{"id":"https://openalex.org/W4416708291","doi":"https://doi.org/10.48550/arxiv.2509.02208","title":"Baichuan-M2: Scaling Medical Capability with Large Verifier System","display_name":"Baichuan-M2: Scaling Medical Capability with Large Verifier System","publication_year":2025,"publication_date":"2025-09-02","ids":{"openalex":"https://openalex.org/W4416708291","doi":"https://doi.org/10.48550/arxiv.2509.02208"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2509.02208","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.02208","pdf_url":"https://arxiv.org/pdf/2509.02208","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/2509.02208","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"M2 Team","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M2 Team","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Dou, Chengfeng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dou, Chengfeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063130397","display_name":"Chong Liu","orcid":"https://orcid.org/0000-0002-9780-9062","observed_orcids":["https://orcid.org/0000-0002-9780-9062","https://orcid.org/0000-0002-1382-1487"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Chong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yang, Fan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Fan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Li, Fei","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Fei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jia, Jiyuan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia, Jiyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021633960","display_name":"Mingyang Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Mingyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ju, Qiang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ju, Qiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328361","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0003-4960-1926","observed_orcids":["https://orcid.org/0000-0003-4960-1926"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Shuai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120616107","display_name":"Shunya Dang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dang, Shunya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101773154","display_name":"Tianpeng Li","orcid":"https://orcid.org/0000-0002-3755-8126","observed_orcids":["https://orcid.org/0000-0002-3755-8126"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Tianpeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102899394","display_name":"Xiangrong Zeng","orcid":"https://orcid.org/0000-0002-1424-9523","observed_orcids":["https://orcid.org/0000-0002-1424-9523"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Xiangrong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016736192","display_name":"Yijie Zhou","orcid":"https://orcid.org/0000-0001-7642-5011","observed_orcids":["https://orcid.org/0000-0001-7642-5011"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Yijie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107930628","display_name":"Chenzheng Zhu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Chenzheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Pan, Da","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan, Da","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Deng, Fei","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deng, Fei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120521195","display_name":"Guangwei Ai","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ai, Guangwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112223588","display_name":"Guosheng Dong","orcid":"https://orcid.org/0009-0006-2955-9272","observed_orcids":["https://orcid.org/0009-0006-2955-9272"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong, Guosheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101680982","display_name":"Hongda Zhang","orcid":"https://orcid.org/0009-0006-7833-3122","observed_orcids":["https://orcid.org/0009-0006-7833-3122","https://orcid.org/0000-0002-2109-5972"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Hongda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125387171","display_name":"Jinyang Tai","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tai, Jinyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Hong, Jixiang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hong, Jixiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100625351","display_name":"Kai L\u00fc","orcid":"https://orcid.org/0000-0001-5720-6681","observed_orcids":["https://orcid.org/0000-0001-5720-6681"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Kai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Sun, Linzhuang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Linzhuang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Guo, Peidong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Peidong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ma, Qian","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Qian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Xin, Rihui","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin, Rihui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100566873","display_name":"Shihui Yang","orcid":"https://orcid.org/0000-0002-9394-9148","observed_orcids":["https://orcid.org/0000-0002-9394-9148"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Shihui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101763846","display_name":"Shusen