{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:18:18Z","timestamp":1784179098261,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":63,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the National Key Research and Development Program of China","award":["2022YFB3104701"],"award-info":[{"award-number":["2022YFB3104701"]}]},{"name":"the National Natural Science Foundation of China","award":["62272437, 62121002"],"award-info":[{"award-number":["62272437, 62121002"]}]},{"name":"the CCCD Key Lab of Ministry of Culture and Tourism"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.1145\/3626772.3657683","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T12:40:05Z","timestamp":1720701605000},"page":"1893-1903","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":28,"title":["Large Language Models are Learnable Planners for Long-Term Recommendation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2616-6880","authenticated-orcid":false,"given":"Wentao","family":"Shi","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8472-7992","authenticated-orcid":false,"given":"Xiangnan","family":"He","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7863-5183","authenticated-orcid":false,"given":"Yang","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5187-9196","authenticated-orcid":false,"given":"Chongming","family":"Gao","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4113-2840","authenticated-orcid":false,"given":"Xinyue","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0251-465X","authenticated-orcid":false,"given":"Jizhi","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7570-5756","authenticated-orcid":false,"given":"Qifan","family":"Wang","sequence":"additional","affiliation":[{"name":"Meta AI, Menlo Park, CA, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5828-9842","authenticated-orcid":false,"given":"Fuli","family":"Feng","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"2023 a. A Bi-Step Grounding Paradigm for Large Language Models in Recommendation Systems. CoRR","author":"Bao Keqin","year":"2023","unstructured":"Keqin Bao, Jizhi Zhang, Wenjie Wang, Yang Zhang, Zhengyi Yang, Yancheng Luo, Fuli Feng, Xiangnan He, and Qi Tian. 2023 a. A Bi-Step Grounding Paradigm for Large Language Models in Recommendation Systems. CoRR , Vol. abs\/2308.08434 (2023)."},{"key":"e_1_3_2_1_3_1","volume-title":"2023 b. Tallrec: An effective and efficient tuning framework to align large language model with recommendation. arXiv preprint arXiv:2305.00447","author":"Bao Keqin","year":"2023","unstructured":"Keqin Bao, Jizhi Zhang, Yang Zhang, Wenjie Wang, Fuli Feng, and Xiangnan He. 2023 b. Tallrec: An effective and efficient tuning framework to align large language model with recommendation. arXiv preprint arXiv:2305.00447 (2023)."},{"key":"e_1_3_2_1_4_1","unstructured":"Ethan Brooks Logan Walls Richard L. Lewis and Satinder Singh. 