Elamur Research⌕
☰
home / papers / 2025 / Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning

Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning

Paper · 2025 · ByteDance Seed, Jiaze Chen, Tiantian Fan et al.

Summary

Seed1.5-Thinking is a reasoning model from ByteDance Seed. It works through an extended chain of thought before giving its answer. The authors identify three factors behind strong reasoning models: training data, a stable RL algorithm and scalable RL infrastructure.

The model uses a Mixture-of-Experts design with 200B total and 20B active parameters. It is trained with two kinds of RL data:

  • Verifiable tasks: cleaned STEM problems, competitive-programming tasks checked in a code sandbox, and generated logic puzzles with automatic answer checkers.
  • Non-verifiable prompts: tasks such as writing and translation, scored by a pairwise reward model.

To avoid unstable training runs, the team relies on their VAPO (actor-critic) and DAPO (policy-gradient) methods. An asynchronous streaming rollout system makes training iterations faster.

The model reaches 86.7 on AIME 2024, 55.0 on Codeforces and 77.3 on GPQA. It beats DeepSeek R1 but still trails o3 and Gemini 2.5 Pro on the hardest tests. It also generalizes beyond reasoning, winning more human preference comparisons against R1. Two new, harder benchmarks are introduced for the research community.

Key points

  • Results: AIME 2024 86.7, AIME 2025 74.0, Codeforces 55.0, GPQA 77.3. On non-reasoning tasks, human raters gave about 8% more positive feedback than for DeepSeek R1.
  • RL data:
    • About 100k STEM problems, more than 80% of them math, filtered with Doubao-Pro 1.5.
    • About 10k puzzles from 22 task generators, such as Sudoku, mazes and 24-point.
    • Coding problems that come with unit tests and checker scripts.
  • New benchmarks:
    • BeyondAIME: 100 expert-written problems with integer answers, at or above the difficulty of the hardest AIME questions.
    • A Codeforces set built from the 12 latest contests, scored with pass@1 and pass@8 rather than Elo estimates.
  • Verifiers: on a human-labeled test set, the reasoning-based Seed-Thinking-Verifier reaches 99.3% accuracy, compared with 82.7% for Seed-Verifier.
  • Algorithms and ablations:
    • VAPO outperforms DAPO consistently: 60% vs 50% on Qwen-32B and 79% vs 73% on Seed-150B-MoE. This supports using Qwen-32B as a cheap proxy for comparing RL algorithms.
    • Initializing from an RFT model plateaus sooner and ends lower than the baseline (54% vs 58% AIME avg@32).
    • The streaming rollout infrastructure gives roughly 3× faster iterations than synchronous training.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 9,086 worksArtificial Intelligence · 8,889 worksArts and Humanities · 9,296 worksLanguage and Linguistics · 9,206 worksComputer Vision and Pattern Recognition · 1,282 works

🧭 Topics 1Research subjects and languages the work is about.Reasoning · 510 works

