{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T20:26:57Z","timestamp":1787689617349,"version":"build-2784847793"},"publisher-location":"New York, NY, USA","reference-count":23,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770854.3780325","type":"proceedings-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T12:07:40Z","timestamp":1785499660000},"page":"176-187","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Holistic Data Scheduler for LLM Pre-training via Multi-Objective Reinforcement Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8608-4078","authenticated-orcid":false,"given":"Chenhao","family":"Dang","sequence":"first","affiliation":[{"name":"China Electronics Technology Group Corporation 15th Research Institute, Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0076-8189","authenticated-orcid":false,"given":"Jing","family":"Ma","sequence":"additional","affiliation":[{"name":"BRAIN, Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7096-0766","authenticated-orcid":false,"given":"Mingjie","family":"Liao","sequence":"additional","affiliation":[{"name":"Alibaba Group, 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","unstructured":"Kingma DP Ba J Adam et al. 2014. A method for stochastic optimization. arXiv preprint arXiv:1412.6980 Vol. 1412 6 (2014)."},{"key":"e_1_3_2_2_2_1","volume-title":"Shayne Longpre, Nathan Lambert, Xinyi Wang, Niklas Muennighoff, Bairu Hou, Liangming Pan, Haewon Jeong, et al.","author":"Albalak Alon","year":"2024","unstructured":"Alon Albalak, Yanai Elazar, Sang Michael Xie, Shayne Longpre, Nathan Lambert, Xinyi Wang, Niklas Muennighoff, Bairu Hou, Liangming Pan, Haewon Jeong, et al., 2024. A survey on data selection for language models. arXiv preprint arXiv:2402.16827 (2024)."},{"key":"e_1_3_2_2_3_1","volume-title":"Efficient online data mixing for language model pre-training. arXiv preprint arXiv:2312.02406","author":"Albalak Alon","year":"2023","unstructured":"Alon Albalak, Liangming Pan, Colin Raffel, and William Yang Wang. 2023. Efficient online data mixing for language model pre-training. arXiv preprint arXiv:2312.02406 (2023)."},{"key":"e_1_3_2_2_4_1","series-title":"SIAM journal on computing","volume-title":"The nonstochastic multiarmed bandit problem","author":"Auer Peter","year":"2002","unstructured":"Peter Auer, Nicolo Cesa-Bianchi, Yoav Freund, and Robert E Schapire. 2002. The nonstochastic multiarmed bandit problem. SIAM journal on computing, Vol. 32, 1 (2002), 48-77."},{"key":"e_1_3_2_2_5_1","volume-title":"International Conference on Machine Learning. PMLR, 2397-2430","author":"Biderman Stella","year":"2023","unstructured":"Stella Biderman, Hailey Schoelkopf, Quentin Gregory Anthony, Herbie Bradley, Kyle O'Brien, Eric Hallahan, Mohammad Aflah Khan, Shivanshu Purohit, USVSN Sai Prashanth, Edward Raff, et al., 2023. Pythia: A suite for analyzing large language models across training and scaling. In International Conference on Machine Learning. PMLR, 2397-2430."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"crossref","unstructured":"Sid Black Stella Biderman Eric Hallahan Quentin Anthony Leo Gao Laurence Golding Horace He Connor Leahy Kyle McDonell Jason Phang et al. 2022. Gpt-neox-20b: An open-source autoregressive language model. arXiv preprint arXiv:2204.06745 (2022).","DOI":"10.18653\/v1\/2022.bigscience-1.9"},{"key":"e_1_3_2_2_7_1","volume-title":"Aioli: A Unified Optimization Framework for Language Model Data Mixing. In The Thirteenth International Conference on Learning Representations.","author":"Chen Mayee F","unstructured":"Mayee F Chen, Michael Y Hu, Nicholas Lourie, Kyunghyun Cho, and Christopher Re. [n.d.]. Aioli: A Unified Optimization Framework for Language Model Data Mixing. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_2_8_1","volume-title":"Flashattention: Fast and memory-efficient exact attention with io-awareness. Advances in neural information processing systems","author":"Dao Tri","year":"2022","unstructured":"Tri Dao, Dan Fu, Stefano Ermon, Atri Rudra, and Christopher R\u00e9. 2022. Flashattention: Fast and memory-efficient exact attention with io-awareness. Advances in neural information processing systems, Vol. 35 (2022), 16344-16359."},{"key":"e_1_3_2_2_9_1","volume-title":"International conference on machine learning. PMLR, 5547-5569","author":"Du Nan","year":"2022","unstructured":"Nan Du, Yanping Huang, Andrew M Dai, Simon Tong, Dmitry Lepikhin, Yuanzhong Xu, Maxim Krikun, Yanqi Zhou, Adams Wei Yu, Orhan Firat, et al., 2022. Glam: Efficient scaling of language models with mixture-of-experts. In International conference on machine learning. PMLR, 5547-5569."},{"key":"e_1_3_2_2_10_1","volume-title":"Proceedings of the 41st International Conference on Machine Learning. 12895-12915","author":"Fan Simin","year":"2024","unstructured":"Simin Fan, Matteo Pagliardini, and Martin Jaggi. 2024. DOGE: domain reweighting with generalization estimation. In Proceedings of the 41st International Conference on Machine Learning. 12895-12915."