2023. Large Language Models can Implement Policy Iteration. arxiv: 2210.03821 [cs.LG]"},{"key":"e_1_3_2_1_5_1","volume-title":"Bias and Debias in Recommender System: A Survey and Future Directions. CoRR","author":"Chen Jiawei","year":"2020","unstructured":"Jiawei Chen, Hande Dong, Xiang Wang, Fuli Feng, Meng Wang, and Xiangnan He. 2020. Bias and Debias in Recommender System: A Survey and Future Directions. CoRR , Vol. abs\/2010.03240 (2020)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Jiawei Chen Junkang Wu Jiancan Wu Xuezhi Cao Sheng Zhou and Xiangnan He. 2023. Adap-(\u03c4) : Adaptively Modulating Embedding Magnitude for Recommendation. In WWW. ACM 1085--1096.","DOI":"10.1145\/3543507.3583363"},{"key":"e_1_3_2_1_7_1","volume-title":"Chi","author":"Chen Minmin","year":"2019","unstructured":"Minmin Chen, Alex Beutel, Paul Covington, Sagar Jain, Francois Belletti, and Ed H. Chi. 2019. Top-K Off-Policy Correction for a REINFORCE Recommender System. In WSDM. ACM, 456--464."},{"key":"e_1_3_2_1_8_1","volume-title":"Uncovering ChatGPT's Capabilities in Recommender Systems. arXiv preprint arXiv:2305.02182","author":"Dai Sunhao","year":"2023","unstructured":"Sunhao Dai, Ninglu Shao, Haiyuan Zhao, Weijie Yu, Zihua Si, Chen Xu, Zhongxiang Sun, Xiao Zhang, and Jun Xu. 2023. Uncovering ChatGPT's Capabilities in Recommender Systems. arXiv preprint arXiv:2305.02182 (2023)."},{"key":"e_1_3_2_1_9_1","volume-title":"Sutton","author":"Degris Thomas","year":"2012","unstructured":"Thomas Degris, Martha White, and Richard S. Sutton. 2012. Off-Policy Actor-Critic. CoRR , Vol. abs\/1205.4839 (2012)."},{"key":"e_1_3_2_1_10_1","volume-title":"Reinforcement Learning in Large Discrete Action Spaces. CoRR","author":"Dulac-Arnold Gabriel","year":"2015","unstructured":"Gabriel Dulac-Arnold, Richard Evans, Peter Sunehag, and Ben Coppin. 2015. Reinforcement Learning in Large Discrete Action Spaces. CoRR , Vol. abs\/1512.07679 (2015)."},{"key":"e_1_3_2_1_11_1","volume-title":"Recommender systems in the era of large language models (llms). arXiv preprint arXiv:2307.02046","author":"Fan Wenqi","year":"2023","unstructured":"Wenqi Fan, Zihuai Zhao, Jiatong Li, Yunqing Liu, Xiaowei Mei, Yiqi Wang, Jiliang Tang, and Qing Li. 2023. Recommender systems in the era of large language models (llms). arXiv preprint arXiv:2307.02046 (2023)."},{"key":"e_1_3_2_1_12_1","volume-title":"A Large Language Model Enhanced Conversational Recommender System. arXiv preprint arXiv:2308.06212","author":"Feng Yue","year":"2023","unstructured":"Yue Feng, Shuchang Liu, Zhenghai Xue, Qingpeng Cai, Lantao Hu, Peng Jiang, Kun Gai, and Fei Sun. 2023. A Large Language Model Enhanced Conversational Recommender System. arXiv preprint arXiv:2308.06212 (2023)."},{"key":"e_1_3_2_1_13_1","volume-title":"Benchmarking Batch Deep Reinforcement Learning Algorithms. CoRR","author":"Fujimoto Scott","year":"2019","unstructured":"Scott Fujimoto, Edoardo Conti, Mohammad Ghavamzadeh, and Joelle Pineau. 2019a. Benchmarking Batch Deep Reinforcement Learning Algorithms. CoRR , Vol. abs\/1910.01708 (2019)."},{"key":"e_1_3_2_1_14_1","volume-title":"ICML (Proceedings of Machine Learning Research","volume":"2062","author":"Fujimoto Scott","year":"2019","unstructured":"Scott Fujimoto, David Meger, and Doina Precup. 2019b. Off-Policy Deep Reinforcement Learning without Exploration. In ICML (Proceedings of Machine Learning Research, Vol. 97). PMLR, 2052--2062."