{"id":"https://openalex.org/W7165194577","doi":"https://doi.org/10.1145/3770854.3785688","title":"Exploring Recommender System Evaluation:A Multi-Modal LLM Agent Framework for A/B Testing","display_name":"Exploring Recommender System Evaluation:A Multi-Modal LLM Agent Framework for A/B Testing","publication_year":2026,"publication_date":"2026-08-01","ids":{"openalex":"https://openalex.org/W7165194577","doi":"https://doi.org/10.1145/3770854.3785688"},"language":"en","primary_location":{"id":"pmh:oai:pure.atira.dk:publications/761614e1-30e3-4d58-97ae-4368d303b1bd","is_oa":true,"landing_page_url":"https://hdl.handle.net/2031/761614e1-30e3-4d58-97ae-4368d303b1bd","pdf_url":null,"source":{"id":"https://openalex.org/S7407055387","display_name":"CityU Scholars","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"type":"conference-paper","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/2031/761614e1-30e3-4d58-97ae-4368d303b1bd","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127961556","display_name":"Wenlin Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Wenlin; id_orcid 0000-0003-1809-8264","raw_affiliation_strings":["Department of Data Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Data Science","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057851674","display_name":"X J Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Li, Xiangyang","raw_affiliation_strings":["Department of Data Science","Huawei Technologies Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Data Science","institution_ids":[]},{"raw_affiliation_string":"Huawei Technologies Co., Ltd","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122661771","display_name":"Qiyuan Ge","orcid":null},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ge, Qiyuan","raw_affiliation_strings":["City University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075136607","display_name":"Kuicai Dong","orcid":"https://orcid.org/0000-0002-5564-0641"},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dong, Kuicai","raw_affiliation_strings":["Huawei Technologies Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138891708","display_name":"Pengyue; id_orcid 0000-0003-4712-3676 Jia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia, Pengyue; id_orcid 0000-0003-4712-3676","raw_affiliation_strings":["Department of Data Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Data Science","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057851674","display_name":"X J Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Li, Xiaopeng; id_orcid 0009-0008-6162-8500","raw_affiliation_strings":["Department of Data Science","Huawei Technologies Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Data Science","institution_ids":[]},{"raw_affiliation_string":"Huawei Technologies Co., Ltd","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138935965","display_name":"Zijian Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I4210136497","display_name":"Jilin Medical University","ror":"https://ror.org/03mzw7781","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136497"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Zijian","raw_affiliation_strings":["Jilin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jilin University","institution_ids":["https://openalex.org/I194450716","https://openalex.org/I4210136497"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138897308","display_name":"Maolin; id_orcid 0000-0002-0073-0172 Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I146617529","display_name":"Applied Science and Technology Research Institute","ror":"https://ror.org/03xmkea05","country_code":"CN","type":"facility","lineage":["https://openalex.org/I146617529"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Maolin; id_orcid 0000-0002-0073-0172","raw_affiliation_strings":["Hong Kong Institute of AI for Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong Institute of AI for Science","institution_ids":["https://openalex.org/I146617529"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100633632","display_name":"Yue Wang","orcid":"https://orcid.org/0000-0003-0098-5359"},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Wang, Yichao","raw_affiliation_strings":["Huawei Technologies Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138881106","display_name":"Huifeng Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Guo, Huifeng","raw_affiliation_strings":["Huawei Technologies Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138855209","display_name":"Ruiming Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tang, Ruiming","raw_affiliation_strings":["Huawei Technologies Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5138931167","display_name":"Xiangyu; id_orcid 0000-0003-2926-4416 Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhao, Xiangyu; id_orcid 0000-0003-2926-4416","raw_affiliation_strings":["Department of Data Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Data Science","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100633632","https://openalex.org/A5138931167"],"corresponding_institution_ids":["https://openalex.org/I4210160618"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.2249000072479248,"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":0.2249000072479248,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.18029999732971191,"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/T12128","display_name":"AI