{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T20:24:24Z","timestamp":1787689464532,"version":"build-2784847793"},"publisher-location":"New York, NY, USA","reference-count":62,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770854.3780263","type":"proceedings-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T12:07:40Z","timestamp":1785499660000},"page":"1240-1250","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Can Prompt Difficulty be Online Predicted for Accelerating RL Finetuning of Reasoning Models?"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1803-8435","authenticated-orcid":false,"given":"Yun","family":"Qu","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7758-725X","authenticated-orcid":false,"given":"Qi","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7302-5039","authenticated-orcid":false,"given":"Yixiu","family":"Mao","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1561-3216","authenticated-orcid":false,"given":"Vincent Tao","family":"Hu","sequence":"additional","affiliation":[{"name":"CompVis @ LMU Munich, Munich Center for Machine Learning (MCML), munich, Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0766-120X","authenticated-orcid":false,"given":"Bj\u00f6rn","family":"Ommer","sequence":"additional","affiliation":[{"name":"CompVis @ LMU Munich, Munich Center for Machine Learning (MCML), munich, Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9542-5260","authenticated-orcid":false,"given":"Xiangyang","family":"Ji","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,20]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"crossref","unstructured":"P Auer. 2002. Finite-time Analysis of the Multiarmed Bandit Problem.","DOI":"10.1023\/A:1013689704352"},{"key":"e_1_3_2_2_2_1","volume-title":"Hanbyul Kim, JeongYeon Nam, and Donghyun Kwak.","author":"Bae Sanghwan","year":"2025","unstructured":"Sanghwan Bae, Jiwoo Hong, Min Young Lee, Hanbyul Kim, JeongYeon Nam, and Donghyun Kwak. 2025. Online difficulty filtering for reasoning oriented reinforcement learning. arXiv preprint arXiv:2504.03380 (2025)."},{"key":"e_1_3_2_2_3_1","unstructured":"Shuai Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Sibo Song Kai Dang Peng Wang Shijie Wang Jun Tang et al. 2025. Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"e_1_3_2_2_5_1","volume-title":"A Bernoulli two-armed bandit. The Annals of Mathematical Statistics","author":"Berry Donald A","year":"1972","unstructured":"Donald A Berry. 1972. A Bernoulli two-armed bandit. The Annals of Mathematical Statistics (1972), 871-897."},{"key":"e_1_3_2_2_6_1","volume-title":"Streaming variational bayes. Advances in neural information processing systems","author":"Broderick Tamara","year":"2013","unstructured":"Tamara Broderick, Nicholas Boyd, Andre Wibisono, Ashia C Wilson, and Michael I Jordan. 2013. Streaming variational bayes. Advances in neural information processing systems, Vol. 26 (2013)."},{"key":"e_1_3_2_2_7_1","volume-title":"Self-Evolving Curriculum for LLM Reasoning. arXiv preprint arXiv:2505.14970","author":"Chen Xiaoyin","year":"2025","unstructured":"Xiaoyin Chen, Jiarui Lu, Minsu Kim, Dinghuai Zhang, Jian Tang, Alexandre Pich\u00e9, Nicolas Gontier, Yoshua Bengio, and Ehsan Kamalloo. 2025. Self-Evolving Curriculum for LLM Reasoning. arXiv preprint arXiv:2505.14970 (2025)."