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Chongming Gao Kexin Huang Jiawei Chen Yuan Zhang Biao Li Peng Jiang Shiqi Wang Zhong Zhang and Xiangnan He. 2023. Alleviating Matthew Effect of Offline Reinforcement Learning in Interactive Recommendation. In SIGIR. ACM 238--248.","DOI":"10.1145\/3539618.3591636"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.06.002"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3594871"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Huifeng Guo Ruiming Tang Yunming Ye Zhenguo Li and Xiuqiang He. 2017. DeepFM: A Factorization-Machine based Neural Network for CTR Prediction. In IJCAI. ijcai.org 1725--1731.","DOI":"10.24963\/ijcai.2017\/239"},{"key":"e_1_3_2_1_19_1","volume-title":"Large language models are zero-shot rankers for recommender systems. arXiv preprint arXiv:2305.08845","author":"Hou Yupeng","year":"2023","unstructured":"Yupeng Hou, Junjie Zhang, Zihan Lin, Hongyu Lu, Ruobing Xie, Julian McAuley, and Wayne Xin Zhao. 2023. Large language models are zero-shot rankers for recommender systems. arXiv preprint arXiv:2305.08845 (2023)."},{"key":"e_1_3_2_1_20_1","volume-title":"ICML (Proceedings of Machine Learning Research","volume":"9147","author":"Huang Wenlong","year":"2022","unstructured":"Wenlong Huang, Pieter Abbeel, Deepak Pathak, and Igor Mordatch. 2022a. Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents. In ICML (Proceedings of Machine Learning Research, Vol. 162). PMLR, 9118--9147."},{"key":"e_1_3_2_1_21_1","volume-title":"CoRL (Proceedings of Machine Learning Research","volume":"1782","author":"Huang Wenlong","year":"2022","unstructured":"Wenlong Huang, Fei Xia, Ted Xiao, Harris Chan, Jacky Liang, Pete Florence, Andy Zeng, Jonathan Tompson, Igor Mordatch, Yevgen Chebotar, Pierre Sermanet, Tomas Jackson, Noah Brown, Linda Luu, Sergey Levine, Karol Hausman, and Brian Ichter. 2022b. Inner Monologue: Embodied Reasoning through Planning with Language Models. In CoRL (Proceedings of Machine Learning Research, Vol. 205). PMLR, 1769--1782."},{"key":"e_1_3_2_1_22_1","volume-title":"Recommender ai agent: Integrating large language models for interactive recommendations. arXiv preprint arXiv:2308.16505","author":"Huang Xu","year":"2023","unstructured":"Xu Huang, Jianxun Lian, Yuxuan Lei, Jing Yao, Defu Lian, and Xing Xie. 2023. Recommender ai agent: Integrating large language models for interactive recommendations. arXiv preprint arXiv:2308.16505 (2023)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Eugene Ie Vihan Jain Jing Wang Sanmit Narvekar Ritesh Agarwal Rui Wu Heng-Tze Cheng Tushar Chandra and Craig Boutilier. 2019. SlateQ: A Tractable Decomposition for Reinforcement Learning with Recommendation Sets. In IJCAI. ijcai.org 2592--2599.","DOI":"10.24963\/ijcai.2019\/360"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_1_25_1","volume-title":"McAuley","author":"Kang Wang-Cheng","year":"2018","unstructured":"Wang-Cheng Kang and Julian J. McAuley. 2018. Self-Attentive Sequential Recommendation. In ICDM. IEEE Computer Society, 197--206."},{"key":"e_1_3_2_1_26_1","volume-title":"Chi, and Derek Zhiyuan Cheng","author":"Kang Wang-Cheng","year":"2023","unstructured":"Wang-Cheng Kang, Jianmo Ni, Nikhil Mehta, Maheswaran Sathiamoorthy, Lichan Hong, Ed Chi, and Derek Zhiyuan Cheng. 2023. Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Prediction. arXiv preprint arXiv:2305.06474 (2023)."},{"key":"e_1_3_2_1_27_1","unstructured":"Aviral Kumar Aurick Zhou George Tucker and Sergey Levine. 2020. Conservative Q-Learning for Offline Reinforcement Learning. In NeurIPS."