{"id":"https://openalex.org/W7160831892","doi":"https://doi.org/10.48550/arxiv.2605.07305","title":"MedAction: Towards Active Multi-turn Clinical Diagnostic LLMs","display_name":"MedAction: Towards Active Multi-turn Clinical Diagnostic LLMs","publication_year":2026,"publication_date":"2026-05-08","ids":{"openalex":"https://openalex.org/W7160831892","doi":"https://doi.org/10.48550/arxiv.2605.07305"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.07305","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07305","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.2605.07305","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135867361","display_name":"Hsin-Ling Hsu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hsu, Hsin-Ling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059460381","display_name":"Zizheng Wang","orcid":"https://orcid.org/0000-0001-5983-5326"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zizheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058298924","display_name":"Donghua Zhang","orcid":"https://orcid.org/0000-0003-2959-9638"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Donghua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135882841","display_name":"Nai-Chia Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Nai-Chia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135865618","display_name":"Jerry Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jerry","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068409543","display_name":"Jun-En Ding","orcid":"https://orcid.org/0000-0002-1233-138X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Jun-En","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103418202","display_name":"Cheng Ting Hsu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hsu, Chia-Hsuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135876243","display_name":"Guoan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Guoan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135855695","display_name":"Feng Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135874142","display_name":"Fang-Ming Hung","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hung, Fang-Ming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135860479","display_name":"Chenwei Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Chenwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135868746","display_name":"Liyue Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Liyue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":12,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9348000288009644,"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":0.9348000288009644,"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/T10028","display_name":"Topic Modeling","score":0.018400000408291817,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.006599999964237213,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.7049999833106995},{"id":"https://openalex.org/keywords/medical-diagnosis","display_name":"Medical diagnosis","score":0.6751999855041504},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.635699987411499},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5726000070571899},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5019999742507935},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5016999840736389},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4830999970436096},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.41929998993873596},{"id":"https://openalex.org/keywords/data-consistency","display_name":"Data consistency","score":0.39340001344680786}],"concepts":[{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.7049999833106995},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.6751999855041504},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.635699987411499},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.58160001039505},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5726000070571899},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5019999742507935},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5016999840736389},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4830999970436096},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42579999566078186},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.41929998993873596},{"id":"https://openalex.org/C93361087","wikidata":"https://www.wikidata.org/wiki/Q4426698","display_name":"Data consistency","level":2,"score":0.39340001344680786},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3792000114917755},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.3698999881744385},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.3668999969959259},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3578999936580658},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3560999929904938},{"id":"https://openalex.org/C82157600","wikidata":"https://www.wikidata.org/wiki/Q2671652","display_name":"Diagnostic test","level":2,"score":0.3476000130176544},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3441999852657318},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.3416999876499176},{"id":"https://openalex.org/C2779134260","wikidata":"https://www.wikidata.org/wiki/Q12136","display_name":"Disease","level":2,"score":0.3296999931335449},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C177713679","wikidata":"https://www.wikidata.org/wiki/Q679690","display_name":"Intensive care medicine","level":1,"score":0.31690001487731934},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.2597000002861023}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.07305","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07305","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.2605.07305","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07305","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":{"Most":[0],"existing":[1,77],"LLM":[2],"diagnoses":[3],"are":[4,151],"evaluated":[5],"on":[6,175,183],"static,":[7],"single-turn":[8],"settings":[9],"where":[10],"complete":[11,86],"patient":[12],"information":[13,87],"is":[14],"provided":[15],"upfront,":[16],"an":[17,172],"oversimplification":[18],"of":[19,31,164],"real":[20],"clinical":[21,29],"practice.":[22],"We":[23,118],"study":[24],"active":[25],"diagnosis:":[26],"the":[27,134,139,192],"real-life":[28],"process":[30],"starting":[32],"from":[33,85,167],"initial":[34],"observation,":[35],"ordering":[36],"tests,":[37],"interpreting":[38],"results,":[39],"and":[40,66,110,142,186],"updating":[41],"a":[42,74,103,162],"differential":[43],"diagnosis":[44],"across":[45],"multiple":[46],"turns.":[47],"Through":[48],"systematic":[49],"analysis,":[50],"we":[51,100,159],"identify":[52],"three":[53],"recurring":[54],"failure":[55],"modes":[56],"in":[57],"current":[58],"LLMs:":[59],"ungrounded":[60],"test":[61],"ordering,":[62],"unreliable":[63],"diagnostic":[64,113],"update,":[65],"degraded":[67],"multi-turn":[68,112],"coherence.":[69],"Together,":[70],"these":[71],"failures":[72],"reveal":[73],"core":[75],"deficit:":[76],"medical":[78,196],"training":[79],"data":[80],"teaches":[81],"models":[82,182],"to":[83,90,123],"reason":[84],"but":[88],"not":[89],"act":[91],"under":[92],"evolving,":[93],"partial":[94],"evidence.":[95,155],"To":[96],"address":[97],"this":[98,157],"gap,":[99],"introduce":[101],"MedAction,":[102],"tree-structured":[104],"distillation":[105],"pipeline":[106],"that":[107,148],"synthesizes":[108],"diverse":[109],"high-quality":[111],"trajectories":[114,166],"via":[115],"LLM-environment":[116],"interaction.":[117],"propose":[119],"two":[120],"knowledge-graph-grounded":[121],"metrics":[122],"filter":[124],"trajectory":[125],"quality:":[126],"Disease":[127],"Trajectory":[128],"Consistency":[129,144],"(DTC),":[130],"which":[131,146],"tracks":[132],"whether":[133],"model's":[135],"hypothesis":[136],"converges":[137],"toward":[138],"correct":[140],"diagnosis,":[141],"Reasoning-Action":[143],"(RAC),":[145],"verifies":[147],"belief":[149],"updates":[150],"driven":[152],"by":[153],"gathered":[154],"Using":[156],"pipeline,":[158],"construct":[160],"MedAction-32K,":[161],"dataset":[163],"32,681":[165],"2,896":[168],"PMC":[169],"cases.":[170],"Fine-tuning":[171],"8B":[173],"model":[174],"MedAction-32K":[176],"achieves":[177],"state-of-the-art":[178],"performance":[179],"among":[180],"open-source":[181,195],"both":[184],"MedR-Bench":[185],"our":[187],"curated":[188],"MedAction-300-Hard":[189],"benchmark,":[190],"pushing":[191],"edge":[193],"for":[194],"LLMs.":[197]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-12T00:00:00"}