{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:27Z","timestamp":1786120827595,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"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":[[2026,8,9]]},"DOI":"10.1145\/3770855.3818423","type":"proceedings-article","created":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:08:33Z","timestamp":1786064913000},"page":"7070-7081","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Generative Optimization for Incentivized Advertising with Global Level Constraints"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-4777-2841","authenticated-orcid":false,"given":"Gege","family":"Chen","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4984-5307","authenticated-orcid":false,"given":"Ning","family":"Luo","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7313-3129","authenticated-orcid":false,"given":"Hao","family":"Jiang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0345-7771","authenticated-orcid":false,"given":"Da","family":"Li","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7469-1083","authenticated-orcid":false,"given":"Wenzheng","family":"Shu","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9386-8859","authenticated-orcid":false,"given":"Teng","family":"Sha","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3749-4019","authenticated-orcid":false,"given":"Yanxiang","family":"Zeng","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7364-8324","authenticated-orcid":false,"given":"Wenxin","family":"Tai","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8038-8150","authenticated-orcid":false,"given":"Fan","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7253-0674","authenticated-orcid":false,"given":"Xialong","family":"Liu","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512103"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557100"},{"key":"e_1_3_2_1_3_1","volume-title":"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling. arXiv preprint arXiv:1803.01271","author":"Bai Shaojie","year":"2018","unstructured":"Shaojie Bai. 2018. An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling. arXiv preprint arXiv:1803.01271 (2018)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3746252.3761558"},{"key":"e_1_3_2_1_5_1","volume-title":"BCRLSP: An offline reinforcement learning framework for sequential targeted promotion. arXiv preprint arXiv:2207.07790","author":"Chen Fanglin","year":"2022","unstructured":"Fanglin Chen, Xiao Liu, Bo Tang, Feiyu Xiong, Serim Hwang, and Guomian Zhuang. 2022. BCRLSP: An offline reinforcement learning framework for sequential targeted promotion. arXiv preprint arXiv:2207.07790 (2022)."},{"key":"e_1_3_2_1_6_1","volume-title":"Decision transformer: Reinforcement learning via sequence modeling. Advances in neural information processing systems 34","author":"Chen Lili","year":"2021","unstructured":"Lili Chen, Kevin Lu, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Misha Laskin, Pieter Abbeel, Aravind Srinivas, and Igor Mordatch. 2021. Decision transformer: Reinforcement learning via sequence modeling. Advances in neural information processing systems 34 (2021), 15084-15097."},{"key":"e_1_3_2_1_7_1","volume-title":"Onerec: Unifying retrieve and rank with generative recommender and iterative preference alignment. arXiv preprint arXiv:2502.18965","author":"Deng Jiaxin","year":"2025","unstructured":"Jiaxin Deng, Shiyao Wang, Kuo Cai, Lejian Ren, Qigen Hu, Weifeng Ding, Qiang Luo, and Guorui Zhou. 2025. Onerec: Unifying retrieve and rank with generative recommender and iterative preference alignment. arXiv preprint arXiv:2502.18965 (2025)."},{"key":"e_1_3_2_1_8_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_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3523227.3546767"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412215"},{"key":"e_1_3_2_1_11_1","volume-title":"OneSug: The Unified End-to-End Generative Framework for E-commerce Query Suggestion. arXiv preprint arXiv:2506.06913","author":"Guo Xian","year":"2025","unstructured":"Xian Guo, Ben Chen, Siyuan Wang, Ying Yang, Chenyi Lei, Yuqing Ding, and Han Li. 2025. OneSug: The Unified End-to-End Generative Framework for E-commerce Query Suggestion. arXiv preprint arXiv:2506.06913 (2025)."