference optimization. Preprint, arXiv:2503.11701. — [arXiv:2503.11701](https://arxiv.org/abs/2503.11701) find
  30. Zichen Liu, Changyu Chen, Chao Du, Wee Sun Lee, and Min Lin. 2024. Sample-efficient alignment for LLMs. In Language Gamification - NeurIPS 2024 Workshop. find
  31. Junyu Luo, Bohan Wu, Xiao Luo, Zhiping Xiao, Yiqiao Jin, Rong-Cheng Tu, Nan Yin, Yifan Wang, Jingyang Yuan, Wei Ju, and Ming Zhang. 2025a. A survey on efficient large language model training: From data-centric perspectives. In Proceedings of the 63rd Annual Meeting of the Association for Computation…
  32. 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. 2025b. Deepscaler: Surpassing o1-preview with a 1.5b model by scaling rl. https://pretty-radio -b75.notion.site/DeepScaleR-Surpassing-O 1-Preview-… find
  33. Chengqi Lyu, Songyang Gao, Yuzhe Gu, Wenwei Zhang, Jianfei Gao, Kuikun Liu, Ziyi Wang, Shuaibin Li, Qian Zhao, Haian Huang, Weihan Cao, Jiangning Liu, Hongwei Liu, Junnan Liu, Songyang Zhang, Dahua Lin, and Kai Chen. 2025. Exploring the limit of outcome reward for learning mathematical reasoning. Pr… — [arXiv:2502.06781](https://arxiv.org/abs/2502.06781) find
  34. 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
  35. Xuran Ming, Shoubin Li, Mingyang Li, Lvlong He, and Qing Wang. 2024. Autolabel: Automated textual data annotation method based on active learning and large language model. In Knowledge Science, Engineering and Management: 17th International Conference, KSEM 2024, Birmingham, UK, August 16–… find
  36. Andrew J. Nam and James L. McClelland. 2024. Systematic human learning and generalization from a brief tutorial with explanatory feedback. Open Mind, 8:148–176. find
  37. OpenAI. 2024. Openai o1 system card. Preprint, arXiv:2412.16720.
  38. Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul Christiano, Jan Leike, and Ryan Lowe. 2022. Train…
  39. Zhuoshi Pan, Qianhui Wu, Huiqiang Jiang, Menglin Xia, Xufang Luo, Jue Zhang, Qingwei Lin, Victor Rühle, Yuqing Yang, Chin-Yew Lin, H. Vicky Zhao, Lili Qiu, and Dongmei Zhang. 2024. LLMLingua-2: Data distillation for efficient and faithful task-agnostic prompt compression. In Findings of the Associat…
  40. Emmanouil Antonios Platanios, Otilia Stretcu, Graham Neubig, Barnabas Poczos, and Tom Mitchell. 2019. Competence-based curriculum learning for neural machine translation. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langu… find
  41. Mihir Prabhudesai, Lili Chen, Alex Ippoliti, Katerina Fragkiadaki, Hao Liu, and Deepak Pathak. 2025. Maximizing confidence alone improves reasoning. Preprint, arXiv:2505.22660. — [arXiv:2505.22660](https://arxiv.org/abs/2505.22660) find
  42. Chen Qian, Wei Liu, Hongzhang Liu, Nuo Chen, Yufan Dang, Jiahao Li, Cheng Yang, Weize Chen, Yusheng Su, Xin Cong, Juyuan Xu, Dahai Li, Zhiyuan Liu, and Maosong Sun. 2024. ChatDev: Communicative agents for software development. In Proceedings of the 62nd Annual Meeting of the Association for Computat…
  43. David Rein, Betty Li Hou, Asa Cooper Stickland, Jackson Petty, Richard Yuanzhe Pang, Julien Dirani, Julian Michael, and Samuel R. Bowman. 2023. Gpqa: A graduate-level google-proof q&a benchmark. Preprint, arXiv:2311.12022.
  44. Sheikh Shafayat, Fahim Tajwar, Ruslan Salakhutdinov, Jeff Schneider, and Andrea Zanette. 2025. Can large reasoning models self-train? Preprint, arXiv:2505.21444. find
  45. Rulin Shao, Shuyue Stella Li, Rui Xin, Scott Geng, Yiping Wang, Sewoong Oh, Simon Shaolei Du, Nathan Lambert, Sewon Min, Ranjay Krishna, Yulia Tsvetkov, Hannaneh Hajishirzi, Pang Wei Koh, and Luke Zettlemoyer. 2025. Spurious rewards: Rethinking training signals in rlvr. Preprint, arXiv:2506.10947. find
  46. Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, Y. K. Li, Y. Wu, and Daya Guo. 2024. Deepseekmath: Pushing the limits of mathematical reasoning in open language models. Preprint, arXiv:2402.03300.
