{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T13:00:46Z","timestamp":1780664446674,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":116,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T00:00:00Z","timestamp":1777161600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,27]]},"DOI":"10.1145\/3767295.3803580","type":"proceedings-article","created":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T20:20:04Z","timestamp":1777062004000},"page":"400-422","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Laminar: A Scalable Asynchronous RL Post-Training Framework"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3395-3994","authenticated-orcid":false,"given":"Guangming","family":"Sheng","sequence":"first","affiliation":[{"name":"Computer Science, The University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5758-5954","authenticated-orcid":false,"given":"Yuxuan","family":"Tong","sequence":"additional","affiliation":[{"name":"ByteDance, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5902-1611","authenticated-orcid":false,"given":"Borui","family":"Wan","sequence":"additional","affiliation":[{"name":"Computer Science, The University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2436-8761","authenticated-orcid":false,"given":"Wang","family":"Zhang","sequence":"additional","affiliation":[{"name":"ByteDance Inc., San Jose, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3309-9179","authenticated-orcid":false,"given":"Chaobo","family":"Jia","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9702-5288","authenticated-orcid":false,"given":"Xibin","family":"Wu","sequence":"additional","affiliation":[{"name":"Bytedance, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6144-7399","authenticated-orcid":false,"given":"Yuqi","family":"Wu","sequence":"additional","affiliation":[{"name":"Shanghai Jiaotong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8751-4655","authenticated-orcid":false,"given":"Xiang","family":"Li","sequence":"additional","affiliation":[{"name":"Bytedance, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7374-1940","authenticated-orcid":false,"given":"Chi","family":"Zhang","sequence":"additional","affiliation":[{"name":"ByteDance, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3989-4358","authenticated-orcid":false,"given":"Yanghua","family":"Peng","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Seattle, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4879-5335","authenticated-orcid":false,"given":"Haibin","family":"Lin","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Seattle, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8346-3323","authenticated-orcid":false,"given":"Xin","family":"Liu","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Seattle, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3144-4398","authenticated-orcid":false,"given":"Chuan","family":"Wu","sequence":"additional","affiliation":[{"name":"Computer Science, The University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,26]]},"reference":[{"key":"e_1_3_2_1_1_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_1_2_1","volume-title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale. arXiv:2503.14476 [cs.LG] https:\/\/arxiv.org\/abs\/2503.14476","author":"Yu Qiying","year":"2025","unstructured":"Qiying Yu, Zheng Zhang, Ruofei Zhu, Yufeng Yuan, Xiaochen Zuo, Yu Yue, Weinan Dai, 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, Yuxuan Song, Xiangpeng Wei, Hao Zhou, Jingjing Liu, Wei-Ying Ma, Ya-Qin Zhang, Lin Yan, Mu Qiao, Yonghui Wu, and Mingxuan Wang. 2025. DAPO: An Open-Source LLM Reinforcement Learning System at Scale. arXiv:2503.14476 [cs.LG] https:\/\/arxiv.org\/abs\/2503.14476"},{"key":"e_1_3_2_1_3_1","volume-title":"Hisham Cholakkal, Mubarak Shah, Ming-Hsuan Yang, Phillip HS Torr, Fahad Shahbaz Khan, and Salman Khan.","author":"Kumar Komal","year":"2025","unstructured":"Komal Kumar, Tajamul Ashraf, Omkar Thawakar, Rao Muhammad Anwer, Hisham Cholakkal, Mubarak Shah, Ming-Hsuan Yang, Phillip HS Torr, Fahad Shahbaz Khan, and Salman Khan. 2025. Llm post-training: A deep dive into reasoning large language models. arXiv preprint arXiv:2502.21321 (2025)."},{"key":"e_1_3_2_1_4_1","unstructured":"OpenAI. 2025. Learning to reason with llms. https:\/\/openai.com\/index\/learning-to-reason-with-llms\/."},{"key":"e_1_3_2_1_5_1","unstructured":"xAI.2025. Grok4. https:\/\/x.ai\/news\/grok-4."},{"key":"e_1_3_2_1_6_1","volume-title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues? arXiv preprint arXiv: 2310.06770","author":"Jimenez Carlos E.","year":"2023","unstructured":"Carlos E. Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik Narasimhan. 2023. SWE-bench: Can Language Models Resolve Real-World GitHub Issues? arXiv preprint arXiv: 2310.06770 (2023)."},{"key":"e_1_3_2_1_7_1","unstructured":"ByteDance Seed Jiaze Chen Tiantian Fan Xin Liu Lingjun Liu Zhiqi Lin Mingxuan Wang Chengyi Wang Xiangpeng Wei Wenyuan Xu et al. 2025. Seed1. 5-thinking: Advancing superb reasoning models with reinforcement learning. arXiv preprint arXiv:2504.13914 (2025)."