{"id":"https://openalex.org/W4387800910","doi":"https://doi.org/10.48550/arxiv.2310.11954","title":"MusicAgent: An AI Agent for Music Understanding and Generation with Large Language Models","display_name":"MusicAgent: An AI Agent for Music Understanding and Generation with Large Language Models","publication_year":2023,"publication_date":"2023-10-18","ids":{"openalex":"https://openalex.org/W4387800910","doi":"https://doi.org/10.48550/arxiv.2310.11954"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2310.11954","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.11954","pdf_url":"https://arxiv.org/pdf/2310.11954","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2310.11954","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065501741","display_name":"Dingyao Yu","orcid":"https://orcid.org/0000-0002-7013-3576","observed_orcids":["https://orcid.org/0000-0002-7013-3576"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"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":"Yu, Dingyao","raw_affiliation_strings":["Microsoft Research Asia","Peking University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Peking University ,","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028035527","display_name":"Kaitao Song","orcid":"https://orcid.org/0000-0002-4046-8594","observed_orcids":["https://orcid.org/0000-0002-4046-8594"]},"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":"Song, Kaitao","raw_affiliation_strings":["Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030047753","display_name":"Peiling Lu","orcid":null,"observed_orcids":[]},"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":"Lu, Peiling","raw_affiliation_strings":["Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":null,"display_name":"He, Tianyu","orcid":null,"observed_orcids":[]},"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":"He, Tianyu","raw_affiliation_strings":["Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100571689","display_name":"Xu Tan","orcid":"https://orcid.org/0009-0002-0528-4631","observed_orcids":["https://orcid.org/0009-0002-0528-4631"]},"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":"Tan, Xu","raw_affiliation_strings":["Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101883632","display_name":"Wei Ye","orcid":"https://orcid.org/0009-0006-0568-9128","observed_orcids":["https://orcid.org/0009-0006-0568-9128"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye, Wei","raw_affiliation_strings":["Peking University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University ,","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101435571","display_name":"Shikun Zhang","orcid":"https://orcid.org/0000-0002-8576-2674","observed_orcids":["https://orcid.org/0000-0002-8576-2674","https://orcid.org/0000-0002-3132-4935"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Shikun","raw_affiliation_strings":["Peking University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University ,","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":null,"display_name":"Bian, Jiang","orcid":null,"observed_orcids":[]},"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":"Bian, Jiang","raw_affiliation_strings":["Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":32,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.5702999830245972,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.5702999830245972,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.42480000853538513,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T13904","display_name":"Artificial Intelligence Applications","score":0.0007999999797903001,"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/ai-agents","display_name":"AI agents","score":0.5090000033378601},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9079999923706055},{"id":"https://openalex.org/keywords/musical-understanding","display_name":"musical understanding","score":0.8740000128746033},{"id":"https://openalex.org/keywords/music-generation","display_name":"music generation","score":0.9810000061988831},{"id":"https://openalex.org/keywords/tool-integration","display_name":"tool integration","score":0.6389999985694885},{"id":"https://openalex.org/keywords/task-decomposition","display_name":"task decomposition","score":0.8510000109672546},{"id":"https://openalex.org/keywords/timbre-synthesis","display_name":"timbre synthesis","score":0.8009999990463257},{"id":"https://openalex.org/keywords/music-classification","display_name":"music