{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T17:16:44Z","timestamp":1775841404465,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation of China","award":["62472428"],"award-info":[{"award-number":["62472428"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792805","type":"proceedings-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T21:54:39Z","timestamp":1775771679000},"page":"7979-7988","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["GAM: A Generative Auto-Marketing Framework in Online E-commerce Platforms"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-9489-7838","authenticated-orcid":false,"given":"Yuejia","family":"Dou","sequence":"first","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5904-0889","authenticated-orcid":false,"given":"Shuai","family":"Dou","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4007-8340","authenticated-orcid":false,"given":"Yuchao","family":"Ma","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8209-4734","authenticated-orcid":false,"given":"Bingzhe","family":"Wang","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0292-2078","authenticated-orcid":false,"given":"Tianyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6665-2288","authenticated-orcid":false,"given":"Zhilin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8094-1545","authenticated-orcid":false,"given":"Chuan","family":"Yu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3111-1005","authenticated-orcid":false,"given":"Jian","family":"Xu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9192-8928","authenticated-orcid":false,"given":"Qi","family":"Qi","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China, Beijing Key Laboratory of Research on Large Models and Intelligent Governance, Beijing, China, and Engineering Research Center of Next-Generation Intelligent Search and Recommendation, MOE, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3699824.3699838"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-35389-6_2"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557100"},{"key":"e_1_3_2_1_4_1","volume-title":"International Conference on Artificial Intelligence and Statistics. PMLR, 4447-4455","author":"Azar Mohammad Gheshlaghi","year":"2024","unstructured":"Mohammad Gheshlaghi Azar, Zhaohan Daniel Guo, Bilal Piot, Remi Munos, Mark Rowland, Michal Valko, and Daniele Calandriello. 2024. A general theoretical paradigm to understand learning from human preferences. In International Conference on Artificial Intelligence and Statistics. PMLR, 4447-4455."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/0167-7187(94)00469-2"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.27.9.988"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018702"},{"key":"e_1_3_2_1_8_1","volume-title":"Decision transformer: Reinforcement learning via sequence modeling. Advances in neural information processing systems","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, Vol. 34 (2021), 15084-15097."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2020408.2020604"},{"key":"e_1_3_2_1_10_1","volume-title":"Kto: Model alignment as prospect theoretic optimization. arXiv preprint arXiv:2402.01306","author":"Ethayarajh Kawin","year":"2024","unstructured":"Kawin Ethayarajh, Winnie Xu, Niklas Muennighoff, Dan Jurafsky, and Douwe Kiela. 2024. Kto: Model alignment as prospect theoretic optimization. arXiv preprint arXiv:2402.01306 (2024)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1257\/jep.23.3.37"},{"key":"e_1_3_2_1_12_1","volume-title":"International conference on machine learning. PMLR","author":"Fujimoto Scott","year":"2019","unstructured":"Scott Fujimoto, David Meger, and Doina Precup. 2019. Off-policy deep reinforcement learning without exploration. In International conference on machine learning. PMLR, 2052-2062."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3729987"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412215"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671526"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467199"},{"key":"e_1_3_2_1_17_1","volume-title":"Q-value regularized transformer for offline reinforcement learning. arXiv preprint arXiv:2405.17098","author":"Hu Shengchao","year":"2024","unstructured":"Shengchao Hu, Ziqing Fan, Chaoqin Huang, Li Shen, Ya Zhang, Yanfeng Wang, and Dacheng Tao. 2024. Q-value regularized transformer for offline reinforcement learning. arXiv preprint arXiv:2405.17098 (2024)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3737197"},{"key":"e_1_3_2_1_19_1","volume-title":"International Conference on Learning Representations.","author":"Joachims Thorsten","year":"2018","unstructured":"Thorsten Joachims, Adith Swaminathan, and Maarten De Rijke. 2018. Deep learning with logged bandit feedback. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2764"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/11871842_29"},{"key":"e_1_3_2_1_22_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_23_1","volume-title":"Conservative q-learning for offline reinforcement learning. Advances in neural information processing systems","author":"Kumar Aviral","year":"2020","unstructured":"Aviral Kumar, Aurick Zhou, George Tucker, and Sergey Levine. 2020. Conservative q-learning for offline reinforcement learning. Advances in neural information processing systems, Vol. 33 (2020), 1179-1191."