Cite

Cite as ByteDance Seed, Jiaze Chen, Tiantian Fan, Xin Liu, Lingjun Liu, Zhiqi Lin, Mingxuan Wang, Chengyi Wang, Xiangpeng Wei, Wenyuan Xu, Yufeng Yuan, Yu Yue, Lin Yan, Qiying Yu, Xiaochen Zuo, Chi Zhang, Ruofei Zhu, Zhecheng An, Zhihao Bai, Yu Bao, Xingyan Bin, Jiangjie Chen, Feng Chen, Hongmin Chen, Riwei Chen, Liangqiang Chen, Zixin Chen, Jinsong Chen, Siyan Chen, Kaiyuan Chen, Zhi Chen, Jin Chen, Jiecao Chen, Jinxin Chi, Weinan Dai, Ning Dai, Jiahui Dai, Shihan Dou, Yantao Du, Zhengyin Du, Jianhui Duan, Chen Dun, Ting-Han Fan, Jiazhan Feng, Junda Feng, Ziyuan Feng, Yuwei Fu, Wenqi Fu, Hanjie Fu, Hao Ge, Hongyi Guo, Mingji Han, Li Han, Wenhao Hao, Xintong Hao, Qianyu He, Jerry He, Feng He, Wen Heng, Zehua Hong, Qi Hou, Liang Hu, Shengding Hu, Nan Hu, Kai Hua, Qi Huang, Ziyue Huang, Hongzhi Huang, Zihao Huang, Ting Huang, Wenhao Huang, Wei Jia, Bin Jia, Xiaoying Jia, Yuhua Jiang, Haobin Jiang, Ziheng Jiang, Kaihua Jiang, Chengquan Jiang, Jianpeng Jiao, Xiaoran Jin, Xing Jin, Xunhao Lai, Zheng Li, Xiang Li, Liyi Li, Hongkai Li, Zheng Li, Shengxian Wan, Ya Wang, Yunshui Li, Chenggang Li, Niuniu Li, Siyu Li, Xi Li, Xiao Li, Aoyan Li, Yuntao Li, Nianning Liang, Xinnian Liang, Haibin Lin, Weijian Lin, Ye Lin, Zhicheng Liu, Guanlin Liu, Guanlin Liu, Chenxiao Liu, Yan Liu, Gaohong Liu, Juncai Liu, Chundian Liu, Deyi Liu, Kaibo Liu, Siyao Liu, Qi Liu, Yongfei Liu, Kang Liu, Gan Liu, Boyi Liu, Rui Long, Weiqiang Lou, Chenwei Lou, Xiang Luo, Yao Luo, Caiping Lv, Heyang Lv, Bole Ma, Qianli Ma, Hongzhi Ma, Yiyuan Ma, Jin Ma, Wenchang Ma, Tingting Ma, Chen Mao, Qiyang Min, Zhe Nan, Guanghan Ning, Jinxiang Ou, Haojie Pan, Renming Pang, Yanghua Peng, Tao Peng, Lihua Qian, Lihua Qian, Mu Qiao, Meng Qu, Cheng Ren, Hongbin Ren, Yong Shan, Wei Shen, Ke Shen, Kai Shen, Guangming Sheng, Jinlong Shi, Wenlei Shi, Guang Shi, Shuai Shuai Cao, Yuxin Song, Zuquan Song, Jing Su, Yifan Sun, Tao Sun, Zewei Sun, Borui Wan, Zihan Wang, Xiaohui Wang, Xi Wang, Shuguang Wang, Jun Wang, Qinlong Wang, Chenyuan Wang, Shuai Wang, Zihan Wang, Changbao Wang, Jiaqiang Wang, Shihang Wang, Xuwu Wang, Zaiyuan Wang, Yuxuan Wang, Wenqi Wang, Taiqing Wang, Chengzhi Wei, Houmin Wei, Ziyun Wei, Shufa Wei, Zheng Wu, Yonghui Wu, Yangjun Wu, Bohong Wu, Shuang Wu, Jingqiao Wu, Ning Wu, Shuangzhi Wu, Jianmin Wu, Chenguang Xi, Fan Xia, Yuqiao Xian, Liang Xiang, Boren Xiang, Bowen Xiao, Zhen Xiao, Xia Xiao, Yongsheng Xiao, Chao Xin, Shulin Xin, Yuwen Xiong, Jingjing Xu, Ziwen Xu, Chenyin Xu, Jiayi Xu, Yifan Xu, Wei Xu, Yufei Xu, Shikun Xu, Shipeng Yan, Shen Yan, Qingping Yang, Xi Yang, Tianhao Yang, Yuehang Yang, Yuan Yang, Ximing Yang, Zeyu Yang, Guang Yang, Yifan Yang, Xuesong Yao, Bairen Yi, Fan Yin, Jianian Yin, Ziqiang Ying, Xiangyu Yu, Hongli Yu, Song Yu, Menghan Yu, Huan Yu, Siyu Yuan, Jun Yuan, Yutao Zeng, Tianyang Zhan, Zheng Zhang, Yun Zhang, Mofan Zhang, Wang Zhang, Ru Zhang, Zhi Zhang, Tianqi Zhang, Xinyi Zhang, Zhexi Zhang, Sijun Zhang, Wenqiang Zhang, Xiangxiang Zhang, Yongtao Zhang, Yuyu Zhang, Ge Zhang, He Zhang, Yue Zhang, Renjie Zheng, Ningxin Zheng, Zhuolin Zheng, Yaowei Zheng, Chen Zheng, Xiaoyun Zhi, Wanjun Zhong, Cheng Zhong, Zheng Zhong, Baoquan Zhong, Xun Zhou, Na Zhou, Huan Zhou, Hang Zhu, Defa Zhu, Wenjia Zhu and Lei Zuo. 2025. Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning. arXiv:2504.13914.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2504.13914 · arXiv 2504.13914

