{"id":"https://openalex.org/W4416016528","doi":"https://doi.org/10.1145/3746252.3761127","title":"EvalAgent: Towards Evaluating News Recommender Systems with LLM-based Agents","display_name":"EvalAgent: Towards Evaluating News Recommender Systems with LLM-based Agents","publication_year":2025,"publication_date":"2025-11-08","ids":{"openalex":"https://openalex.org/W4416016528","doi":"https://doi.org/10.1145/3746252.3761127"},"language":null,"primary_location":{"id":"doi:10.1145/3746252.3761127","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3761127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101744071","display_name":"Guangping Zhang","orcid":"https://orcid.org/0009-0001-9853-8268"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangping Zhang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0001-9853-8268","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100364191","display_name":"Peng Zhang","orcid":"https://orcid.org/0000-0002-9109-4625"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Zhang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-9109-4625","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022905969","display_name":"Jiahao Liu","orcid":"https://orcid.org/0000-0002-5654-5902"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahao Liu","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-5654-5902","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhuoheng Li","orcid":"https://orcid.org/0009-0001-3964-3201"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuoheng Li","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0001-3964-3201","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440920","display_name":"Dongsheng Li","orcid":"https://orcid.org/0000-0003-3103-8442"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongsheng Li","raw_affiliation_strings":["Microsoft Research Asia, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3103-8442","affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Shanghai, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071156485","display_name":"Hansu Gu","orcid":"https://orcid.org/0000-0002-1426-3210"},"institutions":[{"id":"https://openalex.org/I2802723755","display_name":"Independent Sector","ror":"https://ror.org/05vhwqa91","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2802723755"]},{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hansu Gu","raw_affiliation_strings":["Independent, Seattle, USA"],"raw_orcid":"https://orcid.org/0000-0002-1426-3210","affiliations":[{"raw_affiliation_string":"Independent, Seattle, USA","institution_ids":["https://openalex.org/I2802723755","https://openalex.org/I58610484"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004237040","display_name":"Tun Lu","orcid":"https://orcid.org/0000-0002-6633-4826"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tun Lu","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6633-4826","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091087409","display_name":"Ning Gu","orcid":"https://orcid.org/0000-0002-2915-974X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Gu","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2915-974X","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4086","last_page":"4095"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.6656000018119812,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.6656000018119812,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.03610000014305115,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.026599999517202377,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.8955000042915344},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.49779999256134033},{"id":"https://openalex.org/keywords/collaborative-filtering","display_name":"Collaborative filtering","score":0.4609000086784363},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.37119999527931213},{"id":"https://openalex.org/keywords/online-and-offline","display_name":"Online and offline","score":0.35899999737739563},{"id":"https://openalex.org/keywords/user-engagement","display_name":"User engagement","score":0.3244999945163727}],"concepts":[{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.8955000042915344},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8363000154495239},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5085999965667725},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.49779999256134033},{"id":"https://openalex.org/C21569690","wikidata":"https://www.wikidata.org/wiki/Q94702","display_name":"Collaborative filtering","level":3,"score":0.4609000086784363},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4011000096797943},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.37119999527931213},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.35899999737739563},{"id":"https://openalex.org/C2984870255","wikidata":"https://www.wikidata.org/wiki/Q5196451","display_name":"User engagement","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.314300000667572},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26759999990463257}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746252.3761127","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3761127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4817111480","display_name":null,"funder_award_id":"62172106","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2030007850","https://openalex.org/W2774321216","https://openalex.org/W2896659017","https://openalex.org/W2917760808","https://openalex.org/W2945357717","https://openalex.org/W3201178526","https://openalex.org/W4205665497","https://openalex.org/W4224313282","https://openalex.org/W4387835442","https://openalex.org/W4393065402","https://openalex.org/W4394938993","https://openalex.org/W4396758674","https://openalex.org/W4400525295","https://openalex.org/W4405643789","https://openalex.org/W4406800520","https://openalex.org/W4409671937","https://openalex.org/W4410089597"],"related_works":[],"abstract_inverted_index":{"Online":[0],"news":[1,70,94,149],"platforms":[2],"have":[3],"become":[4],"the":[5,90,97,103],"primary":[6],"source":[7],"of":[8,93,118],"information":[9],"consumption,":[10],"with":[11,35,133,160],"recommender":[12,71,135,150,169],"systems":[13],"serving":[14],"as":[15],"critical":[16],"gateways":[17],"that":[18],"shape":[19],"public":[20],"discourse":[21],"through":[22],"their":[23],"algorithmic":[24],"power,":[25],"necessitating":[26],"rigorous":[27],"evaluation":[28,32,146],"methodologies.":[29],"Traditional":[30],"offline":[31],"methods":[33],"struggle":[34],"evolving":[36],"user":[37,155],"behavior":[38],"and":[39,49,100,115,143,154],"dynamic":[40],"system":[41,65,170],"adaptation,":[42],"while":[43],"online":[44,69],"experiments":[45,153],"are":[46],"costly,":[47],"time-consuming,":[48],"ethically":[50,144],"challenging.":[51],"To":[52],"address":[53],"these":[54],"challenges,":[55],"this":[56],"paper":[57],"introduces":[58],"EvalAgent,":[59],"a":[60,113,140],"large":[61],"language":[62],"model":[63,79],"agent":[64],"for":[66,148],"simulating":[67],"real-world":[68,134],"systems.":[72,136,151],"EvalAgent":[73],"employs":[74],"Stable":[75],"Memory":[76],"(StM)":[77],"to":[78,106,129,164],"users'":[80,108],"exploration-exploitation":[81],"dynamics,":[82],"mitigating":[83],"noise":[84],"from":[85],"irrelevant":[86],"interactions":[87],"by":[88],"analyzing":[89],"distribution":[91],"density":[92],"articles":[95],"within":[96],"short-term":[98],"memory,":[99],"incrementally":[101],"maintains":[102],"long-term":[104],"memory":[105],"capture":[107],"high-level":[109],"preferences,":[110],"thereby":[111],"enabling":[112],"consistent":[114],"reliable":[116],"simulation":[117],"sustained":[119],"interactions.":[120],"It":[121],"further":[122],"incorporates":[123],"an":[124],"Environment":[125],"Interaction":[126],"Framework":[127],"(EIF)":[128],"enable":[130],"seamless":[131],"engagement":[132],"This":[137],"approach":[138],"yields":[139],"precise,":[141],"scalable,":[142],"responsible":[145],"framework":[147],"Comprehensive":[152],"studies":[156],"substantiate":[157],"EvalAgent's":[158],"efficacy,":[159],"publicly":[161],"available":[162],"code":[163],"support":[165],"ongoing":[166],"research":[167],"in":[168],"evaluation.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-11-08T00:00:00"}