},{"key":"e_1_3_2_1_8_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_1_9_1","volume-title":"From System 1 to System 2: A Survey of Reasoning Large Language Models. arXiv preprint arXiv: 2502.17419","author":"Li Zhong-Zhi","year":"2025","unstructured":"Zhong-Zhi Li, Duzhen Zhang, Ming-Liang Zhang, Jiaxin Zhang, Zengyan Liu, Yuxuan Yao, Haotian Xu, Junhao Zheng, Pei-Jie Wang, Xiuyi Chen, Yingying Zhang, Fei Yin, Jiahua Dong, Zhiwei Li, Bao-Long Bi, Ling-Rui Mei, Junfeng Fang, Xiao Liang, Zhijiang Guo, Le Song, and Cheng-Lin Liu. 2025. From System 1 to System 2: A Survey of Reasoning Large Language Models. arXiv preprint arXiv: 2502.17419 (2025)."},{"key":"e_1_3_2_1_10_1","unstructured":"Taiyi Wang Zhihao Wu Jianheng Liu Jianye Hao Jun Wang and Kun Shao. 2025. DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agents. arXiv:2410.14803 [cs.LG] https:\/\/arxiv.org\/abs\/2410.14803"},{"key":"e_1_3_2_1_11_1","unstructured":"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. 2023. DeepSpeed-Chat: Easy Fast and Affordable RLHF Training of ChatGPT-like Models at All Scales. arXiv:2308.01320 [cs.LG] https:\/\/arxiv.org\/abs\/2308.01320"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3696075"},{"key":"e_1_3_2_1_13_1","volume-title":"2024 USENIX Annual Technical Conference (USENIX ATC 24)","author":"Lei Kinman","year":"2024","unstructured":"Kinman Lei, Yuyang Jin, Mingshu Zhai, Kezhao Huang, Haoxing Ye, and Jidong Zhai. 2024. PUZZLE: Efficiently Aligning Large Language Models through Light-Weight Context Switch. In 2024 USENIX Annual Technical Conference (USENIX ATC 24). USENIX Association, Santa Clara, CA, 127\u2013140. https:\/\/www.usenix.org\/conference\/atc24\/presentation\/lei"},{"key":"e_1_3_2_1_14_1","volume-title":"ReaL: Efficient RLHF Training of Large Language Models with Parameter Reallocation. arXiv preprint arXiv: 2406.14088","author":"Mei Zhiyu","year":"2024","unstructured":"Zhiyu Mei, Wei Fu, Kaiwei Li, Guangju Wang, Huanchen Zhang, and Yi Wu. 2024. ReaL: Efficient RLHF Training of Large Language Models with Parameter Reallocation. arXiv preprint arXiv: 2406.14088 (2024)."},{"key":"e_1_3_2_1_15_1","volume-title":"Rlhfuse: Efficient rlhf training for large language models with inter-and intra-stage fusion. arXiv preprint arXiv:2409.13221","author":"Zhong Yinmin","year":"2024","unstructured":"Yinmin Zhong, Zili Zhang, Bingyang Wu, Shengyu Liu, Yukun Chen, Changyi Wan, Hanpeng Hu, Lei Xia, Ranchen Ming, Yibo Zhu, et al. 2024. Rlhfuse: Efficient rlhf training for large language models with inter-and intra-stage fusion. arXiv preprint arXiv:2409.13221 (2024)."},{"key":"e_1_3_2_1_16_1","unstructured":"Jian Hu Xibin Wu Zilin Zhu Xianyu Weixun Wang Dehao Zhang and Yu Cao. 2024. OpenRLHF: An Easy-to-use Scalable and High-performance RLHF Framework. arXiv:2405.11143 [cs.AI] https:\/\/arxiv.org\/abs\/2405.11143"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","unstructured":"Yinmin Zhong Zili Zhang Xiaoniu Song Hanpeng Hu Chao Jin Bingyang Wu Nuo Chen Yukun Chen Yu Zhou Changyi Wan Hongyu Zhou Yimin Jiang Yibo Zhu and Daxin Jiang. 2025. StreamRL: Scalable Heterogeneous and Elastic RL for LLMs with Disaggregated Stream Generation. arXiv:2504.15930 [cs] 10.48550\/arXiv.2504.15930","DOI":"10.48550\/arXiv.2504.15930"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","unstructured":"Wei Fu Jiaxuan Gao Xujie Shen Chen Zhu Zhiyu Mei Chuyi He Shusheng Xu Guo Wei Jun Mei Jiashu Wang Tongkai Yang Binhang Yuan and Yi Wu. 2025. ***AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning. arXiv:2505.24298 [cs] 10.48550\/arXiv.2505.24298","DOI":"10.48550\/arXiv.2505.24298"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","unstructured":"Bo Wu Sid Wang Yunhao Tang Jia Ding Eryk Helenowski Liang Tan Tengyu Xu Tushar Gowda Zhengxing Chen Chen Zhu Xiaocheng Tang Yundi Qian Beibei Zhu and Rui Hou. 2025. LlamaRL: A Distributed Asynchronous Reinforcement Learning Framework for Efficient Large-scale LLM Training. arXiv:2505.24034 [cs] 10.48550\/arXiv.2505.24034","DOI":"10.48550\/arXiv.2505.24034"},{"key":"e_1_3_2_1_20_1","volume-title":"Raluca Ada Popa, and Ion Stoica.","author":"Tan Sijun","year":"2025","unstructured":"Sijun Tan, Michael Luo, Colin Cai, Tarun Venkat, Kyle Montgomery, Aaron Hao, Tianhao Wu, Arnav Balyan, Manan Roongta, Chenguang Wang, Li Erran Li, Raluca Ada Popa, and Ion Stoica. 2025. rLLM: A Framework for Post-Training Language Agents. https:\/\/pretty-radio-b75.notion.site\/rLLM-A-Framework-for-Post-Training-Language-Agents-21b81902c146819db63cd98a54ba5f31. Notion Blog."},{"key":"e_1_3_2_1_21_1","volume-title":"Jannik Straube, Manveer Basra, Aaron Pazdera, Kushal Thaman, Matthew Di Ferrante, Felix Gabriel, Fares Obeid, Kemal Erdem, Michael Keiblinger, and Johannes Hagemann.","author":"Team Prime Intellect","year":"2025","unstructured":"Prime Intellect Team, Sami Jaghouar, Justus Mattern, Jack Min Ong, Jannik Straube, Manveer Basra, Aaron Pazdera, Kushal Thaman, Matthew Di Ferrante, Felix Gabriel, Fares Obeid, Kemal Erdem, Michael Keiblinger, and Johannes Hagemann. 