{"id":"https://openalex.org/W7221751965","doi":"https://doi.org/10.48550/arxiv.2610.14772","title":"How Should a Camera-First AI Agent Work?","display_name":"How Should a Camera-First AI Agent Work?","publication_year":2026,"publication_date":"2026-10-10","ids":{"openalex":"https://openalex.org/W7221751965","doi":"https://doi.org/10.48550/arxiv.2610.14772"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.14772","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.14772","pdf_url":"https://arxiv.org/pdf/2610.14772","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":"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/2610.14772","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140680954","display_name":"Xiaofan Wu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Xiaofan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5158738417","display_name":"Xi Zeng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Xi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140672743","display_name":"Miaoxia Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Miaoxia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140615506","display_name":"Peishan Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Peishan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5158748790","display_name":"Shuyan Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Shuyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5158722762","display_name":"Chen Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5158814322","display_name":"Xiaohan Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xiaohan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5158819419","display_name":"Wanling Xu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Wanling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140674869","display_name":"Jiyun Yao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Jiyun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140586953","display_name":"Hanyong Zhong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong, Hanyong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5158801884","display_name":"Jiahao Zhu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Jiahao","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":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":0.6044999957084656,"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":0.6044999957084656,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.11429999768733978,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.06889999657869339,"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/visual-tracking","display_name":"visual object tracking","score":0.3970000147819519},{"id":"https://openalex.org/keywords/mot17","display_name":"MOT17","score":0.6299999952316284},{"id":"https://openalex.org/keywords/multimodal-models","display_name":"multimodal models","score":0.5130000114440918},{"id":"https://openalex.org/keywords/tool-use","display_name":"tool use","score":0.39100000262260437},{"id":"https://openalex.org/keywords/working-memory","display_name":"working memory","score":0.39899998903274536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7139999866485596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5242000222206116},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.519599974155426},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5033000111579895},{"id":"https://openalex.org/C2776946740","wikidata":"https://www.wikidata.org/wiki/Q358652","display_name":"Deliberation","level":3,"score":0.49059998989105225},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.46140000224113464},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.44760000705718994},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.43619999289512634},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.38519999384880066},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.38190001249313354},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.37229999899864197},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.36480000615119934},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.32350000739097595},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.3160000145435333},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.29429998993873596},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C193611912","wikidata":"https://www.wikidata.org/wiki/Q4677596","display_name":"Active vision","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C88576662","wikidata":"https://www.wikidata.org/wiki/Q18646","display_name":"Episodic memory","level":3,"score":0.28540000319480896},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2759999930858612},{"id":"https://openalex.org/C121375916","wikidata":"https://www.wikidata.org/wiki/Q936559","display_name":"Principle of compositionality","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.25870001316070557},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.2531000077724457},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.2513999938964844},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.14772","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.14772","pdf_url":"https://arxiv.org/pdf/2610.14772","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.14772","doi":"https://doi.org/10.48550/arxiv.2610.14772","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.14772","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:2610.14772","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.14772","pdf_url":"https://arxiv.org/pdf/2610.14772","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":"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/W7221751965.pdf","grobid_xml":"https://content.openalex.org/works/W7221751965.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W2097856935","https://openalex.org/W2119885245","https://openalex.org/W2147527908","https://openalex.org/W2325237720","https://openalex.org/W2581624817","https://openalex.org/W2610140147","https://openalex.org/W2794288488","https://openalex.org/W3168124404","https://openalex.org/W4306886919","https://openalex.org/W4376122773","https://openalex.org/W4393967974","https://openalex.org/W4396914181","https://openalex.org/W4400141368","https://openalex.org/W4403883071","https://openalex.org/W4409051416","https://openalex.org/W4415800788","https://openalex.org/W7151536174"],"related_works":["https://openalex.org/W7222120372","https://openalex.org/W7161314149","https://openalex.org/W7131082765","https://openalex.org/W6910636478","https://openalex.org/W7130591119","https://openalex.org/W7167727990","https://openalex.org/W7167923505","https://openalex.org/W7155081196","https://openalex.org/W7162780049","https://openalex.org/W7166526890"],"abstract_inverted_index":{"Camera-first":[0],"agents":[1,20],"must":[2],"act":[3],"on":[4,159],"the":[5,14,38,65,74,80,108,157,169],"visual":[6,48],"world":[7],"as":[8,69,87],"it":[9,140],"unfolds.":[10],"We":[11,84,117,155],"argue":[12],"that":[13,72,132],"central":[15],"obstacle":[16],"for":[17,41],"future":[18],"camera-first":[19],"is":[21,82,141],"not":[22],"recognition":[23],"ability":[24],"-":[25,44],"multimodal":[26],"models":[27],"(vision-language":[28],"and":[29,36,56,91,114,146,167,183],"live/streaming":[30],"alike)":[31],"generalize":[32],"well":[33],"through":[34],"language":[35],"remain":[37],"right":[39],"tool":[40],"semantic":[42],"reasoning":[43,70,104],"but":[45],"time.":[46],"Many":[47],"targets":[49],"are":[50,54],"ephemeral:":[51],"they":[52],"appear,":[53],"query-relevant,":[55],"leave":[57],"within":[58],"a":[59,76,92,97,102,119,134,147,164,177],"short":[60,178],"window.":[61],"Binding":[62],"memory":[63,99,138],"to":[64,136],"same":[66],"end-to-end":[67],"path":[68],"means":[71],"by":[73],"time":[75],"monolithic":[77],"pipeline":[78],"completes,":[79],"evidence":[81,192],"gone.":[83],"formalize":[85],"this":[86],"Ephemeral-Target":[88],"Interaction":[89],"(ETI)":[90],"Perceptual":[93],"Deadline":[94],"Contract":[95],"separating":[96],"hard":[98],"deadline":[100],"from":[101,172],"soft":[103],"deadline,":[105],"grounded":[106],"in":[107,144],"bounded,":[109,124],"passive":[110],"nature":[111],"of":[112],"sensory":[113],"working":[115],"memory.":[116],"propose":[118],"two-deadline":[120],"architecture:":[121],"an":[122,128,184],"always-on,":[123],"non-semantic":[125],"fast":[126],"path;":[127],"active":[129],"remembering":[130],"mechanism":[131],"commits":[133],"moment":[135],"durable":[137],"before":[139],"overwritten":[142],"(event-driven":[143],"v1);":[145],"deferred":[148],"deliberation":[149],"layer":[150],"(multimodal":[151],"model":[152],"+":[153],"tools).":[154],"instantiate":[156],"contract":[158],"real":[160],"MOT17":[161],"track":[162],"windows,":[163],"consistency":[165],"check,":[166],"calibrate":[168],"single-path":[170],"baseline":[171],"measured":[173],"frontier-model":[174],"latency:":[175],"even":[176],"answer":[179],"takes":[180],"1.2-9.3":[181],"s,":[182],"agentic":[185],"identify-and-search":[186],"longer.":[187],"Answers":[188],"can":[189],"be":[190,194],"late;":[191],"cannot":[193],"missed.":[195]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-15T00:00:00"}