},{"key":"e_1_3_2_2_11_1","unstructured":"Leo Gao Stella Biderman Sid Black Laurence Golding Travis Hoppe Charles Foster Jason Phang Horace He Anish Thite Noa Nabeshima et al. 2020. The pile: An 800gb dataset of diverse text for language modeling. arXiv preprint arXiv:2101.00027 (2020)."},{"key":"e_1_3_2_2_12_1","volume-title":"International conference on machine learning. Pmlr","author":"Haarnoja Tuomas","year":"2018","unstructured":"Tuomas Haarnoja, Aurick Zhou, Pieter Abbeel, and Sergey Levine. 2018. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In International conference on machine learning. Pmlr, 1861-1870."},{"key":"e_1_3_2_2_13_1","volume-title":"Measuring massive multitask language understanding. arXiv preprint arXiv:2009.03300","author":"Hendrycks Dan","year":"2020","unstructured":"Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2020. Measuring massive multitask language understanding. arXiv preprint arXiv:2009.03300 (2020)."},{"key":"e_1_3_2_2_14_1","volume-title":"Autoscale: Scale-aware data mixing for pre-training llms. arXiv preprint arXiv:2407.20177","author":"Kang Feiyang","year":"2024","unstructured":"Feiyang Kang, Yifan Sun, Bingbing Wen, Si Chen, Dawn Song, Rafid Mahmood, and Ruoxi Jia. 2024. Autoscale: Scale-aware data mixing for pre-training llms. arXiv preprint arXiv:2407.20177 (2024)."},{"key":"e_1_3_2_2_15_1","volume-title":"Regmix: Data mixture as regression for language model pre-training. arXiv preprint arXiv:2407.01492","author":"Liu Qian","year":"2024","unstructured":"Qian Liu, Xiaosen Zheng, Niklas Muennighoff, Guangtao Zeng, Longxu Dou, Tianyu Pang, Jing Jiang, and Min Lin. 2024. Regmix: Data mixture as regression for language model pre-training. arXiv preprint arXiv:2407.01492 (2024)."},{"key":"e_1_3_2_2_16_1","volume-title":"Actor-Critic based Online Data Mixing For Language Model Pre-Training. arXiv preprint arXiv:2505.23878","author":"Ma Jing","year":"2025","unstructured":"Jing Ma, Chenhao Dang, and Mingjie Liao. 2025. Actor-Critic based Online Data Mixing For Language Model Pre-Training. arXiv preprint arXiv:2505.23878 (2025)."},{"key":"e_1_3_2_2_17_1","volume-title":"A survey on large language models with some insights on their capabilities and limitations. arXiv preprint arXiv:2501.04040","author":"Matarazzo Andrea","year":"2025","unstructured":"Andrea Matarazzo and Riccardo Torlone. 2025. A survey on large language models with some insights on their capabilities and limitations. arXiv preprint arXiv:2501.04040 (2025)."},{"key":"e_1_3_2_2_18_1","volume-title":"vocd-D, and HD-D: A validation study of sophisticated approaches to lexical diversity assessment. Behavior research methods","author":"McCarthy Philip M","year":"2010","unstructured":"Philip M McCarthy and Scott Jarvis. 2010. MTLD, vocd-D, and HD-D: A validation study of sophisticated approaches to lexical diversity assessment. Behavior research methods, Vol. 42, 2 (2010), 381-392."},{"key":"e_1_3_2_2_19_1","volume-title":"Unsupervised topic models are data mixers for pre-training language models. arXiv preprint arXiv:2502.16802","author":"Peng Jiahui","year":"2025","unstructured":"Jiahui Peng, Xinlin Zhuang, Qiu Jiantao, Ren Ma, Jing Yu, Tianyi Bai, and Conghui He. 2025. Unsupervised topic models are data mixers for pre-training language models. arXiv preprint arXiv:2502.16802 (2025)."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"e_1_3_2_2_21_1","first-page":"69798","article-title":"Doremi: Optimizing data mixtures speeds up language model pretraining","volume":"36","author":"Xie Sang Michael","year":"2023","unstructured":"Sang Michael Xie, Hieu Pham, Xuanyi Dong, Nan Du, Hanxiao Liu, Yifeng Lu, Percy S Liang, Quoc V Le, Tengyu Ma, and Adams Wei Yu. 2023. Doremi: Optimizing data mixtures speeds up language model pretraining. Advances in Neural Information Processing Systems, Vol. 36 (2023), 69798-69818.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_22_1","volume-title":"Data mixing laws: Optimizing data mixtures by predicting language modeling performance. arXiv preprint arXiv:2403.16952","author":"Ye Jiasheng","year":"2024","unstructured":"Jiasheng Ye, Peiju Liu, Tianxiang Sun, Jun Zhan, Yunhua Zhou, and Xipeng Qiu. 2024. Data mixing laws: Optimizing data mixtures by predicting language modeling performance. arXiv preprint arXiv:2403.16952 (2024)."},{"key":"e_1_3_2_2_23_1","unstructured":"Wayne Xin Zhao Kun Zhou Junyi Li Tianyi Tang Xiaolei Wang Yupeng Hou Yingqian Min Beichen Zhang Junjie Zhang Zican Dong et al. 2023. A Survey of Large Language Models. arXiv preprint arXiv:2303.18223 (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\/3770854.3780325","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T20:17:51Z","timestamp":1787689071000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770854.3780325"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":23,"alternative-id":["10.1145\/3770854.3780325","10.1145\/3770854"],"URL":"https:\/\/doi.org\/10.1145\/3770854.3780325","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"}}]}}