{"id":"https://openalex.org/W7133329518","doi":"https://doi.org/10.48550/arxiv.2603.01104","title":"Egocentric Co-Pilot: Web-Native Smart-Glasses Agents for Assistive Egocentric AI","display_name":"Egocentric Co-Pilot: Web-Native Smart-Glasses Agents for Assistive Egocentric AI","publication_year":2026,"publication_date":"2026-03-01","ids":{"openalex":"https://openalex.org/W7133329518","doi":"https://doi.org/10.48550/arxiv.2603.01104"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.01104","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.01104","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.01104","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127948246","display_name":"Sicheng Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yang, Sicheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127988174","display_name":"Yukai Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Yukai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128002251","display_name":"Weitong Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cai, Weitong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077534756","display_name":"Shitong Sun","orcid":"https://orcid.org/0000-0003-1825-655X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Shitong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017333905","display_name":"Fengyi Fang","orcid":"https://orcid.org/0000-0002-1082-8368"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fang, Fengyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127992554","display_name":"You He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, You","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007955766","display_name":"Yiqiao Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Yiqiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127994117","display_name":"Jiankang Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deng, Jiankang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128004026","display_name":"Hang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Hang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123229815","display_name":"Jifei Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Jifei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128023421","display_name":"Zhensong Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zhensong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5127948246"],"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":0.5882999897003174,"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":0.5882999897003174,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.11490000039339066,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.039400000125169754,"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/context","display_name":"Context (archaeology)","score":0.5526999831199646},{"id":"https://openalex.org/keywords/toolbox","display_name":"Toolbox","score":0.4106000065803528},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.39629998803138733},{"id":"https://openalex.org/keywords/everyday-life","display_name":"Everyday life","score":0.3538999855518341},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.3490000069141388},{"id":"https://openalex.org/keywords/gaze","display_name":"Gaze","score":0.34380000829696655},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.3418000042438507},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.3386000096797943},{"id":"https://openalex.org/keywords/handshake","display_name":"Handshake","score":0.3357999920845032},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.33480000495910645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.732200026512146},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.620199978351593},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5526999831199646},{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.4106000065803528},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.39629998803138733},{"id":"https://openalex.org/C2779018934","wikidata":"https://www.wikidata.org/wiki/Q1129653","display_name":"Everyday life","level":2,"score":0.3538999855518341},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.3490000069141388},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3418000042438507},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.3386000096797943},{"id":"https://openalex.org/C2778000800","wikidata":"https://www.wikidata.org/wiki/Q830043","display_name":"Handshake","level":3,"score":0.3357999920845032},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.3328000009059906},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C65603577","wikidata":"https://www.wikidata.org/wiki/Q3427877","display_name":"Web resource","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.31200000643730164},{"id":"https://openalex.org/C2781368080","wikidata":"https://www.wikidata.org/wiki/Q501688","display_name":"Context