  47. Guangming Sheng, Chi Zhang, Zilingfeng Ye, Xibin Wu, Wang Zhang, Ru Zhang, Yanghua Peng, Haibin Lin, and Chuan Wu. 2025. Hybridflow: A flexible and efficient rlhf framework. In Proceedings of the Twentieth European Conference on Computer Systems, EuroSys ’25, page 1279–1297. ACM.
  48. Ilia Shumailov, Zakhar Shumaylov, Yiren Zhao, Nicolas Papernot, Ross Anderson, and Yarin Gal. 2024. Ai models collapse when trained on recursively generated data. Nature, 631(8022):755–759. find
  49. Joykirat Singh, Raghav Magazine, Yash Pandya, and Akshay Nambi. 2025. Agentic reasoning and tool integration for llms via reinforcement learning. Preprint, arXiv:2505.01441. — [arXiv:2505.01441](https://arxiv.org/abs/2505.01441) find
  50. Kihyuk Sohn, David Berthelot, Chun-Liang Li, Zizhao Zhang, Nicholas Carlini, Ekin D. Cubuk, Alex Kurakin, Han Zhang, and Colin Raffel. 2020. Fixmatch: simplifying semi-supervised learning with consistency and confidence. In Proceedings of the 34th International Conference on Neural Information Proce… find
  51. InternAgent Team, Bo Zhang, Shiyang Feng, Xiangchao Yan, Jiakang Yuan, Runmin Ma, Yusong Hu, Zhiyin Yu, Xiaohan He, Songtao Huang, Shaowei Hou, Zheng Nie, Zhilong Wang, Jinyao Liu, Tianshuo Peng, Peng Ye, Dongzhan Zhou, Shufei Zhang, Xiaosong Wang, Yilan Zhang, Meng Li, Zhongying Tu, Xiangyu Yue, Wa… find
  52. Kimi Team. 2025. Kimi k1.5: Scaling reinforcement learning with llms. Preprint, arXiv:2501.12599.
  53. L. S. VYGOTSKY. 1978. Mind in Society: Development of Higher Psychological Processes. Harvard University Press. find
  54. Yinjie Wang, Ling Yang, Ye Tian, Ke Shen, and Mengdi Wang. 2025a. Co-evolving llm coder and unit tester via reinforcement learning. Preprint, arXiv:2506.03136. — [arXiv:2506.03136](https://arxiv.org/abs/2506.03136) find
  55. Yiping Wang, Qing Yang, Zhiyuan Zeng, Liliang Ren, Liyuan Liu, Baolin Peng, Hao Cheng, Xuehai He, Kuan Wang, Jianfeng Gao, Weizhu Chen, Shuohang Wang, Simon Shaolei Du, and Yelong Shen. 2025b. Reinforcement learning for reasoning in large language models with one training example. Preprint, arXiv:25… find
  56. Zhenting Wang, Guofeng Cui, Yu-Jhe Li, Kun Wan, and Wentian Zhao. 2025c. Dump: Automated distribution-level curriculum learning for rl-based llm post-training. Preprint, arXiv:2504.09710. — [arXiv:2504.09710](https://arxiv.org/abs/2504.09710) find
  57. Lai Wei, Yuting Li, Chen Wang, Yue Wang, Linghe Kong, Weiran Huang, and Lichao Sun. 2025. Unsupervised post-training for multi-modal llm reasoning via grpo. Preprint, arXiv:2505.22453. — [arXiv:2505.22453](https://arxiv.org/abs/2505.22453) find
  58. Rihui Xin, Han Liu, Zecheng Wang, Yupeng Zhang, Dianbo Sui, Xiaolin Hu, and Bingning Wang. 2025. Surrogate signals from format and length: Reinforcement learning for solving mathematical problems without ground truth answers. Preprint, arXiv:2505.19439. — [arXiv:2505.19439](https://arxiv.org/abs/2505.19439) find
  59. An Yang, Beichen Zhang, Binyuan Hui, Bofei Gao, Bowen Yu, Chengpeng Li, Dayiheng Liu, Jianhong Tu, Jingren Zhou, Junyang Lin, Keming Lu, Mingfeng Xue, Runji Lin, Tianyu Liu, Xingzhang Ren, and Zhenru Zhang. 2024. Qwen2.5-math technical report: Toward mathematical expert model via self-improvement. P…
  60. Chenyu Yang, Shiqian Su, Shi Liu, Xuan Dong, Yue Yu, Weijie Su, Xuehui Wang, Zhaoyang Liu, Jinguo Zhu, Hao Li, Wenhai Wang, Yu Qiao, Xizhou Zhu, and Jifeng Dai. 2025a. Zerogui: Automating online gui learning at zero human cost. Preprint, arXiv:2505.23762. — [arXiv:2505.23762](https://arxiv.org/abs/2505.23762) find
  61. Wenjie Yang, Mao Zheng, Mingyang Song, Zheng Li, and Sitong Wang. 2025b. Ssr-zero: Simple self-rewarding reinforcement learning for machine translation. Preprint, arXiv:2505.16637.