@misc{seed2025seed1,
  title = {{Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning}},
  author = {ByteDance Seed, Jiaze Chen, Tiantian Fan, Xin Liu, Lingjun Liu, Zhiqi Lin, Mingxuan Wang, Chengyi Wang, Xiangpeng Wei, Wenyuan Xu, Yufeng Yuan, Yu Yue, Lin Yan, Qiying Yu, Xiaochen Zuo, Chi Zhang, Ruofei Zhu, Zhecheng An, Zhihao Bai, Yu Bao, Xingyan Bin, Jiangjie Chen, Feng Chen, Hongmin Chen, Riwei Chen, Liangqiang Chen, Zixin Chen, Jinsong Chen, Siyan Chen, Kaiyuan Chen, Zhi Chen, Jin Chen, Jiecao Chen, Jinxin Chi, Weinan Dai, Ning Dai, Jiahui Dai, Shihan Dou, Yantao Du, Zhengyin Du, Jianhui Duan, Chen Dun, Ting-Han Fan, Jiazhan Feng, Junda Feng, Ziyuan Feng, Yuwei Fu, Wenqi Fu, Hanjie Fu, Hao Ge, Hongyi Guo, Mingji Han, Li Han, Wenhao Hao, Xintong Hao, Qianyu He, Jerry He, Feng He, Wen Heng, Zehua Hong, Qi Hou, Liang Hu, Shengding Hu, Nan Hu, Kai Hua, Qi Huang, Ziyue Huang, Hongzhi Huang, Zihao Huang, Ting Huang, Wenhao Huang, Wei Jia, Bin Jia, Xiaoying Jia, Yuhua Jiang, Haobin Jiang, Ziheng Jiang, Kaihua Jiang, Chengquan Jiang, Jianpeng Jiao, Xiaoran Jin, Xing Jin, Xunhao Lai, Zheng Li, Xiang Li, Liyi Li, Hongkai Li, Zheng Li, Shengxian Wan, Ya Wang, Yunshui Li, Chenggang Li, Niuniu Li, Siyu Li, Xi Li, Xiao Li, Aoyan Li, Yuntao Li, Nianning Liang, Xinnian Liang, Haibin Lin, Weijian Lin, Ye Lin, Zhicheng Liu, Guanlin Liu, Guanlin Liu, Chenxiao Liu, Yan Liu, Gaohong Liu, Juncai Liu, Chundian Liu, Deyi Liu, Kaibo Liu, Siyao Liu, Qi Liu, Yongfei Liu, Kang Liu, Gan Liu, Boyi Liu, Rui Long, Weiqiang Lou, Chenwei Lou, Xiang Luo, Yao Luo, Caiping Lv, Heyang Lv, Bole Ma, Qianli Ma, Hongzhi Ma, Yiyuan Ma, Jin Ma, Wenchang Ma, Tingting Ma, Chen Mao, Qiyang Min, Zhe Nan, Guanghan Ning, Jinxiang Ou, Haojie Pan, Renming