{"id":"https://openalex.org/W7214012004","doi":"https://doi.org/10.48550/arxiv.2609.24812","title":"MSI-Bench: Evaluating Multi-Speaker Voice Interaction for Collaborative AI Agents","display_name":"MSI-Bench: Evaluating Multi-Speaker Voice Interaction for Collaborative AI Agents","publication_year":2026,"publication_date":"2026-09-21","ids":{"openalex":"https://openalex.org/W7214012004","doi":"https://doi.org/10.48550/arxiv.2609.24812"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.24812","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.24812","pdf_url":"https://arxiv.org/pdf/2609.24812","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/2609.24812","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107672125","display_name":"Chenxu Xiong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiong, Chenxu","raw_affiliation_strings":["AI Santa Clara , CA 95054"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Santa Clara , CA 95054","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130816695","display_name":"Dongming Shen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Dongming","raw_affiliation_strings":["AI Santa Clara , CA 95054"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Santa Clara , CA 95054","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113013345","display_name":"Yuzhi Tang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Yuzhi","raw_affiliation_strings":["AI Santa Clara , CA 95054"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Santa Clara , CA 95054","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130769824","display_name":"Wentao Ma","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Wentao","raw_affiliation_strings":["AI Santa Clara , CA 95054"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Santa Clara , CA 95054","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152465598","display_name":"Mu Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Mu","raw_affiliation_strings":["AI Santa Clara , CA 95054"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Santa Clara , CA 95054","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130721492","display_name":"Alex Smola","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Smola, Alex","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"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/T12031","display_name":"Speech and dialogue systems","score":0.9961000084877014,"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/T12031","display_name":"Speech and dialogue systems","score":0.9961000084877014,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.003100000089034438,"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":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1406","display_name":"Marketing"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/voice-assistants","display_name":"voice assistants","score":0.7369999885559082},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.4790000021457672},{"id":"https://openalex.org/keywords/multiparty-conversation","display_name":"multi-party conversation","score":0.5379999876022339},{"id":"https://openalex.org/keywords/instruction-following","display_name":"instruction following","score":0.9039999842643738},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.5379999876022339},{"id":"https://openalex.org/keywords/failure-analysis","display_name":"failure analysis","score":0.47600001096725464}],"concepts":[{"id":"https://openalex.org/C111640148","wikidata":"https://www.wikidata.org/wiki/Q847349","display_name":"Rubric","level":2,"score":0.7087000012397766},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6563000082969666},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6107000112533569},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.5491999983787537},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4828999936580658},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4618000090122223},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4422000050544739},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.4309999942779541},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4009000062942505},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36550000309944153},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3587000072002411},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.35600000619888306},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.2621000111103058}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.24812","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.24812","pdf_url":"https://arxiv.org/pdf/2609.24812","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.2609.24812","doi":"https://doi.org/10.48550/arxiv.2609.24812","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.24812","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:2609.24812","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.24812","pdf_url":"https://arxiv.org/pdf/2609.24812","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":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214012004.pdf","grobid_xml":"https://content.openalex.org/works/W7214012004.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W4400717319","https://openalex.org/W4403883071","https://openalex.org/W4409051416","https://openalex.org/W4414690747","https://openalex.org/W4415085804","https://openalex.org/W4415255153","https://openalex.org/W4415318421","https://openalex.org/W4416238789","https://openalex.org/W4416243461","https://openalex.org/W4416246780","https://openalex.org/W7118972306","https://openalex.org/W7126278909","https://openalex.org/W7135212518","https://openalex.org/W7138316890","https://openalex.org/W7138890450","https://openalex.org/W7148492801","https://openalex.org/W7151544009","https://openalex.org/W7155525302","https://openalex.org/W7161175665","https://openalex.org/W7161681586","https://openalex.org/W7164884022","https://openalex.org/W7165373555","https://openalex.org/W7165385035","https://openalex.org/W7166843749","https://openalex.org/W7166882168","https://openalex.org/W7167604932"],"related_works":["https://openalex.org/W7212688662","https://openalex.org/W4416243461","https://openalex.org/W7165650609","https://openalex.org/W4415329203","https://openalex.org/W7155106007","https://openalex.org/W7138316890","https://openalex.org/W7223061734","https://openalex.org/W7116210591","https://openalex.org/W4416246780","https://openalex.org/W7164516351"],"abstract_inverted_index":{"Voice":[0],"provides":[1],"a":[2,56],"natural":[3],"and":[4,22,68,82,95,113,118,125,173],"immediate":[5],"interface":[6],"for":[7,47,179],"AI":[8],"agents.":[9,182],"Many":[10],"settings":[11,30],"in":[12],"which":[13],"voice":[14,50,181],"agents":[15],"could":[16],"be":[17],"useful,":[18],"including":[19],"meetings,":[20],"households,":[21],"collaborative":[23],"work,":[24],"are":[25,34,135],"inherently":[26],"multi-speaker.":[27],"Supporting":[28],"these":[29],"introduces":[31],"challenges":[32],"that":[33],"largely":[35],"absent":[36],"from":[37,131],"one-on-one":[38],"interaction.":[39,51],"We":[40],"introduce":[41],"the":[42,119,138,155],"Multi-Speaker":[43],"Interaction":[44],"Benchmark":[45],"(MSI-Bench)":[46],"evaluating":[48],"multi-speaker":[49,77,79,83,139],"Each":[52],"test":[53,88],"case":[54],"is":[55],"short":[57],"multi-party":[58],"multi-turn":[59],"audio":[60,140],"scene":[61],"with":[62],"participant":[63],"context,":[64],"expected":[65],"tool":[66],"calls,":[67],"atomic":[69],"rubrics.":[70],"The":[71,99],"benchmark":[72],"targets":[73,178],"three":[74],"capability":[75],"families:":[76],"memory,":[78],"instruction":[80],"following,":[81],"reasoning.":[84],"It":[85],"comprises":[86],"1,152":[87],"cases,":[89,117],"evenly":[90],"split":[91,104],"between":[92],"Mandarin":[93,116],"Chinese":[94],"English":[96,112],"(576":[97],"each).":[98],"strongest":[100,120],"configuration":[101,122],"on":[102,108,123,150],"each":[103],"passes":[105],"all":[106],"rubrics":[107],"only":[109],"66.8%":[110],"of":[111,115],"54.5%":[114],"open-weight":[121,133],"34.0%":[124],"19.3%.":[126],"Failure":[127],"analysis":[128],"separates":[129],"perception":[130],"reasoning:":[132],"models":[134,153],"bottlenecked":[136],"by":[137],"front-end,":[141],"while":[142],"frontier":[143],"systems":[144],"still":[145],"fail":[146],"speaker-scoped":[147,170],"decision":[148,171],"making":[149],"clean":[151],"transcripts---and":[152],"across":[154],"board":[156],"often":[157],"respond":[158],"when":[159],"no":[160],"one":[161],"has":[162],"addressed":[163],"them.":[164],"These":[165],"results":[166],"identify":[167],"speaker-grounded":[168],"perception,":[169],"making,":[172],"conversational":[174],"restraint":[175],"as":[176],"concrete":[177],"future":[180]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-23T00:00:00"}