{"id":"https://openalex.org/W4414971197","doi":"https://doi.org/10.1109/access.2025.3649182","title":"The Artificial Intelligence Cognitive Examination: A Survey on the Evolution of Multimodal Evaluation From Recognition to Reasoning","display_name":"The Artificial Intelligence Cognitive Examination: A Survey on the Evolution of Multimodal Evaluation From Recognition to Reasoning","publication_year":2025,"publication_date":"2025-12-29","ids":{"openalex":"https://openalex.org/W4414971197","doi":"https://doi.org/10.1109/access.2025.3649182"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3649182","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3649182","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3649182","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119911793","display_name":"Mayank Ravishankara","orcid":null},"institutions":[{"id":"https://openalex.org/I4210121988","display_name":"Film Independent","ror":"https://ror.org/036cy3843","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210121988"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mayank Ravishankara","raw_affiliation_strings":["Independent Researcher, San Francisco, CA, USA"],"affiliations":[{"raw_affiliation_string":"Independent Researcher, San Francisco, CA, USA","institution_ids":["https://openalex.org/I4210121988"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5119911794","display_name":"Varindra V. Persad Maharaj","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Varindra V. Persad Maharaj","raw_affiliation_strings":["Independent Researcher, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Independent Researcher, Sunnyvale, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5119911793"],"corresponding_institution_ids":["https://openalex.org/I4210121988"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14190067,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"2690","last_page":"2725"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.4894999861717224,"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"}},"topics":[{"id":"https://openalex.org/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.4894999861717224,"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/visual-reasoning","display_name":"Visual reasoning","score":0.6014000177383423},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5372999906539917},{"id":"https://openalex.org/keywords/commonsense-reasoning","display_name":"Commonsense reasoning","score":0.4893999993801117},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.46320000290870667},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.45910000801086426},{"id":"https://openalex.org/keywords/framing","display_name":"Framing (construction)","score":0.39719998836517334},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.39489999413490295},{"id":"https://openalex.org/keywords/chart","display_name":"Chart","score":0.38449999690055847}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7404000163078308},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.6014000177383423},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5827999711036682},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5372999906539917},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.4893999993801117},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.46320000290870667},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.45910000801086426},{"id":"https://openalex.org/C169087156","wikidata":"https://www.wikidata.org/wiki/Q2131593","display_name":"Framing (construction)","level":2,"score":0.39719998836517334},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.39489999413490295},{"id":"https://openalex.org/C190812933","wikidata":"https://www.wikidata.org/wiki/Q28923","display_name":"Chart","level":2,"score":0.38449999690055847},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3776000142097473},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.36970001459121704},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C43540301","wikidata":"https://www.wikidata.org/wiki/Q689971","display_name":"Paradigm shift","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.323199987411499},{"id":"https://openalex.org/C36964233","wikidata":"https://www.wikidata.org/wiki/Q7920942","display_name":"Verbal reasoning","level":3,"score":0.29269999265670776},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C5065155","wikidata":"https://www.wikidata.org/wiki/Q1185775","display_name":"Frame problem","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26579999923706055},{"id":"https://openalex.org/C2778403875","wikidata":"https://www.wikidata.org/wiki/Q20312394","display_name":"Adversarial machine learning","level":3,"score":0.2639999985694885},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C105409693","wikidata":"https://www.wikidata.org/wiki/Q5937824","display_name":"Human intelligence","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.25540000200271606},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2549000084400177}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/access.2025.3649182","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3649182","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2510.04141","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.04141","pdf_url":"https://arxiv.org/pdf/2510.04141","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.04141","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.04141","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:10.1109/access.2025.3649182","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3649182","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"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":{"This":[0,55],"survey":[1,119],"paper":[2],"chronicles":[3],"the":[4,26,60,74,77,82,86,120,143,156,182],"evolution":[5,56],"of":[6,18,62,81,123,146,163,184,192,199],"evaluation":[7,186],"in":[8,114,204],"multimodal":[9,135],"artificial":[10],"intelligence":[11],"(AI),":[12],"framing":[13],"it":[14,53],"as":[15,93,109],"a":[16,30,41,173,190,195],"progression":[17],"increasingly":[19],"sophisticated":[20],"\"cognitive":[21],"examinations.\"":[22],"We":[23,72,117,153,179],"argue":[24],"that":[25,38,48,181],"field":[27],"is":[28,57,187],"undergoing":[29],"paradigm":[31],"shift,":[32],"moving":[33],"from":[34,76],"simple":[35],"recognition":[36],"tasks":[37],"test":[39],"\"what\"":[40],"model":[42],"sees,":[43],"to":[44,85,104],"complex":[45],"reasoning":[46,164],"benchmarks":[47,126,165],"probe":[49],"\"why\"":[50],"and":[51,89,95,112,150],"\"how\"":[52],"understands.":[54],"driven":[58],"by":[59,166],"saturation":[61,162],"older":[63],"benchmarks,":[64],"where":[65,160],"high":[66],"performance":[67],"often":[68],"masks":[69],"fundamental":[70],"weaknesses.":[71],"chart":[73],"journey":[75],"foundational":[78],"\"knowledge":[79],"tests\"":[80],"ImageNet":[83],"era":[84],"\"applied":[87],"logic":[88],"comprehension\"":[90],"exams":[91],"such":[92,108],"GQA":[94],"Visual":[96],"Commonsense":[97],"Reasoning":[98],"(VCR),":[99],"which":[100],"were":[101],"designed":[102,131],"specifically":[103],"diagnose":[105],"systemic":[106],"flaws":[107],"shortcut":[110],"learning":[111],"failures":[113],"compositional":[115],"generalization.":[116],"then":[118],"current":[121],"frontier":[122],"\"expert-level":[124],"integration\"":[125],"(e.g.,":[127],"MMBench,":[128],"SEED-Bench,":[129],"MMMU)":[130],"for":[132,209],"today\u2019s":[133],"powerful":[134],"large":[136],"language":[137],"models":[138,167],"(MLLMs).":[139],"Next,":[140],"we":[141],"explore":[142],"uncharted":[144],"territories":[145],"evaluating":[147],"abstract,":[148],"creative,":[149],"social":[151],"intelligence.":[152],"also":[154],"discuss":[155],"emerging":[157],"\"Post-2025\"":[158],"landscape,":[159],"rapid":[161],"like":[168],"Gemini":[169],"3":[170],"Pro":[171],"necessitates":[172],"shift":[174],"toward":[175],"\"living\"":[176],"adversarial":[177,197],"evaluations.":[178],"conclude":[180],"narrative":[183],"AI":[185],"not":[188],"merely":[189],"history":[191],"datasets,":[193],"but":[194],"continuous,":[196],"process":[198],"designing":[200],"better":[201],"examinations":[202],"that,":[203],"turn,":[205],"redefine":[206],"our":[207],"goals":[208],"creating":[210],"truly":[211],"intelligent":[212],"systems.":[213]},"counts_by_year":[],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-09T00:00:00"}