{"id":"https://openalex.org/W7214110418","doi":"https://doi.org/10.48550/arxiv.2609.25611","title":"Qwen3.8-Omni: Towards Native Omni-Modal Agents","display_name":"Qwen3.8-Omni: Towards Native Omni-Modal Agents","publication_year":2026,"publication_date":"2026-09-22","ids":{"openalex":"https://openalex.org/W7214110418","doi":"https://doi.org/10.48550/arxiv.2609.25611"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.25611","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.25611","pdf_url":"https://arxiv.org/pdf/2609.25611","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.25611","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134080926","display_name":"Qwen Team","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Qwen Team","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5134080926"],"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":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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/T12031","display_name":"Speech and dialogue systems","score":0.0,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/agentic-ai","display_name":"agentic AI","score":0.6039999723434448},{"id":"https://openalex.org/keywords/multimodal-reasoning","display_name":"multimodal reasoning","score":0.6690000295639038},{"id":"https://openalex.org/keywords/long-horizon-planning","display_name":"long-horizon planning","score":0.8920000195503235},{"id":"https://openalex.org/keywords/sparse-mixture-of-experts","display_name":"sparse mixture-of-experts","score":0.8410000205039978},{"id":"https://openalex.org/keywords/long-context-understanding","display_name":"long-context understanding","score":0.7129999995231628},{"id":"https://openalex.org/keywords/video-editing","display_name":"video editing","score":0.675000011920929},{"id":"https://openalex.org/keywords/tool-use","display_name":"tool use","score":0.6909999847412109}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7620999813079834},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.71670001745224},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.6176999807357788},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5712000131607056},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5131999850273132},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.48240000009536743},{"id":"https://openalex.org/C199168358","wikidata":"https://www.wikidata.org/wiki/Q3367000","display_name":"Orchestration","level":3,"score":0.45410001277923584},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.42899999022483826},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3880000114440918},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.36719998717308044},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31299999356269836},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C132829578","wikidata":"https://www.wikidata.org/wiki/Q581151","display_name":"Situated","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C4924752","wikidata":"https://www.wikidata.org/wiki/Q184148","display_name":"Plug-in","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.25049999356269836},{"id":"https://openalex.org/C4441509","wikidata":"https://www.wikidata.org/wiki/Q6418787","display_name":"Multimodal therapy","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.25611","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.25611","pdf_url":"https://arxiv.org/pdf/2609.25611","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.2609.25611","doi":"https://doi.org/10.48550/arxiv.2609.25611","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.25611","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.25611","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.25611","pdf_url":"https://arxiv.org/pdf/2609.25611","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/W7214110418.pdf","grobid_xml":"https://content.openalex.org/works/W7214110418.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416017835","https://openalex.org/W7163190624","https://openalex.org/W7131816660","https://openalex.org/W4415255153","https://openalex.org/W7164311064","https://openalex.org/W7214783416","https://openalex.org/W4402961691","https://openalex.org/W6910636478","https://openalex.org/W7167727990","https://openalex.org/W4417183349"],"abstract_inverted_index":{"We":[0,153],"introduce":[1],"Qwen3.8-Omni-Flash,":[2],"a":[3,43,101,105,145,160,220],"natively":[4,225],"multimodal":[5,10,26,45,88,151,157,186,200,226],"agentic":[6,36,58,204],"model":[7,68],"for":[8,150,182,223],"real-world":[9],"productivity.":[11,152],"Compared":[12],"with":[13],"previous":[14],"omni":[15],"models,":[16],"which":[17],"primarily":[18],"emphasized":[19],"perception":[20],"and":[21,28,64,77,90,113,122,135,167,172,206,212,230],"interaction,":[22],"Qwen3.8-Omni-Flash":[23,195,218],"substantially":[24],"improves":[25],"understanding":[27],"reasoning,":[29,202],"as":[30,32,100,159,219],"well":[31],"performance":[33,198],"on":[34,189],"long-horizon":[35,91,203],"tasks.":[37,66,209],"These":[38,93,210],"capabilities":[39,52,59],"are":[40],"supported":[41],"by":[42],"native":[44,133],"co-training":[46],"strategy":[47],"that":[48,194],"preserves":[49],"strong":[50,197],"text-domain":[51],"while":[53],"facilitating":[54],"the":[55,70,79,130,213],"transfer":[56],"of":[57,75,132,165],"from":[60],"text":[61],"to":[62,82],"audio":[63,112,134],"video":[65,109,114,118,136,207],"The":[67],"inherits":[69],"sparse":[71],"mixture-of-experts":[72],"(MoE)":[73],"architecture":[74],"Qwen3.8-Next":[76],"extends":[78],"context":[80,166],"window":[81],"one":[83],"million":[84],"tokens,":[85],"supporting":[86,108],"long-context":[87],"reasoning":[89],"planning.":[92],"advances":[94],"enable":[95],"integration":[96],"into":[97],"production":[98],"workflows":[99],"primary":[102],"agent":[103,140],"or":[104,119,125],"specialized":[106],"sub-agent,":[107],"editing,":[110],"long-form":[111],"translation,":[115],"music-conditioned":[116],"music":[117],"movie":[120],"generation,":[121],"video-based":[123],"note":[124],"omni-skill":[126],"creation.":[127],"To":[128],"address":[129],"lack":[131],"support":[137,217],"in":[138,228],"existing":[139],"harnesses,":[141],"we":[142,176],"release":[143,177],"Qwen-MM-Plugins,":[144],"lightweight":[146],"open-source":[147,180,215],"plugin":[148],"framework":[149,181],"further":[154],"frame":[155],"real-time":[156,185],"interaction":[158],"system-level":[161],"challenge":[162],"requiring":[163],"orchestration":[164],"memory":[168],"management,":[169],"tool":[170],"use,":[171],"sub-agent":[173],"delegation.":[174],"Accordingly,":[175],"Qwen-Live-Harness,":[178],"an":[179],"building":[183],"responsive,":[184],"agents":[187,227],"based":[188],"Qwen3.8-Omni-Flash.":[190],"Extensive":[191],"evaluations":[192],"demonstrate":[193],"achieves":[196],"across":[199],"understanding,":[201],"execution,":[205],"productivity":[208],"results":[211],"accompanying":[214],"tools":[216],"practical":[221],"foundation":[222],"deploying":[224],"research":[229],"production.":[231]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-24T00:00:00"}