2025. INTELLECT-2: A Reasoning Model Trained Through Globally Decentralized Reinforcement Learning. arXiv:2505.07291 [cs.LG] https:\/\/arxiv.org\/abs\/2505.07291"},{"key":"e_1_3_2_1_22_1","unstructured":"Zhenyu Han Ansheng You Haibo Wang Kui Luo Guang Yang Wenqi Shi Menglong Chen Sicheng Zhang Zeshun Lan Chunshi Deng Huazhong Ji Wenjie Liu Yu Huang Yixiang Zhang Chenyi Pan Jing Wang Xin Huang Chunsheng Li and Jianping Wu. 2025. AsyncFlow: An Asynchronous Streaming RL Framework for Efficient LLM Post-Training. arXiv:2507.01663 [cs.LG] https:\/\/arxiv.org\/abs\/2507.01663"},{"key":"e_1_3_2_1_23_1","volume-title":"ASYNCHRONOUS RLHF: FASTER AND MORE EFFICIENT OFF-POLICY RL FOR LANGUAGE MODELS.","author":"Noukhovitch Michael","year":"2025","unstructured":"Michael Noukhovitch, Shengyi Huang, Rishabh Agarwal, Aaron Courville, Sophie Xhonneux, and Arian Hosseini. 2025. ASYNCHRONOUS RLHF: FASTER AND MORE EFFICIENT OFF-POLICY RL FOR LANGUAGE MODELS. (2025)."},{"key":"e_1_3_2_1_24_1","unstructured":"Christopher Berner Greg Brockman Brooke Chan Vicki Cheung Przemys\u0142aw D\u0119biak Christy Dennison David Farhi Quirin Fischer Shariq Hashme Chris Hesse et al. 2019. Dota 2 with large scale deep reinforcement learning. arXiv preprint arXiv:1912.06680 (2019)."},{"key":"e_1_3_2_1_25_1","volume-title":"Nam Sung Kim, and Alexander Schwing","author":"Li Youjie","year":"2018","unstructured":"Youjie Li, Mingchao Yu, Songze Li, Salman Avestimehr, Nam Sung Kim, and Alexander Schwing. 2018. Pipe-SGD: A decentralized pipelined SGD framework for distributed deep net training. Advances in Neural Information Processing Systems 31 (2018)."},{"key":"e_1_3_2_1_26_1","volume-title":"Gap aware mitigation of gradient staleness. arXiv preprint arXiv:1909.10802","author":"Barkai Saar","year":"2019","unstructured":"Saar Barkai, Ido Hakimi, and Assaf Schuster. 2019. Gap aware mitigation of gradient staleness. arXiv preprint arXiv:1909.10802 (2019)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Yangrui Chen Cong Xie Meng Ma Juncheng Gu Yanghua Peng Haibin Lin Chuan Wu and Yibo Zhu. 2022. SAPipe: Staleness-Aware Pipeline for Data Parallel DNN Training. In Advances in Neural Information Processing Systems.","DOI":"10.52202\/068431-1307"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671844"},{"key":"e_1_3_2_1_29_1","volume-title":"Swe-bench: Can language models resolve real-world github issues? arXiv preprint arXiv:2310.06770","author":"Jimenez Carlos E","year":"2023","unstructured":"Carlos E Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik Narasimhan. 2023. Swe-bench: Can language models resolve real-world github issues? arXiv preprint arXiv:2310.06770 (2023)."},{"key":"e_1_3_2_1_30_1","unstructured":"Yao Cheng Jianfeng Chen Jie Chen Li Chen Liyu Chen and et al. 2025. FullStack Bench: Evaluating LLMs as Full Stack Coders. arXiv:2412.00535 [cs.AI] https:\/\/arxiv.org\/abs\/2412.00535"},{"key":"e_1_3_2_1_31_1","unstructured":"OpenAI. 2025. Introducing deep research. https:\/\/openai.com\/index\/introducing-deep-research\/."},{"key":"e_1_3_2_1_32_1","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang Long","year":"2022","unstructured":"Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems 35 (2022), 27730\u201327744.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_33_1","unstructured":"Yuntao Bai Andy Jones Kamal Ndousse Amanda Askell Anna Chen Nova DasSarma Dawn Drain Stanislav Fort Deep Ganguli Tom Henighan et al. 2022. Training a helpful and harmless assistant with reinforcement learning from human feedback. arXiv preprint arXiv:2204.05862 (2022)."},{"key":"e_1_3_2_1_34_1","volume-title":"The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=TyFrPOKYXw","author":"Dai Josef","year":"2024","unstructured":"Josef Dai, Xuehai Pan, Ruiyang Sun, Jiaming Ji, Xinbo Xu, Mickel Liu, Yizhou Wang, and Yaodong Yang. 2024. Safe RLHF: Safe Reinforcement Learning from Human Feedback. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=TyFrPOKYXw"},{"key":"e_1_3_2_1_35_1","unstructured":"Rui Zheng Wei Shen Yuan Hua Wenbin Lai Shihan Dou Yuhao Zhou Zhiheng Xi Xiao Wang Haoran Huang Tao Gui et al. 2023. Improving generalization of alignment with human preferences through group invariant learning. arXiv preprint arXiv:2310.11971 (2023)."},{"key":"e_1_3_2_1_36_1","volume-title":"Rlaif: Scaling reinforcement learning from human feedback with ai feedback. arXiv preprint arXiv:2309.00267","author":"Lee Harrison","year":"2023","unstructured":"Harrison Lee, Samrat Phatale, Hassan Mansoor, Kellie Lu, Thomas Mesnard, Colton Bishop, Victor Carbune, and Abhinav Rastogi. 2023. Rlaif: Scaling reinforcement learning from human feedback with ai feedback. arXiv preprint arXiv:2309.00267 (2023)."},{"key":"e_1_3_2_1_37_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_1_38_1","volume-title":"ReTool: Reinforcement Learning for Strategic Tool Use in LLMs. arXiv preprint arXiv: 2504.11536","author":"Feng Jiazhan","year":"2025","unstructured":"Jiazhan Feng, Shijue Huang, Xingwei Qu, Ge Zhang, Yujia Qin, Baoquan Zhong, Chengquan Jiang, Jinxin Chi, and Wanjun Zhong. 2025. ReTool: Reinforcement Learning for Strategic Tool Use in LLMs. arXiv preprint arXiv: 2504.11536 (2025)."