},{"key":"e_1_3_2_2_8_1","volume-title":"Sft memorizes, rl generalizes: A comparative study of foundation model post-training. arXiv preprint arXiv:2501.17161","author":"Chu Tianzhe","year":"2025","unstructured":"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. arXiv preprint arXiv:2501.17161 (2025)."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-00296-0"},{"key":"e_1_3_2_2_10_1","unstructured":"Ganqu Cui Lifan Yuan Zefan Wang Hanbin Wang Wendi Li Bingxiang He Yuchen Fan Tianyu Yu Qixin Xu Weize Chen et al. 2025. Process reinforcement through implicit rewards. arXiv preprint arXiv:2502.01456 (2025)."},{"key":"e_1_3_2_2_11_1","volume-title":"Safe rlhf: Safe reinforcement learning from human feedback. arXiv preprint arXiv:2310.12773","author":"Dai Josef","year":"2023","unstructured":"Josef Dai, Xuehai Pan, Ruiyang Sun, Jiaming Ji, Xinbo Xu, Mickel Liu, Yizhou Wang, and Yaodong Yang. 2023. Safe rlhf: Safe reinforcement learning from human feedback. arXiv preprint arXiv:2310.12773 (2023)."},{"key":"e_1_3_2_2_12_1","volume-title":"Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't. arXiv preprint arXiv:2503.16219","author":"Dang Quy-Anh","year":"2025","unstructured":"Quy-Anh Dang and Chris Ngo. 2025. Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't. arXiv preprint arXiv:2503.16219 (2025)."},{"key":"e_1_3_2_2_13_1","volume-title":"Rlhf workflow: From reward modeling to online rlhf. arXiv preprint arXiv:2405.07863","author":"Dong Hanze","year":"2024","unstructured":"Hanze Dong, Wei Xiong, Bo Pang, Haoxiang Wang, Han Zhao, Yingbo Zhou, Nan Jiang, Doyen Sahoo, Caiming Xiong, and Tong Zhang. 2024. Rlhf workflow: From reward modeling to online rlhf. arXiv preprint arXiv:2405.07863 (2024)."},{"key":"e_1_3_2_2_14_1","volume-title":"Concise reasoning via reinforcement learning. arXiv preprint arXiv:2504.05185","author":"Fatemi Mehdi","year":"2025","unstructured":"Mehdi Fatemi, Banafsheh Rafiee, Mingjie Tang, and Kartik Talamadupula. 2025. Concise reasoning via reinforcement learning. arXiv preprint arXiv:2504.05185 (2025)."},{"key":"e_1_3_2_2_15_1","unstructured":"Aaron Grattafiori Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Alex Vaughan et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)."},{"key":"e_1_3_2_2_16_1","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)."},{"key":"e_1_3_2_2_17_1","volume-title":"Junhao Shen, Jinyi Hu, Xu Han, Yujie Huang, Yuxiang Zhang, et al.","author":"He Chaoqun","year":"2024","unstructured":"Chaoqun He, Renjie Luo, Yuzhuo Bai, Shengding Hu, Zhen Leng Thai, Junhao Shen, Jinyi Hu, Xu Han, Yujie Huang, Yuxiang Zhang, et al., 2024. Olympiadbench: A challenging benchmark for promoting agi with olympiad-level bilingual multimodal scientific problems. arXiv preprint arXiv:2402.14008 (2024)."},{"key":"e_1_3_2_2_18_1","volume-title":"Measuring Mathematical Problem Solving With the MATH Dataset. arXiv preprint arXiv:2103.03874","author":"Hendrycks Dan","year":"2021","unstructured":"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. arXiv preprint arXiv:2103.03874 (2021)."},{"key":"e_1_3_2_2_19_1","unstructured":"Hiyouga. 2025. Geometry3K: A Large-scale Multi-modal Geometry Reasoning Dataset. https:\/\/huggingface.co\/datasets\/hiyouga\/geometry3k."