Pang, Yanghua Peng, Tao Peng, Lihua Qian, Lihua Qian, Mu Qiao, Meng Qu, Cheng Ren, Hongbin Ren, Yong Shan, Wei Shen, Ke Shen, Kai Shen, Guangming Sheng, Jinlong Shi, Wenlei Shi, Guang Shi, Shuai Shuai Cao, Yuxin Song, Zuquan Song, Jing Su, Yifan Sun, Tao Sun, Zewei Sun, Borui Wan, Zihan Wang, Xiaohui Wang, Xi Wang, Shuguang Wang, Jun Wang, Qinlong Wang, Chenyuan Wang, Shuai Wang, Zihan Wang, Changbao Wang, Jiaqiang Wang, Shihang Wang, Xuwu Wang, Zaiyuan Wang, Yuxuan Wang, Wenqi Wang, Taiqing Wang, Chengzhi Wei, Houmin Wei, Ziyun Wei, Shufa Wei, Zheng Wu, Yonghui Wu, Yangjun Wu, Bohong Wu, Shuang Wu, Jingqiao Wu, Ning Wu, Shuangzhi Wu, Jianmin Wu, Chenguang Xi, Fan Xia, Yuqiao Xian, Liang Xiang, Boren Xiang, Bowen Xiao, Zhen Xiao, Xia Xiao, Yongsheng Xiao, Chao Xin, Shulin Xin, Yuwen Xiong, Jingjing Xu, Ziwen Xu, Chenyin Xu, Jiayi Xu, Yifan Xu, Wei Xu, Yufei Xu, Shikun Xu, Shipeng Yan, Shen Yan, Qingping Yang, Xi Yang, Tianhao Yang, Yuehang Yang, Yuan Yang, Ximing Yang, Zeyu Yang, Guang Yang, Yifan Yang, Xuesong Yao, Bairen Yi, Fan Yin, Jianian Yin, Ziqiang Ying, Xiangyu Yu, Hongli Yu, Song Yu, Menghan Yu, Huan Yu, Siyu Yuan, Jun Yuan, Yutao Zeng, Tianyang Zhan, Zheng Zhang, Yun Zhang, Mofan Zhang, Wang Zhang, Ru Zhang, Zhi Zhang, Tianqi Zhang, Xinyi Zhang, Zhexi Zhang, Sijun Zhang, Wenqiang Zhang, Xiangxiang Zhang, Yongtao Zhang, Yuyu Zhang, Ge Zhang, He Zhang, Yue Zhang, Renjie Zheng, Ningxin Zheng, Zhuolin Zheng, Yaowei Zheng, Chen Zheng, Xiaoyun Zhi, Wanjun Zhong, Cheng Zhong, Zheng Zhong, Baoquan Zhong, Xun Zhou, Na Zhou, Huan Zhou, Hang Zhu, Defa Zhu, Wenjia Zhu and Lei Zuo},
  year = {2025},
  doi = {10.48550/arxiv.2504.13914},
  eprint = {2504.13914},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2504.13914}
}