},{"key":"e_1_3_2_1_39_1","volume-title":"AIME","author":"Mathematical Association of America.","year":"2024","unstructured":"Mathematical Association of America. 2024. AIME 2024."},{"key":"e_1_3_2_1_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_1_41_1","doi-asserted-by":"crossref","unstructured":"Arash Ahmadian Chris Cremer Matthias Gall\u00e9 Marzieh Fadaee Julia Kreutzer Olivier Pietquin Ahmet \u00dcst\u00fcn and Sara Hooker. 2024. Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs. arXiv:2402.14740 [cs.LG] https:\/\/arxiv.org\/abs\/2402.14740","DOI":"10.18653\/v1\/2024.acl-long.662"},{"key":"e_1_3_2_1_42_1","unstructured":"Gr\u00e9goire Mialon Cl\u00e9mentine Fourrier Craig Swift Thomas Wolf Yann LeCun and Thomas Scialom. 2023. GAIA: a benchmark for General AI Assistants. arXiv:2311.12983 [cs.CL] https:\/\/arxiv.org\/abs\/2311.12983"},{"key":"e_1_3_2_1_43_1","volume-title":"Zhoujun Cheng, Dongchan Shin, Fangyu Lei, Yitao Liu, Yiheng Xu, Shuyan Zhou, Silvio Savarese, Caiming Xiong, Victor Zhong, and Tao Yu.","author":"Xie Tianbao","year":"2024","unstructured":"Tianbao Xie, Danyang Zhang, Jixuan Chen, Xiaochuan Li, Siheng Zhao, Ruisheng Cao, Toh Jing Hua, Zhoujun Cheng, Dongchan Shin, Fangyu Lei, Yitao Liu, Yiheng Xu, Shuyan Zhou, Silvio Savarese, Caiming Xiong, Victor Zhong, and Tao Yu. 2024. OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments. arXiv:2404.07972 [cs.AI] https:\/\/arxiv.org\/abs\/2404.07972"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","unstructured":"Oriol Vinyals Igor Babuschkin Wojciech M Czarnecki Micha\u00ebl Mathieu Andrew Dudzik Junyoung Chung David H Choi Richard Powell Timo Ewalds Petko Georgiev et al. 2019. Grandmaster level in Star-Craft II using multi-agent reinforcement learning. nature 575 7782 (2019) 350\u2013354.","DOI":"10.1038\/s41586-019-1724-z"},{"key":"e_1_3_2_1_45_1","volume-title":"Ashwath Aithal, and Oleksii Kuchaiev.","author":"Shen Gerald","year":"2024","unstructured":"Gerald Shen, Zhilin Wang, Olivier Delalleau, Jiaqi Zeng, Yi Dong, Daniel Egert, Shengyang Sun, Jimmy Zhang, Sahil Jain, Ali Taghibakhshi, Markel Sanz Ausin, Ashwath Aithal, and Oleksii Kuchaiev. 2024. NeMo-Aligner: Scalable Toolkit for Efficient Model Alignment. arXiv:2405.01481 [cs.CL] https:\/\/arxiv.org\/abs\/2405.01481"},{"key":"e_1_3_2_1_46_1","volume-title":"An Adaptive Placement and Parallelism Framework for Accelerating RLHF Training. arXiv preprint arXiv: 2312.11819","author":"Xiao Youshao","year":"2023","unstructured":"Youshao Xiao, Zhenglei Zhou, Fagui Mao, Weichang Wu, Shangchun Zhao, Lin Ju, Lei Liang, Xiaolu Zhang, and Jun Zhou. 2023. An Adaptive Placement and Parallelism Framework for Accelerating RLHF Training. arXiv preprint arXiv: 2312.11819 (2023)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"e_1_3_2_1_48_1","volume-title":"Conference on robot learning. PMLR, 806\u2013816","author":"Kahn Gregory","year":"2018","unstructured":"Gregory Kahn, Adam Villaflor, Pieter Abbeel, and Sergey Levine. 2018. Composable action-conditioned predictors: Flexible off-policy learning for robot navigation. In Conference on robot learning. PMLR, 806\u2013816."},{"key":"e_1_3_2_1_49_1","volume-title":"23rd USENIX Conference on File and Storage Technologies (FAST 25)","author":"Qin Ruoyu","year":"2025","unstructured":"Ruoyu Qin, Zheming Li, Weiran He, Jialei Cui, Feng Ren, Mingxing Zhang, Yongwei Wu, Weimin Zheng, and Xinran Xu. 2025. Mooncake: Trading more storage for less computation\u2014a {KVCache-centric} architecture for serving {LLM} chatbot. In 23rd USENIX Conference on File and Storage Technologies (FAST 25). 155\u2013170."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_2_1_51_1","volume-title":"19th USENIX Symposium on Operating Systems Design and Implementation (OSDI 25)","author":"Zhu Kan","year":"2025","unstructured":"Kan Zhu, Yufei Gao, Yilong Zhao, Liangyu Zhao, Gefei Zuo, Yile Gu, Dedong Xie, Zihao Ye, Keisuke Kamahori, Chien-Yu Lin, et al. 2025. {NanoFlow}: Towards Optimal Large Language Model Serving Throughput. In 19th USENIX Symposium on Operating Systems Design and Implementation (OSDI 25). 749\u2013765."},{"key":"e_1_3_2_1_52_1","volume-title":"Shiyi Cao, Christos Kozyrakis, Ion Stoica, Joseph E. Gonzalez, Clark Barrett, and Ying Sheng.","author":"Zheng Lianmin","year":"2023","unstructured":"Lianmin Zheng, Liangsheng Yin, Zhiqiang Xie, Jeff Huang, Chuyue Sun, Cody Hao Yu, Shiyi Cao, Christos Kozyrakis, Ion Stoica, Joseph E. Gonzalez, Clark Barrett, and Ying Sheng. 2023. Efficiently Programming Large Language Models using SGLang. arXiv preprint arXiv: 2312.07104 (2023)."},{"key":"e_1_3_2_1_53_1","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Agrawal Amey","year":"2024","unstructured":"Amey Agrawal, Nitin Kedia, Ashish Panwar, Jayashree Mohan, Nipun Kwatra, Bhargav Gulavani, Alexey Tumanov, and Ramachandran Ramjee. 2024. Taming {Throughput-Latency} tradeoff in {LLM} inference with {Sarathi-Serve}. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24). 117\u2013134."