},{"key":"e_1_3_2_2_20_1","volume-title":"Reinforce: A simple and efficient approach for aligning large language models. arXiv preprint arXiv:2501.03262","author":"Hu Jian","year":"2025","unstructured":"Jian Hu. 2025. Reinforce: A simple and efficient approach for aligning large language models. arXiv preprint arXiv:2501.03262 (2025)."},{"key":"e_1_3_2_2_21_1","volume-title":"Open-reasoner-zero: An open source approach to scaling up reinforcement learning on the base model. arXiv preprint arXiv:2503.24290","author":"Hu Jingcheng","year":"2025","unstructured":"Jingcheng Hu, Yinmin Zhang, Qi Han, Daxin Jiang, Xiangyu Zhang, and Heung-Yeung Shum. 2025. Open-reasoner-zero: An open source approach to scaling up reinforcement learning on the base model. arXiv preprint arXiv:2503.24290 (2025)."},{"key":"e_1_3_2_2_22_1","volume-title":"Xingxing Liang, Fei Wang, Zhao Zhang, Wei Wei, Boxuan Zhang, Libo Huang, et al.","author":"Huang Jincai","year":"2025","unstructured":"Jincai Huang, Yongjun Xu, Qi Wang, Qi Cheems Wang, Xingxing Liang, Fei Wang, Zhao Zhang, Wei Wei, Boxuan Zhang, Libo Huang, et al., 2025. Foundation models and intelligent decision-making: Progress, challenges, and perspectives. The Innovation (2025)."},{"key":"e_1_3_2_2_23_1","unstructured":"Aaron Jaech Adam Kalai Adam Lerer Adam Richardson Ahmed El-Kishky Aiden Low Alec Helyar Aleksander Madry Alex Beutel Alex Carney et al. 2024. Openai o1 system card. arXiv preprint arXiv:2412.16720 (2024)."},{"key":"e_1_3_2_2_24_1","volume-title":"Vineppo: Unlocking rl potential for llm reasoning through refined credit assignment. arXiv preprint arXiv:2410.01679","author":"Kazemnejad Amirhossein","year":"2024","unstructured":"Amirhossein Kazemnejad, Milad Aghajohari, Eva Portelance, Alessandro Sordoni, Siva Reddy, Aaron Courville, and Nicolas Le Roux. 2024. Vineppo: Unlocking rl potential for llm reasoning through refined credit assignment. arXiv preprint arXiv:2410.01679 (2024)."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0278"},{"key":"e_1_3_2_2_26_1","volume-title":"Limr: Less is more for rl scaling. arXiv preprint arXiv:2502.11886","author":"Li Xuefeng","year":"2025","unstructured":"Xuefeng Li, Haoyang Zou, and Pengfei Liu. 2025. Limr: Less is more for rl scaling. arXiv preprint arXiv:2502.11886 (2025)."},{"key":"e_1_3_2_2_27_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Lightman Hunter","year":"2023","unstructured":"Hunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. 2023. Let's verify step by step. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_2_28_1","volume-title":"Cppo: Accelerating the training of group relative policy optimization-based reasoning models. arXiv preprint arXiv:2503.22342","author":"Lin Zhihang","year":"2025","unstructured":"Zhihang Lin, Mingbao Lin, Yuan Xie, and Rongrong Ji. 2025. Cppo: Accelerating the training of group relative policy optimization-based reasoning models. arXiv preprint arXiv:2503.22342 (2025)."},{"key":"e_1_3_2_2_29_1","volume-title":"ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models. arXiv preprint arXiv:2505.24864","author":"Liu Mingjie","year":"2025","unstructured":"Mingjie Liu, Shizhe Diao, Ximing Lu, Jian Hu, Xin Dong, Yejin Choi, Jan Kautz, and Yi Dong. 2025b. ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models. arXiv preprint arXiv:2505.24864 (2025)."},{"key":"e_1_3_2_2_30_1","volume-title":"Wee Sun Lee, and Min Lin","author":"Liu Zichen","year":"2025","unstructured":"Zichen Liu, Changyu Chen, Wenjun Li, Penghui Qi, Tianyu Pang, Chao Du, Wee Sun Lee, and Min Lin. 2025a. Understanding r1-zero-like training: A critical perspective. arXiv preprint arXiv:2503.20783 (2025)."