{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T08:16:39Z","timestamp":1783152999760,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","funder":[{"name":"the National Key R&D Program of China","award":["2023YFB2703800"],"award-info":[{"award-number":["2023YFB2703800"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792129","type":"proceedings-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T21:54:34Z","timestamp":1775771674000},"page":"40-50","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["DARA: Few-shot Budget Allocation in Online Advertising via In-Context Decision Making with RL-Finetuned LLMs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6319-4290","authenticated-orcid":false,"given":"Mingxuan","family":"Song","sequence":"first","affiliation":[{"name":"School of Computer Science, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8863-3209","authenticated-orcid":false,"given":"Yusen","family":"Huo","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5495-7631","authenticated-orcid":false,"given":"Bohan","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5216-9946","authenticated-orcid":false,"given":"Shenglin","family":"Yin","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6784-9709","authenticated-orcid":false,"given":"Zhen","family":"Xiao","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4646-7131","authenticated-orcid":false,"given":"Jieyi","family":"Long","sequence":"additional","affiliation":[{"name":"Theta Labs, Inc., San Jose, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4251-8575","authenticated-orcid":false,"given":"Zhilin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8094-1545","authenticated-orcid":false,"given":"Chuan","family":"Yu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"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\/3442381.3450074"},{"key":"e_1_3_2_1_2_1","volume-title":"Ormer: A manipulation-resistant and gas-efficient blockchain pricing oracle for defi. arXiv preprint arXiv:2410.07893","author":"Bai Dongbin","year":"2024","unstructured":"Dongbin Bai, Jiannong Cao, Yinfeng Cao, Long Wen, and Milos Stojmenovic. 2024. Ormer: A manipulation-resistant and gas-efficient blockchain pricing oracle for defi. arXiv preprint arXiv:2410.07893 (2024)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242644"},{"key":"e_1_3_2_1_4_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems Vol. 33 (2020) 1877-1901."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714867"},{"key":"e_1_3_2_1_6_1","first-page":"1","article-title":"Simple agent, complex environment: Efficient reinforcement learning with agent states","volume":"23","author":"Dong Shi","year":"2022","unstructured":"Shi Dong, Benjamin Van Roy, and Zhengyuan Zhou. 2022. Simple agent, complex environment: Efficient reinforcement learning with agent states. Journal of Machine Learning Research, Vol. 23, 255 (2022), 1-54.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_7_1","volume-title":"An Adaptable Budget Planner for Enhancing Budget-Constrained Auto-Bidding in Online Advertising. arXiv preprint arXiv:2502.05187","author":"Duan Zhijian","year":"2025","unstructured":"Zhijian Duan, Yusen Huo, Tianyu Wang, Zhilin Zhang, Yeshu Li, Chuan Yu, Jian Xu, Bo Zheng, and Xiaotie Deng. 2025. An Adaptable Budget Planner for Enhancing Budget-Constrained Auto-Bidding in Online Advertising. arXiv preprint arXiv:2502.05187 (2025)."},{"key":"e_1_3_2_1_8_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_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671526"},{"key":"e_1_3_2_1_10_1","unstructured":"Muhammad Usman Hadi Qasem Al-Tashi Rizwan Qureshi Abbas Shah Amgad Muneer Muhammad Irfan Anas Zafar Muhammad Bilal Shaikh Naveed Akhtar Mohammed Ali Al-Garadi et al. [n.d.]. LLMs: A Comprehensive Survey of Applications Challenges Datasets Models Limitations and Future Prospects. ([n.d.])."},{"key":"e_1_3_2_1_11_1","volume-title":"Analysis of a Learning Based Algorithm for Budget Pacing. arXiv preprint arXiv:2205.13330","author":"Hajiaghayi MohammadTaghi","year":"2022","unstructured":"MohammadTaghi Hajiaghayi and Max Springer. 2022. Analysis of a Learning Based Algorithm for Budget Pacing. arXiv preprint arXiv:2205.13330 (2022)."},{"key":"e_1_3_2_1_12_1","unstructured":"Aaron Hurst Adam Lerer Adam P Goucher Adam Perelman Aditya Ramesh Aidan Clark AJ Ostrow Akila Welihinda Alan Hayes Alec Radford et al. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276 (2024)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-9236(02)00004-0"},{"key":"e_1_3_2_1_14_1","unstructured":"Timo Kaufmann Paul Weng Viktor Bengs and Eyke H\u00fcllermeier. 2024. A survey of reinforcement learning from human feedback. (2024)."},{"key":"e_1_3_2_1_15_1","unstructured":"Vojt\u011bch Klouda. 