},{"key":"e_1_3_2_1_54_1","volume-title":"18th USENIX symposium on operating systems design and implementation (OSDI 24)","author":"Sun Biao","year":"2024","unstructured":"Biao Sun, Ziming Huang, Hanyu Zhao, Wencong Xiao, Xinyi Zhang, Yong Li, and Wei Lin. 2024. Llumnix: Dynamic scheduling for large language model serving. In 18th USENIX symposium on operating systems design and implementation (OSDI 24). 173\u2013191."},{"key":"e_1_3_2_1_55_1","unstructured":"Ruidong Zhu Ziheng Jiang Chao Jin Peng Wu Cesar A Stuardo Dongyang Wang Xinlei Zhang Huaping Zhou Haoran Wei Yang Cheng et al. 2025. MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism. arXiv preprint arXiv:2504.02263 (2025)."},{"key":"e_1_3_2_1_56_1","unstructured":"Kimi Team Yifan Bai Yiping Bao Guanduo Chen Jiahao Chen Ningxin Chen Ruijue Chen Yanru Chen Yuankun Chen Yutian Chen et al. 2025. Kimi K2: Open Agentic Intelligence. arXiv preprint arXiv:2507.20534 (2025)."},{"key":"e_1_3_2_1_57_1","unstructured":"2023. NVIDIA Collective Communications Library (NCCL). https:\/\/developer.nvidia.com\/nccl"},{"key":"e_1_3_2_1_58_1","unstructured":"Zhiyi Hu Siyuan Shen Tommaso Bonato Sylvain Jeaugey Cedell Alexander Eric Spada James Dinan Jeff Hammond and Torsten Hoefler. 2025. Demystifying NCCL: An In-depth Analysis of GPU Communication Protocols and Algorithms. arXiv:2507.04786 [cs.DC] https:\/\/arxiv.org\/abs\/2507.04786"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3694715.3695975"},{"key":"e_1_3_2_1_60_1","volume-title":"ByteCheckpoint: A Unified Checkpointing System for Large Foundation Model Development. In 22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25)","author":"Wan Borui","year":"2025","unstructured":"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. 2025. ByteCheckpoint: A Unified Checkpointing System for Large Foundation Model Development. In 22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25). USENIX Association, Philadelphia, PA, 559\u2013578. https:\/\/www.usenix.org\/conference\/nsdi25\/presentation\/wan-borui"},{"key":"e_1_3_2_1_61_1","volume-title":"Proceedings of the ACM SIGOPS 31th Symposium on Operating Systems Principles.","author":"Yingyi Hao Rong Chen Tianle Sun","year":"2025","unstructured":"Tianle Sun Yingyi Hao Rong Chen Mingcong Han Jinyu Gu Xingda Wei, Zhuobin Huang and Haibo Chen. 2025. PhoenixOS: Concurrent OS-level GPU Checkpoint and Restore with Validated Speculation. In Proceedings of the ACM SIGOPS 31th Symposium on Operating Systems Principles."},{"key":"e_1_3_2_1_62_1","unstructured":"2023. SageMaker. https:\/\/docs.aws.amazon.com\/sagemaker\/index.html."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.5555\/3691825.3691864"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2306.16688"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/1629080.1629085"},{"key":"e_1_3_2_1_66_1","volume-title":"Jonathan Raiman, Tim Salimans, Jeremy Schlatter, Jonas Schneider, Szymon Sidor, Ilya Sutskever, Jie Tang, Filip Wolski, and Susan Zhang.","author":"Berner Christopher","year":"2019","unstructured":"OpenAI,:, Christopher Berner, Greg Brockman, Brooke Chan, Vicki Cheung, Przemys\u0142aw D\u0119biak, Christy Dennison, David Farhi, Quirin Fischer, Shariq Hashme, Chris Hesse, Rafal J\u00f3zefowicz, Scott Gray, Catherine Olsson, Jakub Pachocki, Michael Petrov, Henrique P. d. O. Pinto, Jonathan Raiman, Tim Salimans, Jeremy Schlatter, Jonas Schneider, Szymon Sidor, Ilya Sutskever, Jie Tang, Filip Wolski, and Susan Zhang. 2019. Dota 2 with Large Scale Deep Reinforcement Learning. arXiv preprint arXiv: 1912.06680 (2019)."},{"key":"e_1_3_2_1_67_1","unstructured":"Sanfilippo S. 2009. \"Redis In-memory Data Structure Server\". https:\/\/redis.io\/"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"crossref","DOI":"10.2172\/968546","volume-title":"Technical Report","author":"Ikkert Michael","year":"2009","unstructured":"Michael Ikkert, Tim Kieritz, and Peter Sanders. 2009. Parallele Algorithmen. Technical Report. Karlsruher Institut f\u00fcr Technologie (KIT). https:\/\/ae.iti.kit.edu\/documents\/teaching\/parauele-algorithmen\/ws18\/skript.pdf Stand: 16. Oktober 2009."},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613145"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359642"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0022-0000(74)80026-7"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/322186.322187"},{"key":"e_1_3_2_1_73_1","volume-title":"Graham","author":"Johnson David S.","year":"1974","unstructured":"David S. Johnson, Alan Demers, Jeffrey D. Ullman, Michael R Garey, and Ronald L. Graham. 1974. Worst-case performance bounds for simple one-dimensional packing algorithms. SIAM Journal on computing 3, 4 (1974), 299\u2013325."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"e_1_3_2_1_75_1","volume-title":"Yan Yan, Beidi Chen, Guangyu Sun, and Kurt Keutzer.","author":"Yuan Zhihang","year":"2024","unstructured":"Zhihang Yuan, Yuzhang Shang, Yang Zhou, Zhen Dong, Zhe Zhou, Chenhao Xue, Bingzhe Wu, Zhikai Li, Qingyi Gu, Yong Jae Lee, Yan Yan, Beidi Chen, Guangyu Sun, and Kurt Keutzer. 2024. LLM Inference Unveiled: Survey and Roofline Model Insights. arXiv:2402.16363 [cs.CL] https:\/\/arxiv.org\/abs\/2402.16363"},{"key":"e_1_3_2_1_76_1","unstructured":"Tom Schaul John Quan Ioannis Antonoglou and David Silver. 