},{"key":"e_1_3_2_1_28_1","volume-title":"2023 b","author":"Lin Bill Yuchen","year":"2023","unstructured":"Bill Yuchen Lin, Yicheng Fu, Karina Yang, Prithviraj Ammanabrolu, Faeze Brahman, Shiyu Huang, Chandra Bhagavatula, Yejin Choi, and Xiang Ren. 2023 b. SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks. CoRR , Vol. abs\/2305.17390 (2023)."},{"key":"e_1_3_2_1_29_1","volume-title":"2023 a. How Can Recommender Systems Benefit from Large Language Models: A Survey. arXiv preprint arXiv:2306.05817","author":"Lin Jianghao","year":"2023","unstructured":"Jianghao Lin, Xinyi Dai, Yunjia Xi, Weiwen Liu, Bo Chen, Xiangyang Li, Chenxu Zhu, Huifeng Guo, Yong Yu, Ruiming Tang, et al. 2023 a. How Can Recommender Systems Benefit from Large Language Models: A Survey. arXiv preprint arXiv:2306.05817 (2023)."},{"key":"e_1_3_2_1_30_1","volume-title":"2023 c. ReLLa: Retrieval-enhanced Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendation. arXiv preprint arXiv:2308.11131","author":"Lin Jianghao","year":"2023","unstructured":"Jianghao Lin, Rong Shan, Chenxu Zhu, Kounianhua Du, Bo Chen, Shigang Quan, Ruiming Tang, Yong Yu, and Weinan Zhang. 2023 c. ReLLa: Retrieval-enhanced Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendation. arXiv preprint arXiv:2308.11131 (2023)."},{"key":"e_1_3_2_1_31_1","volume-title":"Deep Reinforcement Learning based Recommendation with Explicit User-Item Interactions Modeling. CoRR","author":"Liu Feng","year":"2027","unstructured":"Feng Liu, Ruiming Tang, Xutao Li, Yunming Ye, Haokun Chen, Huifeng Guo, and Yuzhou Zhang. 2018. Deep Reinforcement Learning based Recommendation with Explicit User-Item Interactions Modeling. CoRR , Vol. abs\/1810.12027 (2018)."},{"key":"e_1_3_2_1_32_1","volume-title":"Is chatgpt a good recommender? a preliminary study. arXiv preprint arXiv:2304.10149","author":"Liu Junling","year":"2023","unstructured":"Junling Liu, Chao Liu, Renjie Lv, Kang Zhou, and Yan Zhang. 2023. Is chatgpt a good recommender? a preliminary study. arXiv preprint arXiv:2304.10149 (2023)."},{"key":"e_1_3_2_1_33_1","volume-title":"Asynchronous Methods for Deep Reinforcement Learning. In ICML (JMLR Workshop and Conference Proceedings","volume":"1937","author":"Mnih Volodymyr","year":"2016","unstructured":"Volodymyr Mnih, Adri\u00e0 Puigdom\u00e8 nech Badia, Mehdi Mirza, Alex Graves, Timothy P. Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu. 2016. Asynchronous Methods for Deep Reinforcement Learning. In ICML (JMLR Workshop and Conference Proceedings, Vol. 48). JMLR.org, 1928--1937."},{"key":"e_1_3_2_1_34_1","volume-title":"Riedmiller","author":"Mnih Volodymyr","year":"2013","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin A. Riedmiller. 2013. Playing Atari with Deep Reinforcement Learning. CoRR , Vol. abs\/1312.5602 (2013)."},{"key":"e_1_3_2_1_35_1","volume-title":"McAuley","author":"Ni Jianmo","year":"2019","unstructured":"Jianmo Ni, Jiacheng Li, and Julian J. McAuley. 2019. Justifying Recommendations using Distantly-Labeled Reviews and Fine-Grained Aspects. In EMNLP\/IJCNLP (1). Association for Computational Linguistics, 188--197."},{"key":"e_1_3_2_1_36_1","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang Long","year":"2022","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.