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.528"},{"key":"e_1_3_2_2_32_1","volume-title":"Deepcoder: A fully open-source 14b coder at o3-mini level. Notion Blog","author":"Luo Michael","year":"2025","unstructured":"Michael Luo, Sijun Tan, Roy Huang, Ameen Patel, Alpay Ariyak, Qingyang Wu, Xiaoxiang Shi, Rachel Xin, Colin Cai, Maurice Weber, et al., 2025a. Deepcoder: A fully open-source 14b coder at o3-mini level. Notion Blog (2025)."},{"key":"e_1_3_2_2_33_1","volume-title":"Li Erran Li, et al","author":"Luo Michael","year":"2025","unstructured":"Michael Luo, Sijun Tan, Justin Wong, Xiaoxiang Shi, William Y Tang, Manan Roongta, Colin Cai, Jeffrey Luo, Tianjun Zhang, Li Erran Li, et al., 2025b. Deepscaler: Surpassing o1-preview with a 1.5 b model by scaling rl. Notion Blog (2025)."},{"key":"e_1_3_2_2_34_1","volume-title":"Mm-eureka: Exploring visual aha moment with rule-based large-scale reinforcement learning. CoRR","author":"Meng Fanqing","year":"2025","unstructured":"Fanqing Meng, Lingxiao Du, Zongkai Liu, Zhixiang Zhou, Quanfeng Lu, Daocheng Fu, Botian Shi, Wenhai Wang, Junjun He, Kaipeng Zhang, et al., 2025. Mm-eureka: Exploring visual aha moment with rule-based large-scale reinforcement learning. CoRR (2025)."},{"key":"e_1_3_2_2_35_1","volume-title":"Variational continual learning. arXiv preprint arXiv:1710.10628","author":"Nguyen Cuong V","year":"2017","unstructured":"Cuong V Nguyen, Yingzhen Li, Thang D Bui, and Richard E Turner. 2017. Variational continual learning. arXiv preprint arXiv:1710.10628 (2017)."},{"key":"e_1_3_2_2_36_1","unstructured":"Jiayi Pan Junjie Zhang Xingyao Wang Lifan Yuan Hao Peng and Alane Suhr. 2025. TinyZero. https:\/\/github.com\/Jiayi-Pan\/TinyZero. Accessed: 2025-01-24."},{"key":"e_1_3_2_2_37_1","volume-title":"Yixiu Mao, Yiqin Lv, and Xiangyang Ji.","author":"Qu Yun","year":"2025","unstructured":"Yun Qu, Qi Cheems Wang, Yixiu Mao, Yiqin Lv, and Xiangyang Ji. 2025. Fast and Robust: Task Sampling with Posterior and Diversity Synergies for Adaptive Decision-Makers in Randomized Environments. arXiv preprint arXiv:2504.19139 (2025)."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2014.0650"},{"key":"e_1_3_2_2_39_1","volume-title":"High-dimensional continuous control using generalized advantage estimation. arXiv preprint arXiv:1506.02438","author":"Schulman John","year":"2015","unstructured":"John Schulman, Philipp Moritz, Sergey Levine, Michael Jordan, and Pieter Abbeel. 2015. High-dimensional continuous control using generalized advantage estimation. arXiv preprint arXiv:1506.02438 (2015)."},{"key":"e_1_3_2_2_40_1","volume-title":"Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.g7327"},{"key":"e_1_3_2_2_42_1","volume-title":"Deepseekmath: Pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300","author":"Shao Zhihong","year":"2024","unstructured":"Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, YK Li, Y Wu, et al., 2024. Deepseekmath: Pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300 (2024)."},{"key":"e_1_3_2_2_43_1","volume-title":"HybridFlow: A Flexible and Efficient RLHF Framework. arXiv preprint arXiv: 2409.19256","author":"Sheng Guangming","year":"2024","unstructured":"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. arXiv preprint arXiv: 2409.19256 (2024)."