2016. Prioritized Experience Replay. arXiv:1511.05952"},{"key":"e_1_3_2_1_77_1","volume-title":"Gianni De Fabritiis, and Vincent Moens","author":"Bou Albert","year":"2023","unstructured":"Albert Bou, Matteo Bettini, Sebastian Dittert, Vikash Kumar, Shagun Sodhani, Xiaomeng Yang, Gianni De Fabritiis, and Vincent Moens. 2023. TorchRL: A data-driven decision-making library for PyTorch. arXiv:2306.00577 [cs.LG] https:\/\/arxiv.org\/abs\/2306.00577"},{"key":"e_1_3_2_1_78_1","volume-title":"13th USENIX symposium on operating systems design and implementation (OSDI 18)","author":"Moritz Philipp","year":"2018","unstructured":"Philipp Moritz, Robert Nishihara, Stephanie Wang, Alexey Tumanov, Richard Liaw, Eric Liang, Melih Elibol, Zongheng Yang, William Paul, Michael I Jordan, et al. 2018. Ray: A distributed framework for emerging {AI} applications. In 13th USENIX symposium on operating systems design and implementation (OSDI 18). 561\u2013577."},{"key":"e_1_3_2_1_79_1","unstructured":"2019. Unified Communication X. https:\/\/github.com\/openucx\/ucx"},{"key":"e_1_3_2_1_80_1","volume-title":"arXiv preprint arXiv: 2412.15115","author":"Team Qwen","year":"2024","unstructured":"Qwen Team, 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, Keming Lu, Keqin Bao, Kexin Yang, Le Yu, Mei Li, Mingfeng Xue, Pei Zhang, Qin Zhu, Rui Men, Runji Lin, Tianhao Li, Tianyi Tang, Tingyu Xia, Xingzhang Ren, Xuancheng Ren, Yang Fan, Yang Su, Yichang Zhang, Yu Wan, Yuqiong Liu, Zeyu Cui, Zhenru Zhang, and Zihan Qiu. 2024. Qwen2.5 Technical Report. arXiv preprint arXiv: 2412.15115 (2024)."},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.14778\/3611540.3611569"},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476209"},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1145\/3704435"},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1145\/1465482.1465560"},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","unstructured":"Jacob Hilton Karl Cobbe and John Schulman. 2022. Batch Size-Invariance for Policy Optimization. arXiv:2110.00641 10.48550\/arXiv.2110.00641","DOI":"10.48550\/arXiv.2110.00641"},{"key":"e_1_3_2_1_86_1","unstructured":"Collosal-AI Corporation. 2023. Collosal-Chat. https:\/\/github.com\/binmakeswell\/ColossalChat"},{"key":"e_1_3_2_1_87_1","volume-title":"TRL: Transformer Reinforcement Learning. https:\/\/github.com\/huggingface\/trl.","author":"von Werra Leandro","year":"2020","unstructured":"Leandro von Werra, Younes Belkada, Lewis Tunstall, Edward Beeching, Tristan Thrush, Nathan Lambert, Shengyi Huang, Kashif Rasul, and Quentin Gallou\u00e9dec. 2020. TRL: Transformer Reinforcement Learning. https:\/\/github.com\/huggingface\/trl."},{"key":"e_1_3_2_1_88_1","unstructured":"2025. NeMo RL: A Scalable and Efficient Post-Training Library. https:\/\/github.com\/NVIDIA-NeMo\/RL. GitHub repository."},{"key":"e_1_3_2_1_89_1","unstructured":"Tyler Griggs Sumanth Hegde Eric Tang Shu Liu Shiyi Cao Dacheng Li Charlie Ruan Philipp Moritz Kourosh Hakhamaneshi Richard Liaw Akshay Malik Matei Zaharia Joseph E. Gonzalez and Ion Stoica. 2025. Evolving SkyRL into a Highly-Modular RL Framework. Notion Blog."},{"key":"e_1_3_2_1_90_1","unstructured":"Zilin Zhu Chengxing Xie Xin Lv and slime Contributors. 2025. slime: An LLM post-training framework for RL Scaling. https:\/\/github.com\/THUDM\/slime. GitHub repository. Corresponding author: Xin Lv."},{"key":"e_1_3_2_1_91_1","unstructured":"C. Hesse M. Plappert A. Radford J. Schulman S. Sidor and Y. Wu. 2017. OpenAI baselines. https:\/\/github.com\/openai\/baselines"},{"key":"e_1_3_2_1_92_1","volume-title":"Tensorflow agents: Efficient batched reinforcement learning in tensorflow. arXiv preprint arXiv:1709.02878","author":"Hafner Danijar","year":"2017","unstructured":"Danijar Hafner, James Davidson, and Vincent Vanhoucke. 2017. Tensorflow agents: Efficient batched reinforcement learning in tensorflow. arXiv preprint arXiv:1709.02878 (2017)."},{"key":"e_1_3_2_1_93_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.01561"},{"key":"e_1_3_2_1_94_1","volume-title":"Proceedings of the 35th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"3062","author":"Liang Eric","year":"2018","unstructured":"Eric Liang, Richard Liaw, Robert Nishihara, Philipp Moritz, Roy Fox, Ken Goldberg, Joseph Gonzalez, Michael Jordan, and Ion Stoica. 2018. RLlib: Abstractions for Distributed Reinforcement Learning. In Proceedings of the 35th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 80), Jennifer Dy and Andreas Krause (Eds.). PMLR, 3053\u20133062. https:\/\/proceedings.mlr.press\/v80\/liang18b.html"},{"key":"e_1_3_2_1_95_1","volume-title":"Wortman Vaughan (Eds.)","volume":"34","author":"Liang Eric","year":"2021","unstructured":"Eric Liang, Zhanghao Wu, Michael Luo, Sven Mika, Joseph E Gonzalez, and Ion Stoica. 2021. RLlib Flow: Distributed Reinforcement Learning is a Dataflow Problem. In Advances in Neural Information Processing Systems, M. Ranzato, A. Beygelzimer, Y. Dauphin, P.S. Liang, and J. Wortman Vaughan (Eds.), Vol. 34. Curran Associates, Inc., 5506\u20135517. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/2bce32ed409f5ebcee2a7b417ad9beed-Paper.pdf"},{"key":"e_1_3_2_1_96_1","first-page":"1","article-title":"Tianshou: A Highly Modularized Deep Reinforcement Learning Library","volume":"23","author":"Weng Jiayi","year":"2022","unstructured":"Jiayi Weng, Huayu Chen, Dong Yan, Kaichao You, Alexis Duburcq, Minghao Zhang, Yi Su, Hang Su, and Jun Zhu. 2022. Tianshou: A Highly Modularized Deep Reinforcement Learning Library. Journal of Machine Learning Research 23, 267 (2022), 1\u20136. http:\/\/jmlr.org\/papers\/v23\/21-1127.html","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_97_1","volume-title":"Weinberger (Eds.)","volume":"24","author":"Recht Benjamin","year":"2011","unstructured":"Benjamin Recht, Christopher Re, Stephen Wright, and Feng Niu. 2011. Hogwild!: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent. In Advances in Neural Information Processing Systems, J. Shawe-Taylor, R. Zemel, P. Bartlett, F. Pereira, and K.Q. Weinberger (Eds.), Vol. 24. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2011\/file\/218a0aefd1d1a4be65601cc6ddc1520e-Paper.pdf"},{"key":"e_1_3_2_1_98_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"e_1_3_2_1_99_1","volume-title":"Mehdi Mirza, Alex Graves, Timothy P. Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu.","author":"Mnih Volodymyr","year":"2016","unstructured":"Volodymyr Mnih, Adri\u00e0 Puigdom\u00e8nech Badia, Mehdi Mirza, Alex Graves, Timothy P. Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu. 2016. Asynchronous Methods for Deep Reinforcement Learning. (June 2016). arXiv:1602.01783 [cs.LG]"},{"key":"e_1_3_2_1_100_1","unstructured":"Dan Horgan John Quan David Budden Gabriel Barth-Maron Matteo Hessel Hado van Hasselt and David Silver. 2018. Distributed Prioritized Experience Replay. arXiv:1803.00933 [cs]"},{"key":"e_1_3_2_1_101_1","volume-title":"Reverb: A Framework For Experience Replay. arXiv:2102.04736 [cs.LG]","author":"Cassirer Albin","year":"2021","unstructured":"Albin Cassirer, Gabriel Barth-Maron, Eugene Brevdo, Sabela Ramos, Toby Boyd, Thibault Sottiaux, and Manuel Kroiss. 2021. Reverb: A Framework For Experience Replay. arXiv:2102.04736 [cs.LG]"},{"key":"e_1_3_2_1_102_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning. PMLR, 36380\u201336390","author":"Wang Hanjing","year":"2023","unstructured":"Hanjing Wang, Man-Kit Sit, Congjie He, Ying Wen, Weinan Zhang, Jun Wang, Yaodong Yang, and Luo Mai. 2023. GEAR: A GPU-Centric Experience Replay System for Large Reinforcement Learning Models. In Proceedings of the 40th International Conference on Machine Learning. PMLR, 36380\u201336390."},{"key":"e_1_3_2_1_103_1","volume-title":"21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","author":"Zu Yazhou","year":"2024","unstructured":"Yazhou Zu, Alireza Ghaffarkhah, Hoang-Vu Dang, Brian Towles, Steven Hand, Safeen Huda, Adekunle Bello, Alexander Kolbasov, Arash Rezaei, Dayou Du, Steve Lacy, Hang Wang, Aaron Wisner, Chris Lewis, and Henri Bahini. 2024. Resiliency at Scale: Managing Google's TPUv4 Machine Learning Supercomputer. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). USENIX Association, Santa Clara, CA, 761\u2013774. https:\/\/www.usenix.org\/conference\/nsdi24\/presentation\/zu"},{"key":"e_1_3_2_1_104_1","volume-title":"Characterization of Large Language Model Development in the Datacenter. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","author":"Hu Qinghao","year":"2024","unstructured":"Qinghao Hu, Zhisheng Ye, Zerui Wang, Guoteng Wang, Meng Zhang, Qiaoling Chen, Peng Sun, Dahua Lin, Xiaolin Wang, Yingwei Luo, Yonggang Wen, and Tianwei Zhang. 2024. Characterization of Large Language Model Development in the Datacenter. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). USENIX Association, Santa Clara, CA, 709\u2013729. https:\/\/www.usenix.org\/conference\/nsdi24\/presentation\/hu"},{"key":"e_1_3_2_1_105_1","volume-title":"21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","author":"Jiang Ziheng","year":"2024","unstructured":"Ziheng Jiang, Haibin Lin, Yinmin Zhong, Qi Huang, Yangrui Chen, Zhi Zhang, Yanghua Peng, Xiang Li, Cong Xie, Shibiao Nong, Yulu Jia, Sun He, Hongmin Chen, Zhihao Bai, Qi Hou, Shipeng Yan, Ding Zhou, Yiyao Sheng, Zhuo Jiang, Haohan Xu, Haoran Wei, Zhang Zhang, Pengfei Nie, Leqi Zou, Sida Zhao, Liang Xiang, Zherui Liu, Zhe Li, Xiaoying Jia, Jianxi Ye, Xin Jin, and Xin Liu. 2024. MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). USENIX Association, Santa Clara, CA, 745\u2013760. https:\/\/www.usenix.org\/conference\/nsdi24\/presentation\/jiang-ziheng"},{"key":"e_1_3_2_1_106_1","volume-title":"Evolution of Aegis: Fault Diagnosis for AI Model Training Service in Production. In 22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25)","author":"Dong Jianbo","year":"2025","unstructured":"Jianbo Dong, Kun Qian, Pengcheng Zhang, Zhilong Zheng, Liang Chen, Fei Feng, Yichi Xu, Yikai Zhu, Gang Lu, Xue Li, Zhihui Ren, Zhicheng Wang, Bin Luo, Peng Zhang, Yang Liu, Yanqing Chen, Yu Guan, Weicheng Wang, Chaojie Yang, Yang Zhang, Man Yuan, Hanyu Zhao, Yong Li, Zihan Zhao, Shan Li, Xianlong Zeng, Zhiping Yao, Binzhang Fu, Ennan Zhai, Wei Lin, Chao Wang, and Dennis Cai. 2025. Evolution of Aegis: Fault Diagnosis for AI Model Training Service in Production. In 22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25). USENIX Association, Philadelphia, PA, 865\u2013881. https:\/\/www.usenix.org\/conference\/nsdi25\/presentation\/dong"},{"key":"e_1_3_2_1_107_1","volume-title":"Mycroft: Tracing Dependencies in Collective Communication Towards Reliable LLM Training. arXiv preprint arXiv:2509.03018","author":"Deng Yangtao","year":"2025","unstructured":"Yangtao Deng, Lei Zhang, Qinlong Wang, Xiaoyun Zhi, Xinlei Zhang, Zhuo Jiang, Haohan Xu, Lei Wang, Zuquan Song, Gaohong Liu, et al. 2025. Mycroft: Tracing Dependencies in Collective Communication Towards Reliable LLM Training. arXiv preprint arXiv:2509.03018 (2025)."