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_37_1","volume-title":"Planning with Large Language Models via Corrective Re-prompting. CoRR","author":"Raman Shreyas Sundara","year":"2022","unstructured":"Shreyas Sundara Raman, Vanya Cohen, Eric Rosen, Ifrah Idrees, David Paulius, and Stefanie Tellex. 2022. Planning with Large Language Models via Corrective Re-prompting. CoRR , Vol. abs\/2211.09935 (2022)."},{"key":"e_1_3_2_1_38_1","volume-title":"Proximal Policy Optimization Algorithms. CoRR","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal Policy Optimization Algorithms. CoRR , Vol. abs\/1707.06347 (2017)."},{"key":"e_1_3_2_1_39_1","volume-title":"Can language agents be alternatives to PPO? A Preliminary Empirical Study On OpenAI Gym. CoRR","author":"Sheng Junjie","year":"2023","unstructured":"Junjie Sheng, Zixiao Huang, Chuyun Shen, Wenhao Li, Yun Hua, Bo Jin, Hongyuan Zha, and Xiangfeng Wang. 2023. Can language agents be alternatives to PPO? A Preliminary Empirical Study On OpenAI Gym. CoRR , Vol. abs\/2312.03290 (2023)."},{"key":"e_1_3_2_1_40_1","volume-title":"Reflexion: Language Agents with Verbal Reinforcement Learning. arxiv: 2303.11366 [cs.AI]","author":"Shinn Noah","year":"2023","unstructured":"Noah Shinn, Federico Cassano, Edward Berman, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. 2023. Reflexion: Language Agents with Verbal Reinforcement Learning. arxiv: 2303.11366 [cs.AI]"},{"key":"e_1_3_2_1_41_1","volume-title":"AdaPlanner: Adaptive Planning from Feedback with Language Models. CoRR","author":"Sun Haotian","year":"2023","unstructured":"Haotian Sun, Yuchen Zhuang, Lingkai Kong, Bo Dai, and Chao Zhang. 2023. AdaPlanner: Adaptive Planning from Feedback with Language Models. CoRR , Vol. abs\/2305.16653 (2023)."},{"key":"e_1_3_2_1_42_1","unstructured":"Hugo Touvron et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_43_1","volume-title":"2023 b. Recmind: Large language model powered agent for recommendation. arXiv preprint arXiv:2308.14296","author":"Wang Yancheng","year":"2023","unstructured":"Yancheng Wang, Ziyan Jiang, Zheng Chen, Fan Yang, Yingxue Zhou, Eunah Cho, Xing Fan, Xiaojiang Huang, Yanbin Lu, and Yingzhen Yang. 2023 b. Recmind: Large language model powered agent for recommendation. arXiv preprint arXiv:2308.14296 (2023)."},{"key":"e_1_3_2_1_44_1","volume-title":"Chi, and Minmin Chen","author":"Wang Yuyan","year":"2022","unstructured":"Yuyan Wang, Mohit Sharma, Can Xu, Sriraj Badam, Qian Sun, Lee Richardson, Lisa Chung, Ed H. Chi, and Minmin Chen. 2022. Surrogate for Long-Term User Experience in Recommender Systems. In KDD. ACM, 4100--4109."},{"key":"e_1_3_2_1_45_1","volume-title":"Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents. CoRR","author":"Wang Zihao","year":"2023","unstructured":"Zihao Wang, Shaofei Cai, Anji Liu, Xiaojian Ma, and Yitao Liang. 2023 a. Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents. CoRR , Vol. abs\/2302.01560 (2023)."},{"key":"e_1_3_2_1_46_1","volume-title":"Scott E. Reed, Bobak Shahriari, Noah Y. Siegel, cC aglar G\u00fc lcc ehre, Nicolas Heess, and Nando de Freitas.","author":"Wang Ziyu","year":"2020","unstructured":"Ziyu Wang, Alexander Novikov, Konrad Zolna, Josh Merel, Jost Tobias Springenberg, Scott E. Reed, Bobak Shahriari, Noah Y. Siegel, cC aglar G\u00fc lcc ehre, Nicolas Heess, and Nando de Freitas. 2020. Critic Regularized Regression. In NeurIPS."