},{"key":"e_1_3_2_2_44_1","unstructured":"Zhiqing Sun Sheng Shen Shengcao Cao Haotian Liu Chunyuan Li Yikang Shen Chuang Gan Liang-Yan Gui Yu-Xiong Wang Yiming Yang et al. 2023. Aligning large multimodal models with factually augmented rlhf. arXiv preprint arXiv:2309.14525 (2023)."},{"key":"e_1_3_2_2_45_1","unstructured":"Kimi Team Angang Du Bofei Gao Bowei Xing Changjiu Jiang Cheng Chen Cheng Li Chenjun Xiao Chenzhuang Du Chonghua Liao et al. 2025. Kimi k1. 5: Scaling reinforcement learning with llms. arXiv preprint arXiv:2501.12599 (2025)."},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/25.3-4.285"},{"key":"e_1_3_2_2_47_1","volume-title":"Model predictive task sampling for efficient and robust adaptation. arXiv preprint arXiv:2501.11039","author":"Wang Qi Cheems","year":"2025","unstructured":"Qi Cheems Wang, Zehao Xiao, Yixiu Mao, Yun Qu, Jiayi Shen, Yiqin Lv, and Xiangyang Ji. 2025a. Model predictive task sampling for efficient and robust adaptation. arXiv preprint arXiv:2501.11039 (2025)."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"crossref","unstructured":"Yiping Wang Qing Yang Zhiyuan Zeng Liliang Ren Liyuan Liu Baolin Peng Hao Cheng Xuehai He Kuan Wang Jianfeng Gao et al. 2025b. Reinforcement learning for reasoning in large language models with one training example. arXiv preprint arXiv:2504.20571 (2025).","DOI":"10.52202\/085713-4093"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"crossref","unstructured":"Liang Wen Yunke Cai Fenrui Xiao Xin He Qi An Zhenyu Duan Yimin Du Junchen Liu Lifu Tang Xiaowei Lv et al. 2025. Light-r1: Curriculum sft dpo and rl for long cot from scratch and beyond. arXiv preprint arXiv:2503.10460 (2025).","DOI":"10.18653\/v1\/2025.acl-industry.24"},{"key":"e_1_3_2_2_50_1","unstructured":"Wei Xiong Jiarui Yao Yuhui Xu Bo Pang Lei Wang Doyen Sahoo Junnan Li Nan Jiang Tong Zhang Caiming Xiong et al. 2025. A minimalist approach to llm reasoning: from rejection sampling to reinforce. arXiv preprint arXiv:2504.11343 (2025)."},{"key":"e_1_3_2_2_51_1","volume-title":"Llava-o1: Let vision language models reason step-by-step. arXiv preprint arXiv:2411.10440","author":"Xu Guowei","year":"2024","unstructured":"Guowei Xu, Peng Jin, Li Hao, Yibing Song, Lichao Sun, and Li Yuan. 2024. Llava-o1: Let vision language models reason step-by-step. arXiv preprint arXiv:2411.10440 (2024)."},{"key":"e_1_3_2_2_52_1","unstructured":"An Yang Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chengyuan Li Dayiheng Liu Fei Huang Haoran Wei et al. 2024a. Qwen2. 5 Technical Report. arXiv e-prints (2024) arXiv-2412."},{"key":"e_1_3_2_2_53_1","unstructured":"An Yang Beichen Zhang Binyuan Hui Bofei Gao Bowen Yu Chengpeng Li Dayiheng Liu Jianhong Tu Jingren Zhou Junyang Lin et al. 2024b. Qwen2. 5-math technical report: Toward mathematical expert model via self-improvement. arXiv preprint arXiv:2409.12122 (2024)."},{"key":"e_1_3_2_2_54_1","volume-title":"LIMO: Less is More for Reasoning. arXiv preprint arXiv:2502.03387","author":"Ye Yixin","year":"2025","unstructured":"Yixin Ye, Zhen Huang, Yang Xiao, Ethan Chern, Shijie Xia, and Pengfei Liu. 2025. LIMO: Less is More for Reasoning. arXiv preprint arXiv:2502.03387 (2025)."