{"id":"https://openalex.org/W7137893911","doi":"https://doi.org/10.1609/aaai.v40i2.37113","title":"SoMe: A Realistic Benchmark for LLM-based Social Media Agents","display_name":"SoMe: A Realistic Benchmark for LLM-based Social Media Agents","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137893911","doi":"https://doi.org/10.1609/aaai.v40i2.37113"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i2.37113","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i2.37113","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37113/41075","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37113/41075","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068536664","display_name":"Dizhan Xue","orcid":"https://orcid.org/0000-0002-0173-1556"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dizhan Xue","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences\nSchool of Artificial Intelligence, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences\nSchool of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129641694","display_name":"Jing Cui","orcid":null},"institutions":[{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Cui","raw_affiliation_strings":["School of Computer Science and Engineering, Tianjin University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Tianjin University of Technology","institution_ids":["https://openalex.org/I136765683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129688878","display_name":"Shengsheng Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengsheng Qian","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences\nSchool of Artificial Intelligence, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences\nSchool of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063098561","display_name":"Chuanrui Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanrui Hu","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129643012","display_name":"Changsheng Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changsheng Xu","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences\nSchool of Artificial Intelligence, University of Chinese Academy of Sciences\nPeng Cheng Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences\nSchool of Artificial Intelligence, University of Chinese Academy of Sciences\nPeng Cheng Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"2","first_page":"1391","last_page":"1399"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.3172000050544739,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.3172000050544739,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.12060000002384186,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.10649999976158142,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.84170001745224},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.7728999853134155},{"id":"https://openalex.org/keywords/mainstream","display_name":"Mainstream","score":0.7010999917984009},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5631999969482422},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.5016999840736389}],"concepts":[{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.84170001745224},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.7728999853134155},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7271000146865845},{"id":"https://openalex.org/C2777617010","wikidata":"https://www.wikidata.org/wiki/Q18957","display_name":"Mainstream","level":2,"score":0.7010999917984009},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5631999969482422},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.5016999840736389},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.47049999237060547},{"id":"https://openalex.org/C74216064","wikidata":"https://www.wikidata.org/wiki/Q615684","display_name":"Social computing","level":3,"score":0.4214000105857849},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.39089998602867126},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.38690000772476196},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.30149999260902405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2782999873161316},{"id":"https://openalex.org/C139475501","wikidata":"https://www.wikidata.org/wiki/Q17081866","display_name":"Social heuristics","level":4,"score":0.27149999141693115},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.26409998536109924}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i2.37113","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i2.37113","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37113/41075","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37113","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37113","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i2.37113","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i2.37113","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37113/41075","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.47367575764656067,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2280626339","display_name":null,"funder_award_id":"62276257","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3118817269","display_name":null,"funder_award_id":"2023YFC3310700","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137893911.pdf","grobid_xml":"https://content.openalex.org/works/W7137893911.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Intelligent":[0],"agents":[1,23,70,142],"powered":[2],"by":[3],"large":[4],"language":[5],"models":[6],"(LLMs)":[7],"have":[8],"recently":[9],"demonstrated":[10],"impressive":[11],"capabilities":[12],"and":[13,51,78,99,107,121,135,152,173,185],"gained":[14],"increasing":[15],"popularity":[16],"on":[17],"social":[18,29,68,80,90,104,124,140,146,170,190,204],"media":[19,46,69,81,91,105,125,141,147,171,191,205],"platforms.":[20],"While":[21],"LLM":[22],"are":[24],"reshaping":[25],"the":[26,118,129,157,162,182],"ecology":[27],"of":[28,41,88,164],"media,":[30],"there":[31],"exists":[32],"a":[33,38,62,85,133,197],"current":[34,183],"gap":[35],"in":[36,168],"conducting":[37],"comprehensive":[39],"evaluation":[40,178],"their":[42],"ability":[43],"to":[44,66,131,143],"comprehend":[45],"content,":[47],"understand":[48],"user":[49,97],"behaviors,":[50],"make":[52],"intricate":[53],"decisions.":[54],"To":[55],"address":[56],"this":[57],"challenge,":[58],"we":[59,155],"introduce":[60],"SoMe,":[61],"pioneering":[63],"benchmark":[64],"designed":[65],"evaluate":[67],"equipped":[71],"with":[72,110,117],"various":[73,103],"agent":[74,92,192],"tools":[75],"for":[76,123,138,202],"accessing":[77],"analyzing":[79],"data.":[82],"SoMe":[83,127,195],"comprises":[84],"diverse":[86,145],"collection":[87],"8":[89],"tasks,":[93,126],"9,164,284":[94],"posts,":[95],"6,591":[96],"profiles,":[98],"25,686":[100],"reports":[101],"from":[102],"platforms":[106],"external":[108],"websites,":[109],"17,869":[111],"meticulously":[112],"annotated":[113],"task":[114],"queries.":[115],"Compared":[116],"existing":[119],"datasets":[120],"benchmarks":[122],"is":[128],"first":[130,158],"provide":[132,156],"versatile":[134],"realistic":[136,169],"platform":[137],"LLM-based":[139],"handle":[144,189],"tasks.":[148],"By":[149],"extensive":[150],"quantitative":[151],"qualitative":[153],"analysis,":[154],"overview":[159],"insight":[160],"into":[161],"performance":[163],"mainstream":[165],"agentic":[166],"LLMs":[167,187],"environments":[172],"identify":[174],"several":[175],"limitations.":[176],"Our":[177],"reveals":[179],"that":[180],"both":[181],"closed-source":[184],"open-source":[186],"cannot":[188],"tasks":[193],"satisfactorily.":[194],"provides":[196],"challenging":[198],"yet":[199],"meaningful":[200],"testbed":[201],"future":[203],"agents.":[206]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-03-18T00:00:00"}