2025. Meta-prompts for LLM Prompt Optimization. (2025)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645534"},{"key":"e_1_3_2_1_17_1","volume-title":"Rethinking regularization methods for knowledge graph completion. arXiv preprint arXiv:2505.23442","author":"Li Linyu","year":"2025","unstructured":"Linyu Li, Zhi Jin, Yuanpeng He, Dongming Jin, Haoran Duan, Zhengwei Tao, Xuan Zhang, and Jiandong Li. 2025a. Rethinking regularization methods for knowledge graph completion. arXiv preprint arXiv:2505.23442 (2025)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2025.3538110"},{"key":"e_1_3_2_1_19_1","volume-title":"2018 24th International Conference on Pattern Recognition (ICPR). IEEE, 886-891","author":"Li Pengcheng","year":"2018","unstructured":"Pengcheng Li, Ammar Hawbani, et al., 2018. An efficient budget allocation algorithm for multi-channel advertising. In 2018 24th International Conference on Pattern Recognition (ICPR). IEEE, 886-891."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645386"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1902"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2970463"},{"key":"e_1_3_2_1_23_1","volume-title":"Divya Anand Sinha, and Richard Futrell","author":"Loya Manikanta","year":"2023","unstructured":"Manikanta Loya, Divya Anand Sinha, and Richard Futrell. 2023. Exploring the Sensitivity of LLMs' Decision-Making Capabilities: Insights from Prompt Variation and Hyperparameters. arXiv preprint arXiv:2312.17476 (2023)."},{"key":"e_1_3_2_1_24_1","first-page":"2","article-title":"Apriori rule-based in-app ad selection online algorithm for improving supply-side platform revenues","volume":"8","author":"Mukherjee Anik","year":"2017","unstructured":"Anik Mukherjee, Rangaraja P Sundarraj, and Kaushik Dutta. 2017. Apriori rule-based in-app ad selection online algorithm for improving supply-side platform revenues. ACM Transactions on Management Information Systems (TMIS), Vol. 8, 2-3 (2017), 1-28.","journal-title":"ACM Transactions on Management Information Systems (TMIS)"},{"key":"e_1_3_2_1_25_1","volume-title":"Ngoc Duy Nguyen, and Saeid Nahavandi","author":"Nguyen Thanh Thi","year":"2020","unstructured":"Thanh Thi Nguyen, Ngoc Duy Nguyen, and Saeid Nahavandi. 2020. Deep reinforcement learning for multiagent systems: A review of challenges, solutions, and applications. IEEE transactions on cybernetics, Vol. 50, 9 (2020), 3826-3839."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2022.103663"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459991"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2338"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Laria Reynolds and Kyle McDonell. 2021. Prompt programming for large language models: Beyond the few-shot paradigm. In Extended abstracts of the 2021 CHI conference on human factors in computing systems. 1-7.","DOI":"10.1145\/3411763.3451760"},{"key":"e_1_3_2_1_31_1","unstructured":"Nabeel Seedat Nicolas Huynh Boris van Breugel and Mihaela van der Schaar. 2023. Curated llm: Synergy of llms and data curation for tabular augmentation in ultra low-data regimes. (2023)."},{"key":"e_1_3_2_1_32_1","volume-title":"Optimizing Online Advertising with Multi-Armed Bandits: Mitigating the Cold Start Problem under Auction Dynamics. arXiv preprint arXiv:2502.01867","author":"Soboleva Anastasiia","year":"2025","unstructured":"Anastasiia Soboleva, Andrey Pudovikov, Roman Snetkov, Alina Babenko, Egor Samosvat, and Yuriy Dorn. 2025. Optimizing Online Advertising with Multi-Armed Bandits: Mitigating the Cold Start Problem under Auction Dynamics. arXiv preprint arXiv:2502.01867 (2025)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.3390\/s22103799"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714926"},{"key":"e_1_3_2_1_35_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_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2023.3343111"},{"key":"e_1_3_2_1_37_1","volume-title":"Making the most of what you have: adapting pre-trained visual language models in the low-data regime. arXiv preprint arXiv:2305.02297","author":"Zhang Chuhan","year":"2023","unstructured":"Chuhan Zhang, Antoine Miech, Jiajun Shen, Jean-Baptiste Alayrac, and Pauline Luc. 2023. Making the most of what you have: adapting pre-trained visual language models in the low-data regime. arXiv preprint arXiv:2305.02297 (2023)."}],"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":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774904.3792129","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T07:26:42Z","timestamp":1783150002000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792129"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":37,"alternative-id":["10.1145\/3774904.3792129","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792129","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"}}]}}