{"id":"https://openalex.org/W7131663503","doi":"https://doi.org/10.48550/arxiv.2602.21351","title":"A Hierarchical Multi-Agent System for Autonomous Discovery in Geoscientific Data Archives","display_name":"A Hierarchical Multi-Agent System for Autonomous Discovery in Geoscientific Data Archives","publication_year":2026,"publication_date":"2026-02-24","ids":{"openalex":"https://openalex.org/W7131663503","doi":"https://doi.org/10.48550/arxiv.2602.21351"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2602.21351","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.21351","pdf_url":"https://arxiv.org/pdf/2602.21351","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":"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/2602.21351","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049217355","display_name":"Dmitrii Pantiukhin","orcid":"https://orcid.org/0000-0002-3427-8188","observed_orcids":["https://orcid.org/0000-0002-3427-8188"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pantiukhin, Dmitrii","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091663028","display_name":"Ivan Kuznetsov","orcid":"https://orcid.org/0000-0001-5910-8081","observed_orcids":["https://orcid.org/0000-0001-5910-8081"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kuznetsov, Ivan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116618119","display_name":"Boris Shapkin","orcid":"https://orcid.org/0009-0002-8280-3554","observed_orcids":["https://orcid.org/0009-0002-8280-3554"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shapkin, Boris","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089818130","display_name":"A. Jost","orcid":"https://orcid.org/0009-0007-0571-6429","observed_orcids":["https://orcid.org/0009-0007-0571-6429"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jost, Antonia Anna","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jung, Thomas","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jung, Thomas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5126871127","display_name":"Nikolay Koldunov","orcid":"https://orcid.org/0000-0002-3365-8146","observed_orcids":["https://orcid.org/0000-0002-3365-8146"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Koldunov, Nikolay","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":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/T11986","display_name":"Scientific Computing and Data Management","score":0.8159000277519226,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.8159000277519226,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.05209999904036522,"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/T11937","display_name":"Research Data Management Practices","score":0.04800000041723251,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/multi-agent-systems","display_name":"multi-agent systems","score":0.8629999756813049},{"id":"https://openalex.org/keywords/pangaea","display_name":"Pangea","score":0.9629999995231628},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7020000219345093},{"id":"https://openalex.org/keywords/self-correction","display_name":"self-correction","score":0.6420000195503235},{"id":"https://openalex.org/keywords/data-reusability","display_name":"data reusability","score":0.7020000219345093},{"id":"https://openalex.org/keywords/physical-oceanography","display_name":"physical oceanography","score":0.7960000038146973}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7529000043869019},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7074000239372253},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7052000164985657},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4787999987602234},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4528000056743622},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.44859999418258667},{"id":"https://openalex.org/C2779614968","wikidata":"https://www.wikidata.org/wiki/Q4398","display_name":"Pangaea","level":4,"score":0.4287000000476837},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3578000068664551},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3192000091075897},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3102000057697296},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.30149999260902405},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29910001158714294},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C2776397876","wikidata":"https://www.wikidata.org/wiki/Q1450531","display_name":"Cyberinfrastructure","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C2777516300","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data discovery","level":3,"score":0.28049999475479126},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.27239999175071716},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.25119999051094055},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2602.21351","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.21351","pdf_url":"https://arxiv.org/pdf/2602.21351","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2602.21351","doi":"https://doi.org/10.48550/arxiv.2602.21351","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.21351","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2602.21351","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.21351","pdf_url":"https://arxiv.org/pdf/2602.21351","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/14","score":0.6281526684761047,"display_name":"Life below water"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"rapid":[1],"accumulation":[2],"of":[3,20],"Earth":[4],"science":[5],"data":[6,32,45,117],"has":[7],"created":[8],"a":[9,26,38,59,109],"significant":[10],"scalability":[11],"challenge;":[12],"while":[13],"repositories":[14],"like":[15],"PANGAEA":[16],"host":[17],"vast":[18],"collections":[19],"datasets,":[21],"citation":[22],"metrics":[23],"indicate":[24],"that":[25],"substantial":[27],"portion":[28],"remains":[29],"underutilized,":[30],"limiting":[31],"reusability.":[33],"Here":[34],"we":[35,92],"present":[36],"PANGAEA-GPT,":[37],"hierarchical":[39],"multi-agent":[40],"framework":[41,107],"designed":[42],"for":[43,111],"autonomous":[44],"discovery":[46],"and":[47,71,80,90,113],"analysis.":[48],"Unlike":[49],"standard":[50],"Large":[51],"Language":[52],"Model":[53],"(LLM)":[54],"wrappers,":[55],"our":[56],"architecture":[57],"implements":[58],"centralized":[60],"Supervisor-Worker":[61],"topology":[62],"with":[63,102],"strict":[64],"data-type-aware":[65],"routing,":[66],"sandboxed":[67],"deterministic":[68],"code":[69],"execution,":[70],"self-correction":[72],"via":[73],"execution":[74],"feedback,":[75],"enabling":[76],"agents":[77],"to":[78,97],"diagnose":[79],"resolve":[81],"runtime":[82],"errors.":[83],"Through":[84],"use-case":[85],"scenarios":[86],"spanning":[87],"physical":[88],"oceanography":[89],"ecology,":[91],"demonstrate":[93],"the":[94],"system's":[95],"capacity":[96],"execute":[98],"complex,":[99],"multi-step":[100],"workflows":[101],"minimal":[103],"human":[104],"intervention.":[105],"This":[106],"provides":[108],"methodology":[110],"querying":[112],"analyzing":[114],"heterogeneous":[115],"repository":[116],"through":[118],"coordinated":[119],"agent":[120],"workflows.":[121]},"counts_by_year":[],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2026-02-27T00:00:00"}