},{"key":"e_1_3_2_1_12_1","volume-title":"The Thirteenth International Conference on Learning Representations.","author":"Guo Zijian","year":"2025","unstructured":"Zijian Guo, Weichao Zhou, Shengao Wang, and Wenchao Li. 2025. Constraint-conditioned actor-critic for offline safe reinforcement learning. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1057\/palgrave.jdm.3240007"},{"key":"e_1_3_2_1_14_1","volume-title":"AAAI fall symposia","author":"Hausknecht Matthew J","unstructured":"Matthew J Hausknecht and Peter Stone. 2015. Deep Recurrent Q-Learning for Partially Observable MDPs. In AAAI fall symposia, Vol. 45. 141."},{"key":"e_1_3_2_1_15_1","volume-title":"Tabbie: Pretrained representations of tabular data. arXiv preprint arXiv:2105.02584","author":"Iida Hiroshi","year":"2021","unstructured":"Hiroshi Iida, Dung Thai, Varun Manjunatha, and Mohit Iyyer. 2021. Tabbie: Pretrained representations of tabular data. arXiv preprint arXiv:2105.02584 (2021)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.410"},{"key":"e_1_3_2_1_17_1","volume-title":"Numgpt: Improving numeracy ability of generative pre-trained models. arXiv preprint arXiv:2109.03137","author":"Jin Zhihua","year":"2021","unstructured":"Zhihua Jin, Xin Jiang, Xingbo Wang, Qun Liu, Yong Wang, Xiaozhe Ren, and Huamin Qu. 2021. Numgpt: Improving numeracy ability of generative pre-trained models. arXiv preprint arXiv:2109.03137 (2021)."},{"key":"e_1_3_2_1_18_1","volume-title":"Accelerating offline reinforcement learning application in real-time bidding and recommendation: Potential use of simulation. arXiv preprint arXiv:2109.08331","author":"Kiyohara Haruka","year":"2021","unstructured":"Haruka Kiyohara, Kosuke Kawakami, and Yuta Saito. 2021. Accelerating offline reinforcement learning application in real-time bidding and recommendation: Potential use of simulation. arXiv preprint arXiv:2109.08331 (2021)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671555"},{"key":"e_1_3_2_1_20_1","volume-title":"Offline reinforcement learning with implicit q-learning. arXiv preprint arXiv:2110.06169","author":"Kostrikov Ilya","year":"2021","unstructured":"Ilya Kostrikov, Ashvin Nair, and Sergey Levine. 2021. Offline reinforcement learning with implicit q-learning. arXiv preprint arXiv:2110.06169 (2021)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657802"},{"key":"e_1_3_2_1_22_1","volume-title":"A survey on transformers in reinforcement learning. arXiv preprint arXiv:2301.03044","author":"Li Wenzhe","year":"2023","unstructured":"Wenzhe Li, Hao Luo, Zichuan Lin, Chongjie Zhang, Zongqing Lu, and Deheng Ye. 2023. A survey on transformers in reinforcement learning. arXiv preprint arXiv:2301.03044 (2023)."},{"key":"e_1_3_2_1_23_1","volume-title":"International Conference on Machine Learning. PMLR, 21127-21152","author":"Lin Qian","year":"2023","unstructured":"Qian Lin, Bo Tang, Zifan Wu, Chao Yu, Shangqin Mao, Qianlong Xie, Xingxing Wang, and Dong Wang. 2023. Safe offline reinforcement learning with real-time budget constraints. In International Conference on Machine Learning. PMLR, 21127-21152."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00638"},{"key":"e_1_3_2_1_25_1","volume-title":"Session-Level Dynamic Ad Load Optimization using Offline Robust Reinforcement Learning. arXiv preprint arXiv:2501.05591","author":"Liu Tao","year":"2025","unstructured":"Tao Liu, Qi Xu, Wei Shi, Zhigang Hua, and Shuang Yang. 2025. Session-Level Dynamic Ad Load Optimization using Offline Robust Reinforcement Learning. arXiv preprint arXiv:2501.05591 (2025)."},{"key":"e_1_3_2_1_26_1","volume-title":"International conference on machine learning. PMLR, 21611-21630","author":"Liu Zuxin","year":"2023","unstructured":"Zuxin Liu, Zijian Guo, Yihang Yao, Zhepeng Cen, Wenhao Yu, Tingnan Zhang, and Ding Zhao. 2023. Constrained decision transformer for offline safe reinforcement learning. In International conference on machine learning. PMLR, 21611-21630."