References

23 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. OpenAI. Learning to reason with llms, 2024. find
  2. DeepSeek-AI. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning, 2025.
  3. Google DeepMind. Gemini 2.5: Our most intelligent ai model, 2025. find
  4. Anthropic. Claude 3.7 sonnet and claude code, 2025. find
  5. Yu Yue, Yufeng Yuan, Qiying Yu, Xiaochen Zuo, Ruofei Zhu, Wenyuan Xu, Jiaze Chen, Chengyi Wang, TianTian Fan, Zhengyin Du, Xiangpeng Wei, Xiangyu Yu, Gaohong Liu, Juncai Liu, Lingjun Liu, Haibin Lin, Zhiqi Lin, Bole Ma, Chi Zhang, Mofan Zhang, Wang Zhang, Hang Zhu, Ru Zhang, Xin Liu, Mingxuan Wang,… find
  6. 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, Jinhua Zhu, Jiaze Chen, Jiangjie Chen, Chengyi Wang, Hongli Yu, Weinan D…
  7. ByteDance. Doubao-1.5-pro, 2025. find
  8. Wei Shen, Guanlin Liu, Zheng Wu, Ruofei Zhu, Qingping Yang, Chao Xin, Yu Yue, and Lin Yan. Exploring data scaling trends and effects in reinforcement learning from human feedback, 2025. find
  9. Wenyuan Xu, Xiaochen Zuo, Chao Xin, Yu Yue, Lin Yan, and Yonghui Wu. A unified pairwise framework for rlhf: Bridging generative reward modeling and policy optimization, 2025. find
  10. Yufeng Yuan, Yu Yue, Ruofei Zhu, Tiantian Fan, and Lin Yan. What’s behind ppo’s collapse in long-cot? value optimization holds the secret. arXiv preprint arXiv:2503.01491, 2025. — [arXiv:2503.01491](https://arxiv.org/abs/2503.01491) find
  11. Guangming Sheng, Chi Zhang, Zilingfeng Ye, Xibin Wu, Wang Zhang, Ru Zhang, Yanghua Peng, Haibin Lin, and Chuan Wu. Hybridflow: A flexible and efficient rlhf framework. arXiv preprint arXiv:2409.19256, 2024.
  12. Philipp Moritz, Robert Nishihara, Stephanie Wang, Alexey Tumanov, Richard Liaw, Eric Liang, William Paul, Michael I. Jordan, and Ion Stoica. Ray: A distributed framework for emerging AI applications. CoRR, abs/1712.05889, 2017. — [arXiv:1712.05889](https://arxiv.org/abs/1712.05889) find
  13. Zhewei Yao, Reza Yazdani Aminabadi, Olatunji Ruwase, Samyam Rajbhandari, Xiaoxia Wu, Ammar Ahmad Awan, Jeff Rasley, Minjia Zhang, Conglong Li, Connor Holmes, Zhongzhu Zhou, Michael Wyatt, Molly Smith, Lev Kurilenko, Heyang Qin, Masahiro Tanaka, Shuai Che, Shuaiwen Leon Song, and Yuxiong He. Deepspee… find
  14. Narendra Karmarkar and Richard M Karp. The differencing method of set partitioning. Computer Science Division (EECS), University of California Berkeley, 1982. find
  15. Tianqi Chen, Bing Xu, Chiyuan Zhang, and Carlos Guestrin. Training deep nets with sublinear memory cost. arXiv preprint arXiv:1604.06174, 2016. find
  16. Lianmin Zheng, Zhuohan Li, Hao Zhang, Yonghao Zhuang, Zhifeng Chen, Yanping Huang, Yida Wang, Yuanzhong Xu, Danyang Zhuo, Eric P Xing, et al. Alpa: Automating inter-and {Intra-Operator} parallelism for distributed deep learning. In 16th USENIX Symposium on Operating Systems Design and Implementation… find
  17. Borui Wan, Mingji Han, Yiyao Sheng, Yanghua Peng, Haibin Lin, Mofan Zhang, Zhichao Lai, Menghan Yu, Junda Zhang, Zuquan Song, Xin Liu, and Chuan Wu. Bytecheckpoint: A unified checkpointing system for large foundation model development, 2025. find
  18. Qwen. Qwq-32b: Embracing the power of reinforcement learning, 2024. find
  19. XAI. Grok 3 beta — the age of reasoning agents, 2024. find
  20. Google DeepMind. Gemini 2.0 flash thinking, 2024. find
  21. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901, 2020.
  22. OpenAI. GPT4 technical report. arXiv preprint arXiv:2303.08774, 2023.
  23. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, 35:24824–24837, 2022.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/bytedance-seed-2025-seed1-5-thinking-advancing/