{"id":"https://openalex.org/W7165191037","doi":"https://doi.org/10.48550/arxiv.2606.19341","title":"Native Active Perception as Reasoning for Omni-Modal Understanding","display_name":"Native Active Perception as Reasoning for Omni-Modal Understanding","publication_year":2026,"publication_date":"2026-06-17","ids":{"openalex":"https://openalex.org/W7165191037","doi":"https://doi.org/10.48550/arxiv.2606.19341"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.19341","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.19341","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.2606.19341","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009501136","display_name":"Zhenghao Xing","orcid":"https://orcid.org/0009-0007-5054-2499"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xing, Zhenghao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089618727","display_name":"Ruiyang Xu","orcid":"https://orcid.org/0000-0002-8521-3181"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Ruiyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138950781","display_name":"Yuxuan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yuxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138868858","display_name":"Jinzheng He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Jinzheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138899425","display_name":"Ziyang Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Ziyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038504160","display_name":"Qize Yang","orcid":"https://orcid.org/0000-0002-8884-7665"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Qize","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138859012","display_name":"Yunfei Chu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chu, Yunfei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138960328","display_name":"Jin Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Jin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138907701","display_name":"Junyang Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Junyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138955151","display_name":"Chi-Wing Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Chi-Wing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138835626","display_name":"Pheng-Ann Heng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heng, Pheng-Ann","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":0.6958000063896179,"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":0.6958000063896179,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.05469999834895134,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.03449999913573265,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5523999929428101},{"id":"https://openalex.org/keywords/operationalization","display_name":"Operationalization","score":0.516700029373169},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4083999991416931},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4081999957561493},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.3497999906539917},{"id":"https://openalex.org/keywords/active-vision","display_name":"Active vision","score":0.33809998631477356}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7052000164985657},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5763000249862671},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5523999929428101},{"id":"https://openalex.org/C9354725","wikidata":"https://www.wikidata.org/wiki/Q286017","display_name":"Operationalization","level":2,"score":0.516700029373169},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4767000079154968},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4083999991416931},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4081999957561493},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C193611912","wikidata":"https://www.wikidata.org/wiki/Q4677596","display_name":"Active vision","level":2,"score":0.33809998631477356},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.3246999979019165},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.28040000796318054},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C166052673","wikidata":"https://www.wikidata.org/wiki/Q83021","display_name":"Empirical evidence","level":2,"score":0.25600001215934753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.19341","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.19341","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.2606.19341","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.19341","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Passive":[0],"models":[1],"for":[2],"long":[3],"video":[4,25,45,57,85],"understanding":[5,58],"typically":[6],"rely":[7,34],"on":[8,35,173],"a":[9,60,75],"\"watch-it-all\"":[10],"paradigm,":[11],"processing":[12],"frames":[13],"uniformly":[14],"regardless":[15],"of":[16,145,152],"query":[17],"difficulty,":[18],"causing":[19],"computational":[20],"cost":[21,41],"to":[22,69,96,125],"grow":[23],"with":[24,44,105,114],"duration.":[26,86],"Although":[27],"interactive":[28],"frameworks":[29],"have":[30],"emerged,":[31],"they":[32],"often":[33],"global":[36],"pre-scanning,":[37],"and":[38,109],"their":[39],"context":[40],"still":[42],"scales":[43],"length.":[46],"We":[47],"propose":[48],"OmniAgent,":[49],"the":[50,143,150,179],"first":[51],"native":[52,98],"omni-modal":[53],"agent":[54,177],"that":[55,164],"formulates":[56],"as":[59,142],"POMDP-based":[61],"iterative":[62],"Observation-Thought-Action":[63],"cycle.":[64],"OmniAgent":[65,134,165],"executes":[66],"on-demand":[67],"actions":[68],"selectively":[70],"distill":[71],"audio-visual":[72],"cues":[73],"into":[74],"persistent":[76],"textual":[77],"memory,":[78],"effectively":[79],"decoupling":[80],"reasoning":[81,146],"complexity":[82],"from":[83],"raw":[84],"To":[87],"operationalize":[88],"this,":[89],"we":[90],"introduce":[91],"(1)":[92],"Agentic":[93,111],"Supervised":[94],"Fine-Tuning":[95],"bootstrap":[97],"active":[99,153],"perception":[100],"via":[101],"best-of-N":[102],"trajectory":[103],"synthesis":[104],"dual-stage":[106],"quality":[107],"control,":[108],"(2)":[110],"Reinforcement":[112],"Learning":[113],"TAURA":[115],"(Turn-aware":[116],"Adaptive":[117],"Uncertainty":[118],"Rescaled":[119],"Advantage),":[120],"which":[121],"leverages":[122],"turn-level":[123],"entropy":[124],"steer":[126],"credit":[127],"assignment":[128],"toward":[129],"pivotal":[130],"discovery":[131],"turns.":[132],"Crucially,":[133],"exhibits":[135],"positive":[136],"test-time":[137],"scaling,":[138],"where":[139],"performance":[140,168],"improves":[141],"number":[144],"turns":[147],"increases,":[148],"validating":[149],"efficacy":[151],"perception.":[154],"Empirical":[155],"results":[156],"across":[157],"ten":[158],"benchmarks":[159],"(e.g.,":[160],"VideoMME,":[161],"LVBench)":[162],"demonstrate":[163],"achieves":[166],"state-of-the-art":[167],"among":[169],"open-source":[170],"models.":[171],"Notably,":[172],"LVBench,":[174],"our":[175],"7B":[176],"outperforms":[178],"10$\\times$":[180],"larger":[181],"Qwen2.5-VL-72B":[182],"(50.5%":[183],"vs.":[184],"47.3%).":[185]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-19T00:00:00"}