in Service Interactions","score":0.05999999865889549,"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":0.7409999966621399},{"id":"https://openalex.org/keywords/sandbox","display_name":"Sandbox (software development)","score":0.6995000243186951},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5562000274658203},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5526999831199646},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.49390000104904175},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.37779998779296875},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.37779998779296875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7516999840736389},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.7409999966621399},{"id":"https://openalex.org/C167981075","wikidata":"https://www.wikidata.org/wiki/Q2667186","display_name":"Sandbox (software development)","level":2,"score":0.6995000243186951},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5562000274658203},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5526999831199646},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5483999848365784},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.49390000104904175},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.37779998779296875},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.37779998779296875},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3628000020980835},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.3621000051498413},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.3578999936580658},{"id":"https://openalex.org/C67712803","wikidata":"https://www.wikidata.org/wiki/Q7901853","display_name":"User modeling","level":3,"score":0.2831999957561493},{"id":"https://openalex.org/C71191987","wikidata":"https://www.wikidata.org/wiki/Q763744","display_name":"User agent","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C201025465","wikidata":"https://www.wikidata.org/wiki/Q11248500","display_name":"User experience design","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.258899986743927},{"id":"https://openalex.org/C5894958","wikidata":"https://www.wikidata.org/wiki/Q2297769","display_name":"Software agent","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:pure.atira.dk:publications/761614e1-30e3-4d58-97ae-4368d303b1bd","is_oa":true,"landing_page_url":"https://hdl.handle.net/2031/761614e1-30e3-4d58-97ae-4368d303b1bd","pdf_url":null,"source":{"id":"https://openalex.org/S7407055387","display_name":"CityU Scholars","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:publications/761614e1-30e3-4d58-97ae-4368d303b1bd","is_oa":true,"landing_page_url":"https://hdl.handle.net/2031/761614e1-30e3-4d58-97ae-4368d303b1bd","pdf_url":null,"source":{"id":"https://openalex.org/S7407055387","display_name":"CityU Scholars","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"score":0.782578706741333,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"diningIn":[0],"recommender":[1],"systems,":[2],"online":[3,19,52,115],"A/B":[4,20,53,89,101,154,171],"testing":[5,21,90,155],"is":[6,183],"a":[7,84,96,134],"crucial":[8],"method":[9],"for":[10,88,100],"evaluating":[11],"the":[12,38,61,69,144,147,167,176],"performance":[13],"of":[14,71,146,178],"different":[15],"models.":[16,180],"However,":[17],"conducting":[18],"often":[22],"presents":[23],"significant":[24],"challenges,":[25,81],"including":[26],"substantial":[27],"economic":[28],"costs,":[29],"user":[30,86,112,125],"experience":[31],"degradation,":[32],"and":[33,64,74,105,127,133,161],"considerable":[34],"time":[35],"requirements.":[36],"With":[37],"Large":[39],"Language":[40],"Models'":[41],"powerful":[42],"capacity,":[43],"LLM-based":[44],"agent":[45,87,119,148],"shows":[46],"great":[47],"potential":[48,145],"to":[49,59,68,137,152],"replace":[50],"traditional":[51,153],"testing.":[54],"Nonetheless,":[55],"current":[56],"agents":[57],"fail":[58],"simulate":[60,138],"perception":[62,76],"process":[63],"interaction":[65],"patterns,":[66],"due":[67],"lack":[70],"real":[72,111],"environments":[73],"visual":[75],"capability.":[77],"To":[78],"address":[79],"these":[80],"we":[82,94,164],"introduce":[83],"multi-modal":[85],"(A/B":[91],"Agent).":[92],"Specifically,":[93],"construct":[95],"recommendation":[97,179],"sandbox":[98],"environment":[99],"testing,":[102],"enabling":[103],"multimodal":[104,121],"multi-page":[106],"interactions":[107],"that":[108,166],"align":[109],"with":[110],"behavior":[113],"on":[114],"platforms.":[116],"The":[117],"designed":[118],"leverages":[120],"information":[122],"perception,":[123],"fine-grained":[124],"preferences,":[126],"integrates":[128],"profiles,":[129],"action":[130],"memory":[131],"retrieval,":[132],"fatigue":[135],"system":[136],"complex":[139],"human":[140],"decision-making.":[141],"We":[142],"validated":[143],"as":[149],"an":[150],"alternative":[151],"from":[156],"three":[157],"perspectives:":[158],"model,":[159],"data,":[160],"features.":[162],"Furthermore,":[163],"found":[165],"data":[168],"generated":[169],"by":[170],"Agent":[172],"can":[173],"effectively":[174],"enhance":[175],"capabilities":[177],"Our":[181],"code":[182],"publicly":[184],"available":[185],"at":[186],"https://github.com/Applied-Machine-Learning-Lab/ABAgent.":[187],"\u00a9":[188],"2026":[189],"Owner/Author.":[190]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-06-19T00:00:00"}
