{"id":"https://openalex.org/W7204237976","doi":"https://doi.org/10.48550/arxiv.2608.24134","title":"EgoErrorVQA: Assess Egocentric Comprehension Capabilities through Procedural Errors for Ego-Agentic AI","display_name":"EgoErrorVQA: Assess Egocentric Comprehension Capabilities through Procedural Errors for Ego-Agentic AI","publication_year":2026,"publication_date":"2026-08-25","ids":{"openalex":"https://openalex.org/W7204237976","doi":"https://doi.org/10.48550/arxiv.2608.24134"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2608.24134","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24134","pdf_url":"https://arxiv.org/pdf/2608.24134","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.24134","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137516122","display_name":"Junlong Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Li, Junlong","raw_affiliation_strings":["Department of EEE , The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of EEE , The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030640908","display_name":"Junxi Li","orcid":"https://orcid.org/0000-0002-9428-9751","observed_orcids":["https://orcid.org/0000-0002-9428-9751","https://orcid.org/0009-0009-0974-1319"]},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Li, Junxi","raw_affiliation_strings":["Department of EEE , The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of EEE , The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025795563","display_name":"Jianjun Gao","orcid":"https://orcid.org/0000-0002-7824-5919","observed_orcids":["https://orcid.org/0000-0002-7824-5919","https://orcid.org/0009-0004-9137-2869"]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Gao, Jianjun","raw_affiliation_strings":["School of EEE , Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of EEE , Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123467902","display_name":"Chen Cai","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Cai, Chen","raw_affiliation_strings":["School of EEE , Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of EEE , Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044722301","display_name":"Lap\u2010Pui Chau","orcid":"https://orcid.org/0000-0003-4932-0593","observed_orcids":["https://orcid.org/0000-0003-4932-0593"]},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chau, Lap-Pui","raw_affiliation_strings":["Department of EEE , The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of EEE , The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100784213","display_name":"Yi Wang","orcid":"https://orcid.org/0000-0001-8659-4724","observed_orcids":["https://orcid.org/0000-0001-8659-4724","https://orcid.org/0000-0002-0120-4318"]},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wang, Yi","raw_affiliation_strings":["Department of EEE , The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of EEE , The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":0.9922000169754028,"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":0.9922000169754028,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.003800000064074993,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.0005000000237487257,"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/egocentric-vision","display_name":"egocentric vision","score":0.8379999995231628},{"id":"https://openalex.org/keywords/procedural-errors","display_name":"procedural errors","score":0.9520000219345093},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.9369999766349792},{"id":"https://openalex.org/keywords/visual-question-answering","display_name":"visual question answering","score":0.5870000123977661}],"concepts":[{"id":"https://openalex.org/C164749973","wikidata":"https://www.wikidata.org/wiki/Q18606","display_name":"Procedural memory","level":3,"score":0.7093999981880188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.628600001335144},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.5968000292778015},{"id":"https://openalex.org/C124469403","wikidata":"https://www.wikidata.org/wiki/Q1813993","display_name":"Procedural knowledge","level":3,"score":0.5794000029563904},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5296000242233276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5048999786376953},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.47510001063346863},{"id":"https://openalex.org/C113230428","wikidata":"https://www.wikidata.org/wiki/Q7247149","display_name":"Procedural modeling","level":2,"score":0.4611000120639801},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.39010000228881836},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3855000138282776},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.3702999949455261},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35350000858306885},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32420000433921814},{"id":"https://openalex.org/C120558287","wikidata":"https://www.wikidata.org/wiki/Q1418502","display_name":"Procedural programming","level":4,"score":0.32089999318122864},{"id":"https://openalex.org/C63882131","wikidata":"https://www.wikidata.org/wiki/Q17122954","display_name":"Strengths and weaknesses","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C14156362","wikidata":"https://www.wikidata.org/wiki/Q3235388","display_name":"Descriptive knowledge","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2912999987602234},{"id":"https://openalex.org/C2779149496","wikidata":"https://www.wikidata.org/wiki/Q442100","display_name":"Procedural justice","level":3,"score":0.29100000858306885},{"id":"https://openalex.org/C185874996","wikidata":"https://www.wikidata.org/wiki/Q269699","display_name":"Interdependence","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2632000148296356},{"id":"https://openalex.org/C2777379011","wikidata":"https://www.wikidata.org/wiki/Q938545","display_name":"Implicit learning","level":3,"score":0.25859999656677246},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2533999979496002}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.24134","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24134","pdf_url":"https://arxiv.org/pdf/2608.24134","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.24134","doi":"https://doi.org/10.48550/arxiv.2608.24134","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.24134","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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.24134","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24134","pdf_url":"https://arxiv.org/pdf/2608.24134","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Peace, justice, and strong institutions","score":0.5080863833427429,"id":"https://metadata.un.org/sdg/16"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204237976.pdf","grobid_xml":"https://content.openalex.org/works/W7204237976.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"majority":[1],"of":[2,10,12,29,87,95,133],"our":[3],"everyday":[4,48],"activities":[5],"are":[6,97],"procedural":[7,31,42,62,66,110,127,134],"and":[8,21,84,102,112,145],"consist":[9],"sequences":[11],"interdependent":[13],"steps.":[14],"However,":[15],"existing":[16],"benchmarks":[17],"for":[18,40,47,60],"Visual":[19,22],"Agents":[20],"Language":[23],"Models":[24],"(VLMs)":[25],"overlook":[26],"the":[27,54,78,142],"evaluation":[28,86],"their":[30],"comprehension":[32,63],"ability":[33],"from":[34],"an":[35,119],"egocentric":[36,61],"visual":[37,88],"perspective,":[38],"particularly":[39],"detecting":[41],"errors,":[43],"a":[44,72],"critical":[45],"capability":[46],"assistance.":[49],"To":[50],"bridge":[51],"this":[52],"gap,":[53],"EgoErrorVQA":[55],"task":[56],"is":[57],"firstly":[58],"proposed":[59],"with":[64],"explicit":[65],"errors":[67,111],"modeling.":[68],"Besides,":[69],"we":[70,116],"develop":[71],"user-friendly":[73],"evaluator":[74],"agent":[75],"based":[76],"on":[77,149],"Agent2Agent":[79],"(A2A)":[80],"protocol,":[81],"enabling":[82],"rigorous":[83],"standardized":[85],"agents":[89],"through":[90],"VQA-based":[91],"interaction.":[92],"A":[93],"range":[94],"models":[96],"evaluated":[98],"using":[99],"both":[100],"open-ended":[101],"multiple-choice":[103],"questions,":[104],"revealing":[105],"persistent":[106],"weaknesses":[107],"in":[108],"handling":[109],"error":[113],"types.":[114],"Moreover,":[115],"introduce":[117],"Ego-ADR,":[118],"Adaptive":[120],"Decoupled":[121],"Reasoning":[122],"framework":[123],"that":[124],"decouples":[125],"complex":[126],"reasoning":[128],"to":[129],"enhance":[130],"models'":[131],"understanding":[132],"errors.":[135],"It":[136],"achieves":[137],"consistent":[138],"performance":[139],"gains":[140],"over":[141],"selected":[143],"baselines":[144],"attains":[146],"state-of-the-art":[147],"results":[148],"several":[150],"metrics":[151],"under":[152],"comparable":[153],"settings.":[154],"Code:":[155],"https://github.com/z1oong/EgoErrorVQA":[156]},"counts_by_year":[],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2026-08-27T00:00:00"}