awareness","level":3,"score":0.3075000047683716},{"id":"https://openalex.org/C59046462","wikidata":"https://www.wikidata.org/wiki/Q181319","display_name":"Scrolling","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C201638289","wikidata":"https://www.wikidata.org/wiki/Q457396","display_name":"Ambient intelligence","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.29429998993873596},{"id":"https://openalex.org/C150594956","wikidata":"https://www.wikidata.org/wiki/Q1334829","display_name":"Wearable computer","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2824000120162964},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27549999952316284},{"id":"https://openalex.org/C160174412","wikidata":"https://www.wikidata.org/wiki/Q873806","display_name":"Thumbnail","level":3,"score":0.2632000148296356},{"id":"https://openalex.org/C2778121785","wikidata":"https://www.wikidata.org/wiki/Q781083","display_name":"Augmentative and alternative communication","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C152223200","wikidata":"https://www.wikidata.org/wiki/Q3055471","display_name":"Smart environment","level":3,"score":0.2554999887943268},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.01104","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.01104","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.01104","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.01104","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.8318907022476196,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"What":[0],"if":[1],"accessing":[2],"the":[3,38],"web":[4,39,76,245],"did":[5],"not":[6],"require":[7],"a":[8,10,52,63,70,103,109,127,139,185,213,239],"screen,":[9],"stable":[11],"desk,":[12],"or":[13,26,179],"even":[14],"free":[15],"hands?":[16],"For":[17],"people":[18,255],"navigating":[19],"crowded":[20],"cities,":[21],"living":[22],"with":[23,33,85],"low":[24],"vision,":[25],"experiencing":[27],"cognitive":[28],"overload,":[29],"smart":[30,59,143,189],"glasses":[31,60,144,190],"coupled":[32],"AI":[34],"agents":[35,246],"could":[36],"turn":[37],"into":[40,119,138],"an":[41,151],"always-on":[42,244],"assistive":[43],"layer":[44,113],"over":[45,97],"daily":[46],"life.":[47,223],"We":[48,122],"present":[49],"Egocentric":[50,236],"Co-Pilot,":[51],"web-native":[53,228],"neuro-symbolic":[54],"framework":[55],"that":[56,207,247],"runs":[57],"on":[58,173,188],"and":[61,75,94,117,125,135,145,161,169,175,184,195,231,251],"uses":[62],"Large":[64],"Language":[65],"Model":[66],"(LLM)":[67],"to":[68,89],"orchestrate":[69],"toolbox":[71],"of":[72,166],"perception,":[73],"reasoning,":[74],"tools.":[77],"An":[78],"egocentric":[79,181,209,262],"reasoning":[80],"core":[81],"combines":[82],"Temporal":[83],"Chain-of-Thought":[84],"Hierarchical":[86],"Context":[87],"Compression":[88],"support":[90,96,248],"long-horizon":[91],"question":[92],"answering":[93],"decision":[95],"continuous":[98],"first-person":[99],"video,":[100,134],"far":[101],"beyond":[102],"single":[104],"model's":[105],"context":[106],"window.":[107],"Additionally,":[108],"lightweight":[110],"multimodal":[111],"intent":[112],"maps":[114],"noisy":[115],"speech":[116],"gaze":[118],"structured":[120],"commands.":[121],"further":[123],"implement":[124],"evaluate":[126],"cloud-native":[128],"WebRTC":[129],"pipeline":[130],"integrating":[131],"streaming":[132],"speech,":[133],"control":[136],"messages":[137],"unified":[140],"channel":[141],"for":[142,242,254],"browsers.":[146],"In":[147],"parallel,":[148],"we":[149],"deploy":[150],"on-premise":[152],"WebSocket":[153],"baseline,":[154],"exposing":[155],"concrete":[156,240],"trade-offs":[157],"between":[158],"local":[159],"inference":[160],"cloud":[162],"offloading":[163],"in":[164,221,227],"terms":[165],"latency,":[167],"mobility,":[168],"resource":[170],"use.":[171],"Experiments":[172],"Egolife":[174],"HD-EPIC":[176],"demonstrate":[177],"competitive":[178],"state-of-the-art":[180],"QA":[182],"performance,":[183],"human-in-the-loop":[186],"study":[187],"shows":[191],"higher":[192],"task":[193],"completion":[194],"user":[196],"satisfaction":[197],"than":[198],"leading":[199],"commercial":[200],"baselines.":[201],"Taken":[202],"together,":[203],"these":[204],"results":[205],"indicate":[206],"web-connected":[208],"co-pilots":[210],"can":[211],"be":[212],"practical":[214],"path":[215],"toward":[216],"more":[217],"accessible,":[218],"context-aware":[219],"assistance":[220],"everyday":[222],"By":[224],"grounding":[225],"operation":[226],"communication":[229],"primitives":[230],"modular,":[232],"auditable":[233],"tool":[234],"use,":[235],"Co-Pilot":[237],"offers":[238],"blueprint":[241],"assistive,":[243],"education,":[249],"accessibility,":[250],"social":[252],"inclusion":[253],"who":[256],"may":[257],"benefit":[258],"most":[259],"from":[260],"contextual,":[261],"AI.":[263]},"counts_by_year":[],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2026-03-04T00:00:00"}