  62. Jiaxuan You, Mingjie Liu, Shrimai Prabhumoye, Mostofa Patwary, Mohammad Shoeybi, and Bryan Catanzaro. 2024. LLM-evolve: Evaluation for LLM’s evolving capability on benchmarks. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 16937– 16942, Miami, Florid… find
  63. Zhiyin Yu, Chao Zheng, Chong Chen, Xian-Sheng Hua, and Xiao Luo. 2025. scRAG: Hybrid retrieval-augmented generation for LLM-based cross-tissue single-cell annotation. In Findings of the Association for Computational Linguistics: ACL 2025, pages 954– 970, Vienna, Austria. Association for Computationa… find
  64. Weizhe Yuan, Richard Yuanzhe Pang, Kyunghyun Cho, Xian Li, Sainbayar Sukhbaatar, Jing Xu, and Jason E Weston. 2024. Self-rewarding language models. In Forty-first International Conference on Machine Learning. find
  65. Weihao Zeng, Yuzhen Huang, Wei Liu, Keqing He, Qian Liu, Zejun Ma, and Junxian He. 2025. 7b model and 8k examples: Emerging reasoning with reinforcement learning is both effective and efficient. https://hkust-nlp.notion.site/simplerl-reason. Notion Blog. ↗
  66. Enci Zhang, Xingang Yan, Wei Lin, Tianxiang. Zhang, and Lu Qianchun. 2025a. Learning like humans: Advancing LLM reasoning capabilities via adaptive difficulty curriculum learning and expert-guided self-reformulation. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Proc… find
  67. Jenny Zhang, Shengran Hu, Cong Lu, Robert Lange, and Jeff Clune. 2025b. Darwin godel machine: Open-ended evolution of self-improving agents. Preprint, arXiv:2505.22954. find
  68. Kongcheng Zhang, Qi Yao, Shunyu Liu, Yingjie Wang, Baisheng Lai, Jieping Ye, Mingli Song, and Dacheng Tao. 2025c. Consistent paths lead to truth: Self-rewarding reinforcement learning for llm reasoning. Preprint, arXiv:2506.08745. — [arXiv:2506.08745](https://arxiv.org/abs/2506.08745) find
  69. Qingyang Zhang, Haitao Wu, Changqing Zhang, Peilin Zhao, and Yatao Bian. 2025d. Right question is already half the answer: Fully unsupervisedd LLM reasoning incentization. In Second Workshop on Test-Time Adaptation: Putting Updates to the Test! at ICML 2025. find
  70. Yanzhi Zhang, Zhaoxi Zhang, Haoxiang Guan, Yilin Cheng, Yitong Duan, Chen Wang, Yue Wang, Shuxin Zheng, and Jiyan He. 2025e. No free lunch: Rethinking internal feedback for llm reasoning. Preprint, arXiv:2506.17219. — [arXiv:2506.17219](https://arxiv.org/abs/2506.17219) find
  71. Andrew Zhao, Yiran Wu, Yang Yue, Tong Wu, Quentin Xu, Yang Yue, Matthieu Lin, Shenzhi Wang, Qingyun Wu, Zilong Zheng, and Gao Huang. 2025a. Absolute zero: Reinforced self-play reasoning with zero data. Preprint, arXiv:2505.03335. find
  72. GPQA Test Prompt Xuandong Zhao, Zhewei Kang, Aosong Feng, Sergey Levine, and Dawn Song. 2025b. Learning to reason without external rewards. Preprint, arXiv:2505.19590. \<\|im_start\|\>system Reason step by step, and output your final answer (A, B, C, or D) within \\boxed{}. \<\|im_end\|\> \<\|im_start\|\>user {Q… find
  73. Yuxin Zuo, Kaiyan Zhang, Li Sheng, Shang Qu, Ganqu Cui, Xuekai Zhu, Haozhan Li, Yuchen Zhang, Xinwei Long, Ermo Hua, Biqing Qi, Youbang Sun, Zhiyuan Ma, Lifan Yuan, Ning Ding, and Bowen Zhou. 2025. Ttrl: Test-time reinforcement learning. Preprint, arXiv:2504.16084. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/yu-2026-easy-samples-are-all-you/