},{"key":"e_1_3_2_1_108_1","doi-asserted-by":"crossref","unstructured":"Borui Wan Gaohong Liu Zuquan Song Jun Wang Yun Zhang Guangming Sheng Shuguang Wang Houmin Wei Chenyuan Wang Weiqiang Lou Xi Yang Mofan Zhang Kaihua Jiang Cheng Ren Xiaoyun Zhi Menghan Yu Zhe Nan Zhuolin Zheng Baoquan Zhong Qinlong Wang Huan Yu Jinxin Chi Wang Zhang Yuhan Li Zixian Du Sida Zhao Yongqiang Zhang Jingzhe Tang Zherui Liu Chuan Wu Yanghua Peng Haibin Lin Wencong Xiao Xin Liu and Liang Xiang. 2025. Robust LLM Training Infrastructure at ByteDance. arXiv:2509.16293 [cs.LG] https:\/\/arxiv.org\/abs\/2509.16293","DOI":"10.1145\/3731569.3764838"},{"key":"e_1_3_2_1_109_1","doi-asserted-by":"publisher","DOI":"10.1145\/3572848.3577510"},{"key":"e_1_3_2_1_110_1","doi-asserted-by":"publisher","DOI":"10.1145\/2829988.2787483"},{"key":"e_1_3_2_1_111_1","doi-asserted-by":"publisher","DOI":"10.1145\/2999572.2999609"},{"key":"e_1_3_2_1_112_1","volume-title":"NetBouncer: Active Device and Link Failure Localization in Data Center Networks. In 16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19)","author":"Tan Cheng","year":"2019","unstructured":"Cheng Tan, Ze Jin, Chuanxiong Guo, Tianrong Zhang, Haitao Wu, Karl Deng, Dongming Bi, and Dong Xiang. 2019. NetBouncer: Active Device and Link Failure Localization in Data Center Networks. In 16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19). USENIX Association, Boston, MA, 599\u2013614. https:\/\/www.usenix.org\/conference\/nsdi19\/presentation\/tan"},{"key":"e_1_3_2_1_113_1","volume-title":"Hostping: Diagnosing Intra-host Network Bottlenecks in RDMA Servers. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Liu Kefei","year":"2023","unstructured":"Kefei Liu, Zhuo Jiang, Jiao Zhang, Haoran Wei, Xiaolong Zhong, Lizhuang Tan, Tian Pan, and Tao Huang. 2023. Hostping: Diagnosing Intra-host Network Bottlenecks in RDMA Servers. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). USENIX Association, Boston, MA, 15\u201329. https:\/\/www.usenix.org\/conference\/nsdi23\/presentation\/liu-kefei"},{"key":"e_1_3_2_1_114_1","volume-title":"Fine-Grained DNN Checkpointing. In 19th USENIX Conference on File and Storage Technologies (FAST 21)","author":"Mohan Jayashree","year":"2021","unstructured":"Jayashree Mohan, Amar Phanishayee, and Vijay Chidambaram. 2021. CheckFreq: Frequent, Fine-Grained DNN Checkpointing. In 19th USENIX Conference on File and Storage Technologies (FAST 21). USENIX Association, 203\u2013216. https:\/\/www.usenix.org\/conference\/fast21\/presentation\/mohan"},{"key":"e_1_3_2_1_115_1","volume-title":"19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)","author":"Eisenman Assaf","year":"2022","unstructured":"Assaf Eisenman, Kiran Kumar Matam, Steven Ingram, Dheevatsa Mudigere, Raghuraman Krishnamoorthi, Krishnakumar Nair, Misha Smelyanskiy, and Murali Annavaram. 2022. Check-N-Run: a Checkpointing System for Training Deep Learning Recommendation Models. In 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22). USENIX Association, Renton, WA, 929\u2013943. https:\/\/www.usenix.org\/conference\/nsdi22\/presentation\/eisenman"},{"key":"e_1_3_2_1_116_1","volume-title":"Pipelinerl: Faster on-policy reinforcement learning for long sequence generation. arXiv preprint arXiv:2509.19128","author":"Pich\u00e9 Alexandre","year":"2025","unstructured":"Alexandre Pich\u00e9, Ehsan Kamalloo, Rafael Pardinas, Xiaoyin Chen, and Dzmitry Bahdanau. 2025. Pipelinerl: Faster on-policy reinforcement learning for long sequence generation. arXiv preprint arXiv:2509.19128 (2025)."}],"event":{"name":"EUROSYS '26: 21st European Conference on Computer Systems","location":"McEwan Hall\/The University of Edinburgh Edinburgh Scotland UK","acronym":"EUROSYS '26","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the 21st European Conference on Computer Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3767295.3803580","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T12:05:24Z","timestamp":1780661124000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3767295.3803580"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,26]]},"references-count":116,"alternative-id":["10.1145\/3767295.3803580","10.1145\/3767295"],"URL":"https:\/\/doi.org\/10.1145\/3767295.3803580","relation":{},"subject":[],"published":{"date-parts":[[2026,4,26]]},"assertion":[{"value":"2026-04-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}