{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:18:19Z","timestamp":1784179099936,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172106"],"award-info":[{"award-number":["62172106"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3761127","type":"proceedings-article","created":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T00:18:04Z","timestamp":1762561084000},"page":"4086-4095","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["EvalAgent: Towards Evaluating News Recommender Systems with LLM-based Agents"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-9853-8268","authenticated-orcid":false,"given":"Guangping","family":"Zhang","sequence":"first","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9109-4625","authenticated-orcid":false,"given":"Peng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5654-5902","authenticated-orcid":false,"given":"Jiahao","family":"Liu","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3964-3201","authenticated-orcid":false,"given":"Zhuoheng","family":"Li","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3103-8442","authenticated-orcid":false,"given":"Dongsheng","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1426-3210","authenticated-orcid":false,"given":"Hansu","family":"Gu","sequence":"additional","affiliation":[{"name":"Independent, Seattle, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6633-4826","authenticated-orcid":false,"given":"Tun","family":"Lu","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2915-974X","authenticated-orcid":false,"given":"Ning","family":"Gu","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"2024. News Platform Fact Sheet. https:\/\/www.pewresearch.org\/journalism\/factsheet\/news-platform-fact-sheet\/"},{"key":"e_1_3_2_2_2_1","volume-title":"How algorithmic popularity bias hinders or promotes quality. Scientific reports 8, 1","author":"Ciampaglia Giovanni Luca","year":"2018","unstructured":"Giovanni Luca Ciampaglia, Azadeh Nematzadeh, Filippo Menczer, and Alessandro Flammini. 2018. How algorithmic popularity bias hinders or promotes quality. Scientific reports 8, 1 (2018), 15951."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.5214\/ans.0972.7531.200408"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1111\/bjso.12286"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306618.3314288"},{"key":"e_1_3_2_2_6_1","volume-title":"Online controlled experiments and A\/B tests. Encyclopedia of machine learning and data mining","author":"Kohavi Ron","year":"2015","unstructured":"Ron Kohavi and Roger Longbotham. 2015. Online controlled experiments and A\/B tests. Encyclopedia of machine learning and data mining (2015), 1--11."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v42i3.18142"},{"key":"e_1_3_2_2_8_1","volume-title":"Do offline metrics predict online performance in recommender systems? arXiv preprint arXiv:2011.07931","author":"Krauth Karl","year":"2020","unstructured":"Karl Krauth, Sarah Dean, Alex Zhao, Wenshuo Guo, Mihaela Curmei, Benjamin Recht, and Michael I Jordan. 2020. Do offline metrics predict online performance in recommender systems? arXiv preprint arXiv:2011.07931 (2020)."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714850"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512080"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3474259"},{"key":"e_1_3_2_2_12_1","volume-title":"Recsim ng: Toward principled uncertainty modeling for recommender ecosystems. arXiv preprint arXiv:2103.08057","author":"Mladenov Martin","year":"2021","unstructured":"Martin Mladenov, Chih-Wei Hsu, Vihan Jain, Eugene Ie, Christopher Colby, Nicolas Mayoraz, Hubert Pham, Dustin Tran, Ivan Vendrov, and Craig Boutilier. 2021. Recsim ng: Toward principled uncertainty modeling for recommender ecosystems. arXiv preprint arXiv:2103.08057 (2021)."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606763"},{"key":"e_1_3_2_2_14_1","volume-title":"Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084","author":"Reimers Nils","year":"2019","unstructured":"Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084 (2019)."},{"key":"e_1_3_2_2_15_1","volume-title":"Recommender systems: Techniques, applications, and challenges. Recommender Systems Handbook","author":"Ricci Francesco","year":"2021","unstructured":"Francesco Ricci, Lior Rokach, and Bracha Shapira. 