},{"key":"e_1_3_2_1_47_1","volume-title":"Llmrec: Large language models with graph augmentation for recommendation. arXiv preprint arXiv:2311.00423","author":"Wei Wei","year":"2023","unstructured":"Wei Wei, Xubin Ren, Jiabin Tang, Qinyong Wang, Lixin Su, Suqi Cheng, Junfeng Wang, Dawei Yin, and Chao Huang. 2023. Llmrec: Large language models with graph augmentation for recommendation. arXiv preprint arXiv:2311.00423 (2023)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"crossref","unstructured":"Junda Wu Zhihui Xie Tong Yu Handong Zhao Ruiyi Zhang and Shuai Li. 2022. Dynamics-Aware Adaptation for Reinforcement Learning Based Cross-Domain Interactive Recommendation. In SIGIR. ACM 290--300.","DOI":"10.1145\/3477495.3531969"},{"key":"e_1_3_2_1_49_1","volume-title":"2023 a. Exploring large language model for graph data understanding in online job recommendations. arXiv preprint arXiv:2307.05722","author":"Wu Likang","year":"2023","unstructured":"Likang Wu, Zhaopeng Qiu, Zhi Zheng, Hengshu Zhu, and Enhong Chen. 2023 a. Exploring large language model for graph data understanding in online job recommendations. arXiv preprint arXiv:2307.05722 (2023)."},{"key":"e_1_3_2_1_50_1","volume-title":"2023 b. A Survey on Large Language Models for Recommendation. arXiv preprint arXiv:2305.19860","author":"Wu Likang","year":"2023","unstructured":"Likang Wu, Zhi Zheng, Zhaopeng Qiu, Hao Wang, Hongchao Gu, Tingjia Shen, Chuan Qin, Chen Zhu, Hengshu Zhu, Qi Liu, et al. 2023 b. A Survey on Large Language Models for Recommendation. arXiv preprint arXiv:2305.19860 (2023)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3133025"},{"key":"e_1_3_2_1_52_1","volume-title":"Towards Open-World Recommendation with Knowledge Augmentation from Large Language Models. arXiv preprint arXiv:2306.10933","author":"Xi Yunjia","year":"2023","unstructured":"Yunjia Xi, Weiwen Liu, Jianghao Lin, Jieming Zhu, Bo Chen, Ruiming Tang, Weinan Zhang, Rui Zhang, and Yong Yu. 2023. Towards Open-World Recommendation with Knowledge Augmentation from Large Language Models. arXiv preprint arXiv:2306.10933 (2023)."},{"key":"e_1_3_2_1_53_1","volume-title":"Jose","author":"Xin Xin","year":"2020","unstructured":"Xin Xin, Alexandros Karatzoglou, Ioannis Arapakis, and Joemon M. Jose. 2020. Self-Supervised Reinforcement Learning for Recommender Systems. In SIGIR. ACM, 931--940."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"crossref","unstructured":"Shuyuan Xu Juntao Tan Zuohui Fu Jianchao Ji Shelby Heinecke and Yongfeng Zhang. 2022. Dynamic Causal Collaborative Filtering. In CIKM. ACM 2301--2310.","DOI":"10.1145\/3511808.3557300"},{"key":"e_1_3_2_1_55_1","unstructured":"Shunyu Yao Jeffrey Zhao Dian Yu Nan Du Izhak Shafran Karthik R. Narasimhan and Yuan Cao. 2023. ReAct: Synergizing Reasoning and Acting in Language Models. In ICLR. OpenReview.net."},{"key":"e_1_3_2_1_56_1","volume-title":"EasyRL4Rec: A User-Friendly Code Library for Reinforcement Learning Based Recommender Systems. arXiv preprint arXiv:2402.15164","author":"Yu Yuanqing","year":"2024","unstructured":"Yuanqing Yu, Chongming Gao, Jiawei Chen, Heng Tang, Yuefeng Sun, Qian Chen, Weizhi Ma, and Min Zhang. 2024. EasyRL4Rec: A User-Friendly Code Library for Reinforcement Learning Based Recommender Systems. arXiv preprint arXiv:2402.15164 (2024)."