classification","score":0.9819999933242798}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.803166389465332},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7405505180358887},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.614459753036499},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5278570055961609},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.4853176474571228},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.47595664858818054},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.43028223514556885},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3911290764808655},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3384571075439453},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.13354182243347168},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2310.11954","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.11954","pdf_url":"https://arxiv.org/pdf/2310.11954","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2310.11954","doi":"https://doi.org/10.48550/arxiv.2310.11954","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.11954","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2310.11954","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.11954","pdf_url":"https://arxiv.org/pdf/2310.11954","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320333993","display_name":"Microsoft Research Asia","ror":"https://ror.org/0300m5276"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387800910.pdf","grobid_xml":"https://content.openalex.org/works/W4387800910.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W2894295011","https://openalex.org/W2971458685","https://openalex.org/W3097514409","https://openalex.org/W3173187964","https://openalex.org/W3196954682","https://openalex.org/W3208828709","https://openalex.org/W4224308101","https://openalex.org/W4229005866","https://openalex.org/W4303443398","https://openalex.org/W4318351475","https://openalex.org/W4318908031","https://openalex.org/W4322718191","https://openalex.org/W4323717348","https://openalex.org/W4366999188","https://openalex.org/W4379251846","https://openalex.org/W4385567149","https://openalex.org/W4385567278","https://openalex.org/W4385572845","https://openalex.org/W4393178509","https://openalex.org/W4414360197","https://openalex.org/W7133202489"],"related_works":["https://openalex.org/W4408816333","https://openalex.org/W4415087895","https://openalex.org/W2557022074","https://openalex.org/W4416681942","https://openalex.org/W4415110550","https://openalex.org/W4387838399","https://openalex.org/W4386228790","https://openalex.org/W4389471254","https://openalex.org/W4327974172","https://openalex.org/W7160188280"],"abstract_inverted_index":{"AI-empowered":[0],"music":[1,23,44,55,175,217],"processing":[2],"is":[3,30,68,183],"a":[4,72,114,213],"diverse":[5,141],"field":[6],"that":[7,137],"encompasses":[8],"dozens":[9],"of":[10,36,54,104,180,190],"tasks,":[11,79],"ranging":[12],"from":[13,140,187],"generation":[14],"tasks":[15,21],"(e.g.,":[16,22,158],"timbre":[17],"synthesis)":[18],"to":[19,33,39,70,74,84,95,127,160,184,195,206],"comprehension":[20],"classification).":[24],"For":[25],"developers":[26],"and":[27,57,76,80,89,123,147,164,172,215],"amateurs,":[28],"it":[29,67],"very":[31],"difficult":[32],"grasp":[34],"all":[35],"these":[37,78,162],"task":[38,110],"satisfy":[40],"their":[41,87,97],"requirements":[42],"in":[43,51,109],"processing,":[45],"especially":[46],"considering":[47],"the":[48,52,58,101,188,198,204,210],"huge":[49],"differences":[50],"representations":[53],"data":[56],"model":[59],"applicability":[60],"across":[61],"platforms":[62],"among":[63],"various":[64],"tasks.":[65],"Consequently,":[66],"necessary":[69],"build":[71,134],"system":[73,182,211],"organize":[75,161],"integrate":[77],"thus":[81],"help":[82],"practitioners":[83],"automatically":[85,165],"analyze":[86],"demand":[88],"call":[90],"suitable":[91],"tools":[92,122,139,163],"as":[93],"solutions":[94],"fulfill":[96],"requirements.":[98,130],"Inspired":[99],"by":[100,156],"recent":[102],"success":[103],"large":[105],"language":[106],"models":[107],"(LLMs)":[108],"automation,":[111],"we":[112,133],"develop":[113],"system,":[115],"named":[116],"MusicAgent,":[117],"which":[118],"integrates":[119],"numerous":[120],"music-related":[121],"an":[124,152],"autonomous":[125,153],"workflow":[126,154],"address":[128],"user":[129,167],"More":[131],"specifically,":[132],"1)":[135],"toolset":[136],"collects":[138],"sources,":[142],"including":[143],"Hugging":[144],"Face,":[145],"GitHub,":[146],"Web":[148],"API,":[149],"etc.":[150],"2)":[151],"empowered":[155],"LLMs":[157],"ChatGPT)":[159],"decompose":[166],"requests":[168],"into":[169],"multiple":[170],"sub-tasks":[171],"invoke":[173],"corresponding":[174],"tools.":[176],"The":[177],"primary":[178],"goal":[179],"this":[181],"free":[185],"users":[186,203],"intricacies":[189],"AI-music":[191],"tools,":[192,209],"enabling":[193],"them":[194],"concentrate":[196],"on":[197],"creative":[199],"aspect.":[200],"By":[201],"granting":[202],"freedom":[205],"effortlessly":[207],"combine":[208],"offers":[212],"seamless":[214],"enriching":[216],"experience.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":3}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-10-21T00:00:00"}
