{"id":"https://openalex.org/W4415308780","doi":"https://doi.org/10.1109/iccv51701.2025.01882","title":"LVAgent: Long Video Understanding by Multi-Round Dynamical Collaboration of MLLM Agents","display_name":"LVAgent: Long Video Understanding by Multi-Round Dynamical Collaboration of MLLM Agents","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415308780","doi":"https://doi.org/10.1109/iccv51701.2025.01882"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01882","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01882","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.10200","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101644353","display_name":"Boyu Chen","orcid":"https://orcid.org/0000-0003-1165-1338"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boyu Chen","raw_affiliation_strings":["Shenzhen Key Lab of Computer Vision and Pattern Recognition, Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Key Lab of Computer Vision and Pattern Recognition, Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120047207","display_name":"Zhengrong Yue","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/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengrong Yue","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Siran Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siran Chen","raw_affiliation_strings":["Shenzhen Key Lab of Computer Vision and Pattern Recognition, Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Key Lab of Computer Vision and Pattern Recognition, Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056285519","display_name":"Zikang Wang","orcid":"https://orcid.org/0000-0003-1406-1237"},"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/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zikang Wang","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100356161","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0003-3800-3533"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["Institute for AI Industry Research (AIR), Tsinghua University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for AI Industry Research (AIR), Tsinghua University,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100432643","display_name":"Peng Li","orcid":"https://orcid.org/0000-0001-8780-5554"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Li","raw_affiliation_strings":["Institute for AI Industry Research (AIR), Tsinghua University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for AI Industry Research (AIR), Tsinghua University,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100335705","display_name":"Yali Wang","orcid":"https://orcid.org/0000-0002-2999-7428"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yali Wang","raw_affiliation_strings":["Shenzhen Key Lab of Computer Vision and Pattern Recognition, Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Key Lab of Computer Vision and Pattern Recognition, Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210145761"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14956358,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20237","last_page":"20246"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9096999764442444,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9096999764442444,"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/key","display_name":"Key (lock)","score":0.6100000143051147},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5727999806404114},{"id":"https://openalex.org/keywords/mainstream","display_name":"Mainstream","score":0.4814999997615814},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4706000089645386},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.3619999885559082},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.32919999957084656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8335999846458435},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6100000143051147},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5727999806404114},{"id":"https://openalex.org/C2777617010","wikidata":"https://www.wikidata.org/wiki/Q18957","display_name":"Mainstream","level":2,"score":0.4814999997615814},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4706000089645386},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.3619999885559082},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33550000190734863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3328999876976013},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.328900009393692},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.328000009059906},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2922999858856201},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.2696000039577484},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2522999942302704}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01882","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01882","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.10200","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.10200","pdf_url":"https://arxiv.org/pdf/2503.10200","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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.2503.10200","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.10200","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.10200","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.10200","pdf_url":"https://arxiv.org/pdf/2503.10200","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Existing":[0],"MLLMs":[1],"encounter":[2],"significant":[3],"challenges":[4],"in":[5,25,47,71,141,188],"modeling":[6],"the":[7,61,89,114,148,169,189],"temporal":[8,118],"context":[9],"within":[10],"long":[11,27,44,55,72,110,128,190,204],"videos.":[12],"Currently,":[13],"mainstream":[14,203],"Agent-based":[15],"methods":[16],"use":[17],"external":[18],"tools":[19],"to":[20,52,92,112],"assist":[21],"a":[22,34,40],"single":[23],"MLLM":[24,36,69,165],"answering":[26],"video":[28,56,73,129,191,205],"questions.":[29],"Despite":[30],"such":[31],"tool-based":[32],"support,":[33],"solitary":[35],"still":[37],"offers":[38],"only":[39],"partial":[41],"understanding":[42,192,206],"of":[43,68,78,116,144,164,199],"videos,":[45],"resulting":[46],"limited":[48],"performance.":[49],"In":[50],"order":[51],"better":[53],"address":[54],"tasks,":[57],"we":[58],"introduce":[59],"LVAgent,":[60],"first":[62,170],"framework":[63],"enabling":[64],"multi-round":[65,161],"dynamic":[66,152],"collaboration":[67,163],"agents":[70,87,155],"understanding.":[74],"Our":[75,194],"method":[76,173],"consists":[77],"four":[79,202],"key":[80],"steps:":[81],"1)":[82],"Selection:":[83],"We":[84,103,136],"pre-select":[85],"appropriate":[86],"from":[88],"model":[90],"library":[91],"form":[93],"optimal":[94],"agent":[95,149,171],"teams":[96],"based":[97],"on":[98,201,214],"different":[99],"tasks.":[100,193,207],"2)":[101],"Perception:":[102],"design":[104],"an":[105,197],"effective":[106],"retrieval":[107],"scheme":[108],"for":[109,151],"videos":[111],"improve":[113],"coverage":[115],"critical":[117],"segments":[119],"while":[120],"maintaining":[121],"computational":[122],"efficiency.":[123],"3)":[124],"Action:":[125],"Agents":[126],"answer":[127],"questions":[130],"and":[131,146,181,186],"exchange":[132],"reasons.":[133],"4)":[134],"Reflection:":[135],"evaluate":[137],"each":[138,142],"agent's":[139],"performance":[140],"round":[143],"discussion":[145],"optimize":[147],"team":[150],"collaboration.":[153],"The":[154],"iteratively":[156],"refine":[157],"their":[158],"answers":[159],"by":[160,212],"dynamical":[162],"agents.":[166],"LVAgent":[167,195,209],"is":[168,217],"system":[172],"that":[174],"outperforms":[175],"all":[176],"closed-source":[177],"models":[178,183],"(like":[179,184],"GPT-4o)":[180],"open-source":[182],"InternVL-2.5":[185],"Qwen2-VL)":[187],"achieves":[196],"accuracy":[198,211],"80\\%":[200],"Notably,":[208],"improves":[210],"13.3\\%":[213],"LongVideoBench.":[215],"Code":[216],"available":[218],"at":[219],"https://github.com/64327069/LVAgent.":[220]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-18T00:00:00"}