},{"key":"e_1_3_2_1_24_1","volume-title":"Generative Large-Scale Pre-trained Models for Automated Ad Bidding Optimization. arXiv preprint arXiv:2508.02002","author":"Lei Yu","year":"2025","unstructured":"Yu Lei, Jiayang Zhao, Yilei Zhao, Zhaoqi Zhang, Linyou Cai, Qianlong Xie, and Xingxing Wang. 2025. Generative Large-Scale Pre-trained Models for Automated Ad Bidding Optimization. arXiv preprint arXiv:2508.02002 (2025)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412745"},{"key":"e_1_3_2_1_26_1","volume-title":"Generative Auto-Bidding in Large-Scale Competitive Auctions via Diffusion Completer-Aligner. arXiv preprint arXiv:2509.03348","author":"Li Yewen","year":"2025","unstructured":"Yewen Li, Jingtong Gao, Nan Jiang, Shuai Mao, Ruyi An, Fei Pan, Xiangyu Zhao, Bo An, Qingpeng Cai, and Peng Jiang. 2025a. Generative Auto-Bidding in Large-Scale Competitive Auctions via Diffusion Completer-Aligner. arXiv preprint arXiv:2509.03348 (2025)."},{"key":"e_1_3_2_1_27_1","first-page":"315","volume-title":"GAS: Generative Auto-bidding with Post-training Search. In Companion Proceedings of the ACM on Web Conference","author":"Li Yewen","year":"2025","unstructured":"Yewen Li, Shuai Mao, Jingtong Gao, Nan Jiang, Yunjian Xu, Qingpeng Cai, Fei Pan, Peng Jiang, and Bo An. 2025b. GAS: Generative Auto-bidding with Post-training Search. In Companion Proceedings of the ACM on Web Conference 2025. 315-324."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052616"},{"key":"e_1_3_2_1_29_1","first-page":"124198","article-title":"Simpo: Simple preference optimization with a reference-free reward","volume":"37","author":"Meng Yu","year":"2024","unstructured":"Yu Meng, Mengzhou Xia, and Danqi Chen. 2024. Simpo: Simple preference optimization with a reference-free reward. Advances in Neural Information Processing Systems, Vol. 37 (2024), 124198-124235.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_30_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 Vol. 35 (2022) 27730-27744.","DOI":"10.52202\/068431-2011"},{"key":"e_1_3_2_1_31_1","volume-title":"Direct preference optimization: Your language model is secretly a reward model. Advances in neural information processing systems","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, Vol. 36 (2023), 53728-53741."},{"key":"e_1_3_2_1_32_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_33_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i6.16717"},{"key":"e_1_3_2_1_34_1","first-page":"94428","article-title":"Auctionnet: A novel benchmark for decision-making in large-scale games","volume":"37","author":"Su Kefan","year":"2024","unstructured":"Kefan Su, Yusen Huo, Zhilin Zhang, Shuai Dou, Chuan Yu, Jian Xu, Zongqing Lu, and Bo Zheng. 2024. Auctionnet: A novel benchmark for decision-making in large-scale games. Advances in Neural Information Processing Systems, Vol. 37 (2024), 94428-94452.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/2789272.2886805"},{"key":"e_1_3_2_1_36_1","volume-title":"International conference on machine learning. PMLR, 814-823","author":"Swaminathan Adith","year":"2015","unstructured":"Adith Swaminathan and Thorsten Joachims. 2015b. Counterfactual risk minimization: Learning from logged bandit feedback. In International conference on machine learning. PMLR, 814-823."},{"key":"e_1_3_2_1_37_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_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358031"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3737191"},{"key":"e_1_3_2_1_40_1","volume-title":"Kenton Murray, and Young Jin Kim.","author":"Xu Haoran","year":"2024","unstructured":"Haoran Xu, Amr Sharaf, Yunmo Chen, Weiting Tan, Lingfeng Shen, Benjamin Van Durme, Kenton Murray, and Young Jin Kim. 2024a. Contrastive preference optimization: Pushing the boundaries of llm performance in machine translation. arXiv preprint arXiv:2401.08417 (2024)."},{"key":"e_1_3_2_1_41_1","unstructured":"Jian Xu Zhilin Zhang Zongqing Lu Xiaotie Deng Michael P Wellman Chuan Yu Shuai Dou Yusen Huo Zhiwei Xu Zhijian Duan et al. 2024b. Auto-Bidding in Large-Scale Auctions: Learning Decision-Making in Uncertain and Competitive Games. In NeurIPS 2024 Competition Track."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330681"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2019.2936142"},{"key":"e_1_3_2_1_44_1","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Yu Hao","year":"2017","unstructured":"Hao Yu, Michael Neely, and Xiaohan Wei. 2017. Online convex optimization with stochastic constraints. Advances in Neural Information Processing Systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/2835776.2835843"},{"key":"e_1_3_2_1_46_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, Vol. 34 (2021), 20410-20422.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330700"},{"key":"e_1_3_2_1_48_1","volume-title":"international conference on machine learning. PMLR, 27042-27059","author":"Zheng Qinqing","year":"2022","unstructured":"Qinqing Zheng, Amy Zhang, and Aditya Grover. 2022. Online decision transformer. In international conference on machine learning. PMLR, 27042-27059."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3672353"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25677"}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2026"],"original-title":[],"deposited":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T16:35:58Z","timestamp":1775838958000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792805"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":50,"alternative-id":["10.1145\/3774904.3792805","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792805","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}