},{"key":"e_1_3_2_1_27_1","volume-title":"Generative Regression Based Watch Time Prediction for Short-Video Recommendation. arXiv preprint arXiv:2412.20211","author":"Ma Hongxu","year":"2024","unstructured":"Hongxu Ma, Kai Tian, Tao Zhang, Xuefeng Zhang, Han Zhou, Chunjie Chen, Han Li, Jihong Guan, and Shuigeng Zhou. 2024. Generative Regression Based Watch Time Prediction for Short-Video Recommendation. arXiv preprint arXiv:2412.20211 (2024)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","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) 27730-27744.","DOI":"10.52202\/068431-2011"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313404"},{"key":"e_1_3_2_1_30_1","volume-title":"Direct preference optimization: Your language model is secretly a reward model. Advances in neural information processing systems 36","author":"Rafailov Rafael","year":"2023","unstructured":"Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. 2023. Direct preference optimization: Your language model is secretly a reward model. Advances in neural information processing systems 36 (2023), 53728-53741."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0452"},{"key":"e_1_3_2_1_32_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_33_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, Yang 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_34_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1587"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9590"},{"key":"e_1_3_2_1_36_1","volume-title":"Do NLP models know numbers? probing numeracy in embeddings. arXiv preprint arXiv:1909.07940","author":"Wallace Eric","year":"2019","unstructured":"Eric Wallace, Yizhong Wang, Sujian Li, Sameer Singh, and Matt Gardner. 2019. Do NLP models know numbers? probing numeracy in embeddings. arXiv preprint arXiv:1909.07940 (2019)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599764"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467434"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271748"},{"key":"e_1_3_2_1_40_1","volume-title":"Off-policy primal-dual safe reinforcement learning. arXiv preprint arXiv:2401.14758","author":"Wu Zifan","year":"2024","unstructured":"Zifan Wu, Bo Tang, Qian Lin, Chao Yu, Shangqin Mao, Qianlong Xie, Xingxing Wang, and Dong Wang. 2024. Off-policy primal-dual safe reinforcement learning. arXiv preprint arXiv:2401.14758 (2024)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358031"},{"key":"e_1_3_2_1_42_1","volume-title":"Early convolutions help transformers see better. Advances in neural information processing systems 34","author":"Xiao Tete","year":"2021","unstructured":"Tete Xiao, Mannat Singh, Eric Mintun, Trevor Darrell, Piotr Doll\u00e1r, and Ross Girshick. 2021. Early convolutions help transformers see better. Advances in neural information processing systems 34 (2021), 30392-30400."},{"key":"e_1_3_2_1_43_1","volume-title":"Bi-Level Decision-Focused Causal Learning for Large-Scale Marketing Optimization: Bridging Observational and Experimental Data. arXiv preprint arXiv:2510.19517","author":"Zhang Shuli","year":"2025","unstructured":"Shuli Zhang, Hao Zhou, Jiaqi Zheng, Guibin Jiang, Bing Cheng, Wei Lin, and Guihai Chen. 2025. Bi-Level Decision-Focused Causal Learning for Large-Scale Marketing Optimization: Bridging Observational and Experimental Data. arXiv preprint arXiv:2510.19517 (2025)."},{"key":"e_1_3_2_1_44_1","first-page":"20410","article-title":"BCORLE (\u03bb): An Offline Reinforcement Learning and Evaluation Framework for Coupons Allocation in E-commerce Market","volume":"34","author":"Zhang Yang","year":"2021","unstructured":"Yang Zhang, Bo Tang, Qingyu Yang, Dou An, Hongyin Tang, Chenyang Xi, Xueying Li, and Feiyu Xiong. 2021. BCORLE (\u03bb): An Offline Reinforcement Learning and Evaluation Framework for Coupons Allocation in E-commerce Market. Advances in Neural Information Processing Systems 34 (2021), 20410-20422.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330700"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240374"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3185994"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3672353"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW55747.2022.00171"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330668"}],"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.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:22:16Z","timestamp":1786065736000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3818423"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":51,"alternative-id":["10.1145\/3770855.3818423","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3818423","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}