{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:09:37Z","timestamp":1784138977406,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"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":[[2026,7,20]]},"DOI":"10.1145\/3805712.3808424","type":"proceedings-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:06:26Z","timestamp":1784135186000},"page":"5049-5054","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["AIPO: Adaptive Anchored Intent-aware Policy Optimization for Generative Recommendation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1789-3119","authenticated-orcid":false,"given":"Kun","family":"Yao","sequence":"first","affiliation":[{"name":"JD.COM, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1749-1075","authenticated-orcid":false,"given":"Congcong","family":"Liu","sequence":"additional","affiliation":[{"name":"JD.COM, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0564-3254","authenticated-orcid":false,"given":"Ziheng","family":"Ni","sequence":"additional","affiliation":[{"name":"JD.COM, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1483-2372","authenticated-orcid":false,"given":"Cai","family":"Shang","sequence":"additional","affiliation":[{"name":"JD.COM, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4011-130X","authenticated-orcid":false,"given":"Wenlong","family":"Chen","sequence":"additional","affiliation":[{"name":"JD.COM, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2561-1919","authenticated-orcid":false,"given":"Changping","family":"Peng","sequence":"additional","affiliation":[{"name":"JD.COM, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3275-2528","authenticated-orcid":false,"given":"Ching","family":"Law","sequence":"additional","affiliation":[{"name":"JD.COM, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_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_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3737259"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290999"},{"key":"e_1_3_2_1_4_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_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05961-4"},{"key":"e_1_3_2_1_6_1","volume-title":"Challenges of real-world reinforcement learning. arXiv preprint arXiv:1904.12901","author":"Dulac-Arnold Gabriel","year":"2019","unstructured":"Gabriel Dulac-Arnold, Daniel Mankowitz, and Todd Hester. 2019. Challenges of real-world reinforcement learning. arXiv preprint arXiv:1904.12901 (2019)."},{"key":"e_1_3_2_1_7_1","volume-title":"Forge: Forming semantic identifiers for generative retrieval in industrial datasets. arXiv preprint arXiv:2509.20904","author":"Fu Kairui","year":"2025","unstructured":"Kairui Fu, Tao Zhang, Shuwen Xiao, Ziyang Wang, Xinming Zhang, Chenchi Zhang, Yuliang Yan, Junjun Zheng, Yu Li, Zhihong Chen, et al., 2025. Forge: Forming semantic identifiers for generative retrieval in industrial datasets. arXiv preprint arXiv:2509.20904 (2025)."},{"key":"e_1_3_2_1_8_1","volume-title":"International Conference on Machine Learning. PMLR, 10835-10866","author":"Gao Leo","year":"2023","unstructured":"Leo Gao, John Schulman, and Jacob Hilton. 2023. Scaling laws for reward model overoptimization. In International Conference on Machine Learning. PMLR, 10835-10866."},{"key":"e_1_3_2_1_9_1","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Peiyi Wang Qihao Zhu Runxin Xu Ruoyu Zhang Shirong Ma 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_10_1","unstructured":"Xuegang Hao Ming Zhang Alex Li Xiangyu Qian Zhi Ma Yanlong Zang Shijie Yang Zhongxuan Han Xiaolong Ma Jinguang Liu et al. 2025. OxygenREC: An Instruction-Following Generative Framework for E-commerce Recommendation. arXiv preprint arXiv:2512.22386 (2025)."},{"key":"e_1_3_2_1_11_1","volume-title":"Plum: Adapting pre-trained language models for industrial-scale generative recommendations. arXiv preprint arXiv:2510.07784","author":"He Ruining","year":"2025","unstructured":"Ruining He, Lukasz Heldt, Lichan Hong, Raghunandan Keshavan, Shifan Mao, Nikhil Mehta, Zhengyang Su, Alicia Tsai, Yueqi Wang, Shao-Chuan Wang, et al., 2025. Plum: Adapting pre-trained language models for industrial-scale generative recommendations. arXiv preprint arXiv:2510.07784 (2025)."},{"key":"e_1_3_2_1_12_1","volume-title":"S-GRec: Personalized Semantic-Aware Generative Recommendation with Asymmetric Advantage. arXiv preprint arXiv:2602.10606","author":"Jiang Jie","year":"2026","unstructured":"Jie Jiang, Hongbo Tang, Wenjie Wu, Yangru Huang, Zhenmao Li, Qian Li, Changping Wang, Jun Zhang, and Huan Yu. 2026. S-GRec: Personalized Semantic-Aware Generative Recommendation with Asymmetric Advantage. arXiv preprint arXiv:2602.10606 (2026)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3746252.3761612"},{"key":"e_1_3_2_1_14_1","volume-title":"Minionerec: An open-source framework for scaling generative recommendation. arXiv preprint arXiv:2510.24431","author":"Kong Xiaoyu","year":"2025","unstructured":"Xiaoyu Kong, Leheng Sheng, Junfei Tan, Yuxin Chen, Jiancan Wu, An Zhang, Xiang Wang, and Xiangnan He. 2025. Minionerec: An open-source framework for scaling generative recommendation. arXiv preprint arXiv:2510.24431 (2025)."