{"id":"https://openalex.org/W7154494335","doi":"https://doi.org/10.48550/arxiv.2604.12999","title":"Agentic Discovery with Active Hypothesis Exploration for Visual Recognition","display_name":"Agentic Discovery with Active Hypothesis Exploration for Visual Recognition","publication_year":2026,"publication_date":"2026-04-14","ids":{"openalex":"https://openalex.org/W7154494335","doi":"https://doi.org/10.48550/arxiv.2604.12999"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.12999","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.12999","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.2604.12999","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071208482","display_name":"Jaywon Koo","orcid":"https://orcid.org/0000-0002-5539-5244"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Koo, Jaywon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067752616","display_name":"Jefferson Hernandez","orcid":"https://orcid.org/0000-0002-7091-0478"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hernandez, Jefferson","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050905744","display_name":"Ruozhen He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Ruozhen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133663010","display_name":"Hanjie Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Hanjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042419492","display_name":"CHEN WEI","orcid":"https://orcid.org/0000-0001-6882-109X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5027328044","display_name":"Vicente Ord\u00f3\u00f1ez","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ordonez, Vicente","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"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":0.5503000020980835,"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":0.5503000020980835,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.12530000507831573,"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"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.07240000367164612,"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/tree","display_name":"Tree (set theory)","score":0.46459999680519104},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.4431999921798706},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.44290000200271606},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.40130001306533813},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.3783999979496002},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.35280001163482666},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.3441999852657318}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6876000165939331},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5885999798774719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5800999999046326},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.46459999680519104},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4431999921798706},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.44290000200271606},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.40130001306533813},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3783999979496002},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.35280001163482666},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3441999852657318},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3212999999523163},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.31520000100135803},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.25429999828338623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.12999","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.12999","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.2604.12999","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.12999","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,149,170],"introduce":[1],"HypoExplore,":[2],"an":[3],"agentic":[4],"framework":[5,69,117],"that":[6,58,74,87,139,172,183,193],"formulates":[7],"neural":[8,31],"architecture":[9,160],"discovery":[10,161],"for":[11],"visual":[12],"recognition":[13],"as":[14,179],"a":[15,20,41,47,55,71,83,135,154,167,204],"hypothesis-driven":[16],"scientific":[17],"inquiry.":[18],"Given":[19],"human-specified":[21],"high-level":[22],"research":[23],"direction,":[24],"HypoExplore":[25,194],"ideates,":[26],"implements,":[27],"evaluates,":[28],"and":[29,82,108,143,147,182],"improves":[30],"architectures":[32,124],"through":[33,93],"evolutionary":[34,190],"branching.":[35],"New":[36],"hypotheses":[37],"are":[38],"created":[39],"using":[40],"large":[42],"language":[43],"model":[44],"by":[45,54,157],"selecting":[46],"parent":[48],"hypothesis":[49,113,173],"to":[50,145,153],"build":[51,203],"upon,":[52],"guided":[53],"dual":[56],"strategy":[57],"balances":[59],"exploiting":[60],"validated":[61],"principles":[62,186],"with":[63,127],"resolving":[64],"uncertain":[65],"ones.":[66],"Our":[67,116],"proposed":[68,80],"maintains":[70],"Trajectory":[72],"Tree":[73],"records":[75],"the":[76,103,128,184,208],"lineage":[77],"of":[78,207],"all":[79],"architectures,":[81,199],"Hypothesis":[84],"Memory":[85],"Bank":[86],"actively":[88],"tracks":[89],"confidence":[90,114,174],"scores":[91,175],"acquired":[92],"experimental":[94],"evidence.":[95],"After":[96],"each":[97],"experiment,":[98],"multiple":[99],"feedback":[100],"agents":[101],"analyze":[102],"results":[104],"from":[105,134],"different":[106],"perspectives":[107],"consolidate":[109],"their":[110],"findings":[111],"into":[112],"updates.":[115],"is":[118],"tested":[119],"on":[120,125,163],"discovering":[121],"lightweight":[122],"vision":[123],"CIFAR-10,":[126],"best":[129],"achieving":[130],"94.11%":[131],"accuracy":[132],"evolved":[133],"root":[136],"node":[137],"baseline":[138],"starts":[140],"at":[141],"18.91%,":[142],"generalizes":[144],"CIFAR-100":[146],"Tiny-ImageNet.":[148],"further":[150],"demonstrate":[151],"applicability":[152],"specialized":[155],"domain":[156],"conducting":[158],"independent":[159,189],"runs":[162],"MedMNIST,":[164],"which":[165],"yield":[166],"state-of-the-art":[168],"performance.":[169],"show":[171],"grow":[176],"increasingly":[177],"predictive":[178],"evidence":[180],"accumulates,":[181],"learned":[185],"transfer":[187],"across":[188],"lineages,":[191],"suggesting":[192],"not":[195],"only":[196],"discovers":[197],"stronger":[198],"but":[200],"can":[201],"help":[202],"genuine":[205],"understanding":[206],"design":[209],"space.":[210]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-16T00:00:00"}