2021. Recommender systems: Techniques, applications, and challenges. Recommender Systems Handbook (2021), 1--35."},{"key":"e_1_3_2_2_16_1","volume-title":"A Human-Centered Recommendation Framework With LLM Agents","author":"Shu Yubo","year":"2024","unstructured":"Yubo Shu, Haonan Zhang, Hansu Gu, Peng Zhang, Tun Lu, Dongsheng Li, and Ning Gu. 2024. RAH! RecSys--Assistant--Human: A Human-Centered Recommendation Framework With LLM Agents. IEEE Transactions on Computational Social Systems (2024)."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-017-0762-9"},{"key":"e_1_3_2_2_18_1","volume-title":"Density estimation for statistics and data analysis","author":"Silverman Bernard W","unstructured":"Bernard W Silverman. 2018. Density estimation for statistics and data analysis. Routledge."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308560.3317303"},{"key":"e_1_3_2_2_20_1","volume-title":"Simulating social media using large language models to evaluate alternative news feed algorithms. arXiv preprint arXiv:2310.05984","author":"T\u00f6rnberg Petter","year":"2023","unstructured":"Petter T\u00f6rnberg, Diliara Valeeva, Justus Uitermark, and Christopher Bail. 2023. Simulating social media using large language models to evaluate alternative news feed algorithms. arXiv preprint arXiv:2310.05984 (2023)."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40231-1"},{"key":"e_1_3_2_2_22_1","volume-title":"Jun Xu, Zhicheng Dou, Jun Wang, and Ji-Rong Wen.","author":"Wang Lei","year":"2023","unstructured":"Lei Wang, Jingsen Zhang, Hao Yang, Zhiyuan Chen, Jiakai Tang, Zeyu Zhang, Xu Chen, Yankai Lin, Ruihua Song, Wayne Xin Zhao, Jun Xu, Zhicheng Dou, Jun Wang, and Ji-Rong Wen. 2023. When Large Language Model based Agent Meets User Behavior Analysis: A Novel User Simulation Paradigm. arXiv preprint arXiv:2306.02552 (2023)."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3708985"},{"key":"e_1_3_2_2_24_1","volume-title":"Jingyuan Wang, and Ji-Rong Wen.","author":"Wang Xiaolei","year":"2023","unstructured":"Xiaolei Wang, Xinyu Tang, Wayne Xin Zhao, Jingyuan Wang, and Ji-Rong Wen. 2023. Rethinking the evaluation for conversational recommendation in the era of large language models. arXiv preprint arXiv:2305.13112 (2023)."},{"key":"e_1_3_2_2_25_1","volume-title":"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. Recmind: Large language model powered agent for recommendation. arXiv preprint arXiv:2308.14296 (2023)."},{"key":"e_1_3_2_2_26_1","unstructured":"Zhiheng Xi Wenxiang Chen Xin Guo Wei He Yiwen Ding Boyang Hong Ming Zhang Junzhe Wang Senjie Jin Enyu Zhou et al. 2023. The Rise and Potential of Large Language Model Based Agents: A Survey. arXiv preprint arXiv:2309.07864 (2023)."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4222-0"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657844"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2024.3381329"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645537"},{"key":"e_1_3_2_2_31_1","first-page":"44880","article-title":"KuaiSim: A comprehensive simulator for recommender systems","volume":"36","author":"Zhao Kesen","year":"2023","unstructured":"Kesen Zhao, Shuchang Liu, Qingpeng Cai, Xiangyu Zhao, Ziru Liu, Dong Zheng, Peng Jiang, and Kun Gai. 2023. KuaiSim: A comprehensive simulator for recommender systems. Advances in Neural Information Processing Systems 36 (2023), 44880--44897.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714858"}],"event":{"name":"CIKM '25: The 34th ACM International Conference on Information and Knowledge Management","location":"Seoul Republic of Korea","acronym":"CIKM '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the 34th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746252.3761127","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T01:40:19Z","timestamp":1765503619000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3761127"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":32,"alternative-id":["10.1145\/3746252.3761127","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3761127","relation":{},"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"2025-11-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}