},{"key":"e_1_3_2_1_15_1","unstructured":"Yu Liang Zhongjin Zhang Yuxuan Zhu Kerui Zhang Zhiluohan Guo Wenhang Zhou Zonqi Yang Kangle Wu Yabo Ni Anxiang Zeng et al. 2026. Rethinking Generative Recommender Tokenizer: Recsys-Native Encoding and Semantic Quantization Beyond LLMs. arXiv preprint arXiv:2602.02338 (2026)."},{"key":"e_1_3_2_1_16_1","volume-title":"Rec-r1: Bridging generative large language models and user-centric recommendation systems via reinforcement learning. arXiv preprint arXiv:2503.24289","author":"Lin Jiacheng","year":"2025","unstructured":"Jiacheng Lin, Tian Wang, and Kun Qian. 2025. Rec-r1: Bridging generative large language models and user-centric recommendation systems via reinforcement learning. arXiv preprint arXiv:2503.24289 (2025)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3729989"},{"key":"e_1_3_2_1_18_1","volume-title":"CPGD: Toward Stable Rule-based Reinforcement Learning for Language Models. arXiv preprint arXiv:2505.12504","author":"Liu Zongkai","year":"2025","unstructured":"Zongkai Liu, Fanqing Meng, Lingxiao Du, Zhixiang Zhou, Chao Yu, Wenqi Shao, and Qiaosheng Zhang. 2025a. CPGD: Toward Stable Rule-based Reinforcement Learning for Language Models. arXiv preprint arXiv:2505.12504 (2025)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330984"},{"key":"e_1_3_2_1_20_1","volume-title":"An empirical model of large-batch training. arXiv preprint arXiv:1812.06162","author":"McCandlish Sam","year":"2018","unstructured":"Sam McCandlish, Jared Kaplan, Dario Amodei, and OpenAI Dota Team. 2018. An empirical model of large-batch training. arXiv preprint arXiv:1812.06162 (2018)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0452"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671775"},{"key":"e_1_3_2_1_23_1","volume-title":"Unified Multi-Level Alignment for LLM-based Generative Recommendation. arXiv preprint arXiv:2511.11255","author":"Ye Wencai","year":"2025","unstructured":"Wencai Ye, Mingjie Sun, Shuhang Chen, Wenjin Wu, and Peng Jiang. 2025. Align$^3$GR: Unified Multi-Level Alignment for LLM-based Generative Recommendation. arXiv preprint arXiv:2511.11255 (2025)."},{"key":"e_1_3_2_1_24_1","volume-title":"DualGR: Generative Retrieval with Long and Short-Term Interests Modeling. arXiv preprint arXiv:2511.12518","author":"Yi Zhongchao","year":"2025","unstructured":"Zhongchao Yi, Kai Feng, Xiaojian Ma, Yalong Wang, Yongqi Liu, Han Li, Zhengyang Zhou, and Yang Wang. 2025. DualGR: Generative Retrieval with Long and Short-Term Interests Modeling. arXiv preprint arXiv:2511.12518 (2025)."},{"key":"e_1_3_2_1_25_1","unstructured":"Jun Yin Zhengxin Zeng Mingzheng Li Hao Yan Chaozhuo Li Weihao Han Jianjin Zhang Ruochen Liu Allen Sun Denvy Deng et al. 2024. Unleash LLMs potential for recommendation by coordinating twin-tower dynamic semantic token generator. arXiv preprint arXiv:2409.09253 (2024)."},{"key":"e_1_3_2_1_26_1","volume-title":"Multi-Aspect Cross-modal Quantization for Generative Recommendation. arXiv preprint arXiv:2511.15122","author":"Zhang Fuwei","year":"2025","unstructured":"Fuwei Zhang, Xiaoyu Liu, Dongbo Xi, Jishen Yin, Huan Chen, Peng Yan, Fuzhen Zhuang, and Zhao Zhang. 2025b. Multi-Aspect Cross-modal Quantization for Generative Recommendation. arXiv preprint arXiv:2511.15122 (2025)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3640457.3688129"},{"key":"e_1_3_2_1_28_1","volume-title":"GPR: Towards a Generative Pre-trained One-Model Paradigm for Large-Scale Advertising Recommendation. arXiv preprint arXiv:2511.10138","author":"Zhang Jun","year":"2025","unstructured":"Jun Zhang, Yi Li, Yue Liu, Changping Wang, Yuan Wang, Yuling Xiong, Xun Liu, Haiyang Wu, Qian Li, Enming Zhang, et al., 2025a. GPR: Towards a Generative Pre-trained One-Model Paradigm for Large-Scale Advertising Recommendation. arXiv preprint arXiv:2511.10138 (2025)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219855"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16156"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00118"},{"key":"e_1_3_2_1_32_1","unstructured":"Chujie Zheng Shixuan Liu Mingze Li Xiong-Hui Chen Bowen Yu Chang Gao Kai Dang Yuqiong Liu Rui Men An Yang et al. 2025. Group sequence policy optimization. arXiv preprint arXiv:2507.18071 (2025)."},{"key":"e_1_3_2_1_33_1","unstructured":"Guorui Zhou Hengrui Hu Hongtao Cheng Huanjie Wang Jiaxin Deng Jinghao Zhang Kuo Cai Lejian Ren Lu Ren Liao Yu et al. 2025. Onerec-v2 technical report. arXiv preprint arXiv:2508.20900 (2025)."},{"key":"e_1_3_2_1_34_1","first-page":"1554","volume-title":"Long-Term Interest Clock: Fine-Grained Time Perception in Streaming Recommendation System. In Companion Proceedings of the ACM on Web Conference","author":"Zhu Yongchun","year":"2025","unstructured":"Yongchun Zhu, Guanyu Jiang, Jingwu Chen, Feng Zhang, Qi Wu, and Zuotao Liu. 2025. Long-Term Interest Clock: Fine-Grained Time Perception in Streaming Recommendation System. In Companion Proceedings of the ACM on Web Conference 2025. 1554-1557."}],"event":{"name":"SIGIR '26: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Melbourne VIC Australia","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:33:04Z","timestamp":1784136784000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3808424"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":34,"alternative-id":["10.1145\/3805712.3808424","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3808424","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}