{"id":"https://openalex.org/W7129464062","doi":"https://doi.org/10.48550/arxiv.2602.14456","title":"Traceable Latent Variable Discovery Based on Multi-Agent Collaboration","display_name":"Traceable Latent Variable Discovery Based on Multi-Agent Collaboration","publication_year":2026,"publication_date":"2026-02-16","ids":{"openalex":"https://openalex.org/W7129464062","doi":"https://doi.org/10.48550/arxiv.2602.14456"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.14456","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.14456","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":null,"license_id":null,"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.2602.14456","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126263432","display_name":"Huaming Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Du, Huaming","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066091502","display_name":"Tao Hu","orcid":"https://orcid.org/0009-0002-6661-2723"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Tao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124402952","display_name":"Yijie Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Yijie","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126204779","display_name":"Yu Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Yu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126209024","display_name":"Guisong Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Guisong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048182774","display_name":"Tao Gu","orcid":"https://orcid.org/0000-0001-7711-1196"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gu, Tao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073973267","display_name":"Gang Kou","orcid":"https://orcid.org/0000-0002-9220-8647"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kou, Gang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5126177023","display_name":"Carl Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Carl","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5126263432"],"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/T13702","display_name":"Machine Learning in Healthcare","score":0.7297000288963318,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.7297000288963318,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.0714000016450882,"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":0.03790000081062317,"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/latent-variable","display_name":"Latent variable","score":0.6854000091552734},{"id":"https://openalex.org/keywords/latent-variable-model","display_name":"Latent variable model","score":0.5878999829292297},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5730999708175659},{"id":"https://openalex.org/keywords/causal-model","display_name":"Causal model","score":0.4065999984741211},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.3910999894142151},{"id":"https://openalex.org/keywords/latent-class-model","display_name":"Latent class model","score":0.3864000141620636},{"id":"https://openalex.org/keywords/causal-inference","display_name":"Causal inference","score":0.3840000033378601},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.37560001015663147},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.362199991941452}],"concepts":[{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.6854000091552734},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.64410001039505},{"id":"https://openalex.org/C65965080","wikidata":"https://www.wikidata.org/wiki/Q1806885","display_name":"Latent variable model","level":3,"score":0.5878999829292297},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5730999708175659},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4936999976634979},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.4065999984741211},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4049000144004822},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3910999894142151},{"id":"https://openalex.org/C70727504","wikidata":"https://www.wikidata.org/wiki/Q1806878","display_name":"Latent class model","level":2,"score":0.3864000141620636},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.3840000033378601},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.37560001015663147},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33149999380111694},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3084000051021576},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.3068999946117401},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C166151441","wikidata":"https://www.wikidata.org/wiki/Q4923601","display_name":"Causation","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.2558000087738037},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.14456","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.14456","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2602.14456","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.14456","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"score":0.44044244289398193,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Revealing":[0],"the":[1,6,22,28,37,50,62,82,92,148,156,197,218],"underlying":[2],"causal":[3,32,66,76,115],"mechanisms":[4],"in":[5,19,208,211,215],"real":[7,182],"world":[8],"is":[9],"crucial":[10],"for":[11,98,126,169],"scientific":[12],"and":[13,27,102,139,189,199,213],"technological":[14],"progress.":[15],"Despite":[16],"notable":[17],"advances":[18],"recent":[20],"decades,":[21],"lack":[23],"of":[24,30,39,53,65,86,96,201,206],"high-quality":[25],"data":[26,164],"reliance":[29],"traditional":[31],"discovery":[33],"algorithms":[34],"(TCDA)":[35],"on":[36,179],"assumption":[38],"no":[40],"latent":[41,54,100,119,127,151,158],"confounders,":[42],"as":[43,45,133],"well":[44],"their":[46,103],"tendency":[47],"to":[48,61,112,146,154,172],"overlook":[49],"precise":[51],"semantics":[52],"variables,":[55],"have":[56],"long":[57],"been":[58],"major":[59],"obstacles":[60],"broader":[63],"application":[64],"discovery.":[67],"To":[68],"address":[69],"this":[70,131],"issue,":[71],"we":[72,106,122,166],"propose":[73],"a":[74,109,114,134,187],"novel":[75],"modeling":[77,94,130],"framework,":[78],"TLVD,":[79,202],"which":[80],"integrates":[81],"metadata-based":[83],"reasoning":[84],"capabilities":[85,95],"large":[87],"language":[88],"models":[89],"(LLMs)":[90],"with":[91,136,203],"data-driven":[93,110],"TCDA":[97],"inferring":[99],"variables":[101,159],"semantics.":[104],"Specifically,":[105],"first":[107],"employ":[108,123],"approach":[111],"construct":[113],"graph":[116],"that":[117],"incorporates":[118],"variables.":[120,152],"Then,":[121],"multi-LLM":[124],"collaboration":[125],"variable":[128],"inference,":[129],"process":[132],"game":[135],"incomplete":[137],"information":[138],"seeking":[140],"its":[141],"Bayesian":[142],"Nash":[143],"Equilibrium":[144],"(BNE)":[145],"infer":[147],"possible":[149],"specific":[150],"Finally,":[153],"validate":[155],"inferred":[157],"across":[160,217],"multiple":[161],"real-world":[162],"web-based":[163],"sources,":[165],"leverage":[167],"LLMs":[168],"evidence":[170],"exploration":[171],"ensure":[173],"traceability.":[174],"We":[175],"comprehensively":[176],"evaluate":[177],"TLVD":[178],"three":[180],"de-identified":[181],"patient":[183],"datasets":[184],"provided":[185],"by":[186],"hospital":[188],"two":[190],"benchmark":[191],"datasets.":[192,220],"Extensive":[193],"experimental":[194],"results":[195],"confirm":[196],"effectiveness":[198],"reliability":[200],"average":[204],"improvements":[205],"32.67%":[207],"Acc,":[209],"62.21%":[210],"CAcc,":[212],"26.72%":[214],"ECit":[216],"five":[219]},"counts_by_year":[],"updated_date":"2026-02-18T06:25:47.457606","created_date":"2026-02-18T00:00:00"}