},{"key":"e_1_3_2_1_57_1","volume-title":"2023 b. Large Language Model Is Semi-Parametric Reinforcement Learning Agent. CoRR","author":"Zhang Danyang","year":"2023","unstructured":"Danyang Zhang, Lu Chen, Situo Zhang, Hongshen Xu, Zihan Zhao, and Kai Yu. 2023 b. Large Language Model Is Semi-Parametric Reinforcement Learning Agent. CoRR , Vol. abs\/2306.07929 (2023)."},{"key":"e_1_3_2_1_58_1","volume-title":"2023 a. Is chatgpt fair for recommendation? evaluating fairness in large language model recommendation. arXiv preprint arXiv:2305.07609","author":"Zhang Jizhi","year":"2023","unstructured":"Jizhi Zhang, Keqin Bao, Yang Zhang, Wenjie Wang, Fuli Feng, and Xiangnan He. 2023 a. Is chatgpt fair for recommendation? evaluating fairness in large language model recommendation. arXiv preprint arXiv:2305.07609 (2023)."},{"key":"e_1_3_2_1_59_1","volume-title":"Leyu Lin, and Ji-Rong Wen. 2023 d. Recommendation as instruction following: A large language model empowered recommendation approach. arXiv preprint arXiv:2305.07001","author":"Zhang Junjie","year":"2023","unstructured":"Junjie Zhang, Ruobing Xie, Yupeng Hou, Wayne Xin Zhao, Leyu Lin, and Ji-Rong Wen. 2023 d. Recommendation as instruction following: A large language model empowered recommendation approach. arXiv preprint arXiv:2305.07001 (2023)."},{"key":"e_1_3_2_1_60_1","volume-title":"2023 c. Collm: Integrating collaborative embeddings into large language models for recommendation. arXiv preprint arXiv:2310.19488","author":"Zhang Yang","year":"2023","unstructured":"Yang Zhang, Fuli Feng, Jizhi Zhang, Keqin Bao, Qifan Wang, and Xiangnan He. 2023 c. Collm: Integrating collaborative embeddings into large language models for recommendation. arXiv preprint arXiv:2310.19488 (2023)."},{"key":"e_1_3_2_1_61_1","volume-title":"ExpeL: LLM Agents Are Experiential Learners. CoRR","author":"Zhao Andrew","year":"2023","unstructured":"Andrew Zhao, Daniel Huang, Quentin Xu, Matthieu Lin, Yong-Jin Liu, and Gao Huang. 2023. ExpeL: LLM Agents Are Experiential Learners. CoRR , Vol. abs\/2308.10144 (2023)."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"crossref","unstructured":"Xiangyu Zhao Long Xia Liang Zhang Zhuoye Ding Dawei Yin and Jiliang Tang. 2018. Deep reinforcement learning for page-wise recommendations. In RecSys. ACM 95--103.","DOI":"10.1145\/3240323.3240374"},{"key":"e_1_3_2_1_63_1","volume-title":"Xing Xie, and Zhenhui Li.","author":"Zheng Guanjie","year":"2018","unstructured":"Guanjie Zheng, Fuzheng Zhang, Zihan Zheng, Yang Xiang, Nicholas Jing Yuan, Xing Xie, and Zhenhui Li. 2018. DRN: A Deep Reinforcement Learning Framework for News Recommendation. In WWW. ACM, 167--176."}],"event":{"name":"SIGIR 2024: The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Washington DC USA","acronym":"SIGIR 2024","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657683","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626772.3657683","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:43:57Z","timestamp":1755841437000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657683"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":63,"alternative-id":["10.1145\/3626772.3657683","10.1145\/3626772"],"URL":"https:\/\/doi.org\/10.1145\/3626772.3657683","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]},"assertion":[{"value":"2024-07-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}