},{"key":"e_1_3_2_2_55_1","volume-title":"Dapo: An open-source llm reinforcement learning system at scale. arXiv preprint arXiv:2503.14476","author":"Yu Qiying","year":"2025","unstructured":"Qiying Yu, Zheng Zhang, Ruofei Zhu, Yufeng Yuan, Xiaochen Zuo, Yu Yue, Tiantian Fan, Gaohong Liu, Lingjun Liu, Xin Liu, et al., 2025. Dapo: An open-source llm reinforcement learning system at scale. arXiv preprint arXiv:2503.14476 (2025)."},{"key":"e_1_3_2_2_56_1","volume-title":"What's Behind PPO's Collapse in Long-CoT? Value Optimization Holds the Secret. arXiv preprint arXiv:2503.01491","author":"Yuan Yufeng","year":"2025","unstructured":"Yufeng Yuan, Yu Yue, Ruofei Zhu, Tiantian Fan, and Lin Yan. 2025. What's Behind PPO's Collapse in Long-CoT? Value Optimization Holds the Secret. arXiv preprint arXiv:2503.01491 (2025)."},{"key":"e_1_3_2_2_57_1","volume-title":"Vapo: Efficient and reliable reinforcement learning for advanced reasoning tasks. arXiv preprint arXiv:2504.05118","author":"Yue Yu","year":"2025","unstructured":"Yu Yue, Yufeng Yuan, Qiying Yu, Xiaochen Zuo, Ruofei Zhu, Wenyuan Xu, Jiaze Chen, Chengyi Wang, TianTian Fan, Zhengyin Du, et al., 2025. Vapo: Efficient and reliable reinforcement learning for advanced reasoning tasks. arXiv preprint arXiv:2504.05118 (2025)."},{"key":"e_1_3_2_2_58_1","volume-title":"Simplerl-zoo: Investigating and taming zero reinforcement learning for open base models in the wild. arXiv preprint arXiv:2503.18892","author":"Zeng Weihao","year":"2025","unstructured":"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. arXiv preprint arXiv:2503.18892 (2025)."},{"key":"e_1_3_2_2_59_1","unstructured":"Weihao Zeng Yuzhen Huang Wei Liu Keqing He Qian Liu Zejun Ma and Junxian He. [n.d.]. 7b model and 8k examples: Emerging reasoning with reinforcement learning is both effective and efficient."},{"key":"e_1_3_2_2_60_1","volume-title":"Srpo: A cross-domain implementation of large-scale reinforcement learning on llm. arXiv preprint arXiv:2504.14286","author":"Zhang Xiaojiang","year":"2025","unstructured":"Xiaojiang Zhang, Jinghui Wang, Zifei Cheng, Wenhao Zhuang, Zheng Lin, Minglei Zhang, Shaojie Wang, Yinghan Cui, Chao Wang, Junyi Peng, et al., 2025. Srpo: A cross-domain implementation of large-scale reinforcement learning on llm. arXiv preprint arXiv:2504.14286 (2025)."},{"key":"e_1_3_2_2_61_1","volume-title":"Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts. arXiv preprint arXiv:2506.02177","author":"Zheng Haizhong","year":"2025","unstructured":"Haizhong Zheng, Yang Zhou, Brian R Bartoldson, Bhavya Kailkhura, Fan Lai, Jiawei Zhao, and Beidi Chen. 2025. Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts. arXiv preprint arXiv:2506.02177 (2025)."},{"key":"e_1_3_2_2_62_1","unstructured":"Rui Zheng Shihan Dou Songyang Gao Yuan Hua Wei Shen Binghai Wang Yan Liu Senjie Jin Qin Liu Yuhao Zhou et al. 2023. Secrets of rlhf in large language models part i: Ppo. arXiv preprint arXiv:2307.04964 (2023)."}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3770854.3780263","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T20:03:32Z","timestamp":1787688212000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770854.3780263"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":62,"alternative-id":["10.1145\/3770854.3780263","10.1145\/3770854"],"URL":"https:\/\/doi.org\/10.1145\/3770854.3780263","relation":{},"subject":[],"published":{"date-parts":[[2026,4,20]]},"assertion":[{"value":"2026-04-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}