{"id":"https://openalex.org/W7161559596","doi":"https://doi.org/10.48550/arxiv.2605.16079","title":"VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation","display_name":"VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation","publication_year":2026,"publication_date":"2026-05-15","ids":{"openalex":"https://openalex.org/W7161559596","doi":"https://doi.org/10.48550/arxiv.2605.16079"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.16079","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.16079","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.16079","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136453992","display_name":"Yiming Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Yiming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136381150","display_name":"Yu Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136437368","display_name":"Wenxuan Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Wenxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136362188","display_name":"Zhen Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fang, Zhen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121302270","display_name":"Qing Miao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miao, Qing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125685101","display_name":"Qisheng Su","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Su, Qisheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136450640","display_name":"Jiawei Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Jiawei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066854056","display_name":"Jiayin Cai","orcid":"https://orcid.org/0009-0007-8903-212X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cai, Jiayin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136445421","display_name":"Lin Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136397515","display_name":"Zehui Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Zehui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101318495","display_name":"Yukun Qi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi, Yukun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136424336","display_name":"Yao Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136395050","display_name":"Xiaolong Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Xiaolong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136430679","display_name":"Feng Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Feng","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":false,"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":0.9933000206947327,"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":0.9933000206947327,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.00139999995008111,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0010999999940395355,"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/pipeline","display_name":"Pipeline (software)","score":0.5902000069618225},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5825999975204468},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5684000253677368},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.40450000762939453},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3921999931335449},{"id":"https://openalex.org/keywords/transferability","display_name":"Transferability","score":0.38420000672340393},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.3303999900817871},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.31610000133514404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8137999773025513},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5902000069618225},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5825999975204468},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5684000253677368},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5590999722480774},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.40450000762939453},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3921999931335449},{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.38420000672340393},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3571000099182129},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.3303999900817871},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.3057999908924103},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3012999892234802},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2872999906539917},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.28049999475479126},{"id":"https://openalex.org/C2988167200","wikidata":"https://www.wikidata.org/wiki/Q16885149","display_name":"Online video","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.16079","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.16079","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":"doi:10.48550/arxiv.2605.16079","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.16079","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Vision-Language":[1],"Models":[2],"(LVLMs)":[3],"have":[4],"shown":[5],"significant":[6],"progress":[7],"in":[8,16,48],"video":[9,93,105,117,136,157,175,194],"understanding,":[10],"yet":[11],"they":[12],"face":[13],"substantial":[14],"challenges":[15],"tasks":[17],"requiring":[18],"precise":[19,42],"spatiotemporal":[20],"localization":[21],"at":[22],"the":[23,72,109,146],"instance":[24],"level.":[25],"Existing":[26],"methods":[27],"primarily":[28],"rely":[29],"on":[30,119,173,192],"text":[31],"prompts":[32,38],"for":[33,91],"human-model":[34],"interaction,":[35],"but":[36],"these":[37,83],"struggle":[39],"to":[40,75,111,130],"provide":[41],"spatial":[43],"and":[44,114,141,151,185,200],"temporal":[45],"references,":[46],"resulting":[47],"poor":[49],"user":[50],"experience.":[51],"Furthermore,":[52],"current":[53],"approaches":[54],"typically":[55],"decouple":[56],"visual":[57,68,79,96],"perception":[58,143],"from":[59],"language":[60,65],"reasoning,":[61],"centering":[62],"reasoning":[63,102],"around":[64],"rather":[66],"than":[67],"content,":[69],"which":[70],"limits":[71],"model's":[73],"ability":[74],"proactively":[76,112],"perceive":[77,113],"fine-grained":[78],"evidence.":[80],"To":[81],"address":[82],"challenges,":[84],"we":[85],"propose":[86],"VideoSeeker,":[87],"a":[88,123,155],"novel":[89],"paradigm":[90],"instance-level":[92,104,135,174],"understanding":[94,106,158,176,195],"through":[95],"prompts.":[97],"VideoSeeker":[98],"seamlessly":[99],"integrates":[100],"agentic":[101],"with":[103],"tasks,":[107,177],"enabling":[108],"model":[110,147,164],"retrieve":[115],"relevant":[116,198],"segments":[118],"demand.":[120],"We":[121,138],"construct":[122],"four-stage":[124],"fully":[125],"automated":[126],"data":[127],"synthesis":[128],"pipeline":[129],"efficiently":[131],"generate":[132],"large-scale,":[133],"high-quality":[134],"data.":[137],"internalize":[139],"tool-calling":[140],"proactive":[142],"capabilities":[144],"into":[145],"via":[148],"cold-start":[149],"supervision":[150],"RL":[152],"training,":[153],"building":[154],"powerful":[156,179],"model.":[159],"Experiments":[160],"demonstrate":[161],"that":[162],"our":[163],"achieves":[165],"an":[166],"average":[167],"improvement":[168],"of":[169],"+13.7%":[170],"over":[171],"baselines":[172],"surpassing":[178],"closed-source":[180],"models":[181],"such":[182],"as":[183],"GPT-4o":[184],"Gemini-2.5-Pro,":[186],"while":[187],"also":[188],"showing":[189],"effective":[190],"transferability":[191],"general":[193],"benchmarks.":[196],"The":[197],"datasets":[199],"code":[201],"will":[202],"be":[203],"released":[204],"publicly.":[205]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-19T00:00:00"}