Zhang","orcid":"https://orcid.org/0000-0001-8714-6683","observed_orcids":["https://orcid.org/0000-0001-8714-6683"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Shusen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Mo, Yichuan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mo, Yichuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Liang, Zheng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Zhishou","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zhishou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Cui, Hengfu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cui, Hengfu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhu, Zuyi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Zuyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100764921","display_name":"Xiaochuan Wang","orcid":"https://orcid.org/0000-0001-8207-0042","observed_orcids":["https://orcid.org/0000-0001-8207-0042"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xiaochuan","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":2,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.9955999851226807,"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"}},"topics":[{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.9955999851226807,"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"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.002099999925121665,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0005000000237487257,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/medical-large-language-models","display_name":"medical large language models","score":0.8769999742507935},{"id":"https://openalex.org/keywords/interactive-reinforcement-learning","display_name":"interactive reinforcement learning","score":0.8090000152587891},{"id":"https://openalex.org/keywords/patient-simulator","display_name":"patient simulator","score":0.8500000238418579},{"id":"https://openalex.org/keywords/group-relative-policy-optimization","display_name":"Group Relative Policy Optimization","score":0.8880000114440918},{"id":"https://openalex.org/keywords/clinical-decision-making","display_name":"clinical decision-making","score":0.6899999976158142}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7721999883651733},{"id":"https://openalex.org/C111640148","wikidata":"https://www.wikidata.org/wiki/Q847349","display_name":"Rubric","level":2,"score":0.6478999853134155},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6377000212669373},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5202999711036682},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4447999894618988},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40310001373291016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3873000144958496},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3528999984264374},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.28279998898506165},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26109999418258667},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2509.02208","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.02208","pdf_url":"https://arxiv.org/pdf/2509.02208","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.2509.02208","doi":"https://doi.org/10.48550/arxiv.2509.02208","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.02208","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.02208","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.02208","pdf_url":"https://arxiv.org/pdf/2509.02208","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":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416398373","https://openalex.org/W7214012787","https://openalex.org/W7128042938","https://openalex.org/W7162846872","https://openalex.org/W7126119261","https://openalex.org/W4386557455","https://openalex.org/W4416677620","https://openalex.org/W7153979526","https://openalex.org/W7138103932","https://openalex.org/W4387390101"],"abstract_inverted_index":{"As":[0],"large":[1],"language":[2],"models":[3,154],"(LLMs)":[4],"advance":[5],"in":[6,14,43,198],"conversational":[7],"and":[8,40,106,155],"reasoning":[9,128],"capabilities,":[10],"their":[11,41],"practical":[12,190],"application":[13],"healthcare":[15],"has":[16],"become":[17],"a":[18,25,69,81,94,107,124,132,161,194],"critical":[19],"research":[20],"focus.":[21],"However,":[22],"there":[23],"is":[24,183],"notable":[26],"gap":[27],"between":[28],"the":[29,56,166,199],"performance":[30],"of":[31,60],"medical":[32,61,104,126,203],"LLMs":[33],"on":[34,118,147,165],"static":[35,77],"benchmarks":[36],"such":[37],"as":[38],"USMLE":[39],"utility":[42],"real-world":[44],"clinical":[45,100,191],"decision-making.":[46],"This":[47],"discrepancy":[48],"arises":[49],"because":[50],"traditional":[51],"exams":[52],"fail":[53],"to":[54],"capture":[55],"dynamic,":[57],"interactive":[58,84],"nature":[59],"consultations.":[62],"To":[63],"address":[64],"this":[65,119],"challenge,":[66],"we":[67,121],"introduce":[68],"novel":[70],"dynamic":[71,180],"verification":[72],"framework":[73,89],"that":[74,97,111,178],"moves":[75],"beyond":[76],"answer":[78],"verifier,":[79],"establishing":[80,193],"large-scale,":[82],"high-fidelity":[83],"reinforcement":[85,134],"learning":[86,135],"system.":[87],"Our":[88,175],"comprises":[90],"two":[91],"key":[92],"components:":[93],"Patient":[95],"Simulator":[96],"creates":[98],"realistic":[99],"environments":[101],"using":[102],"de-identified":[103],"records,":[105],"Clinical":[108],"Rubrics":[109],"Generator":[110],"dynamically":[112],"produces":[113],"multi-dimensional":[114],"evaluation":[115],"metrics.":[116],"Building":[117],"foundation,":[120],"develop":[122],"Baichuan-M2,":[123],"32B-parameter":[125],"augmented":[127],"model":[129],"trained":[130],"through":[131],"multi-stage":[133],"strategy":[136],"with":[137,189],"an":[138],"improved":[139],"Group":[140],"Relative":[141],"Policy":[142],"Optimization":[143],"(GRPO)":[144],"algorithm.":[145],"Evaluated":[146],"HealthBench,":[148],"Baichuan-M2":[149],"outperforms":[150],"all":[151],"other":[152],"open-source":[153],"most":[156],"advanced":[157],"closed-source":[158],"counterparts,":[159],"achieving":[160],"score":[162],"above":[163],"32":[164],"challenging":[167],"HealthBench":[168],"Hard":[169],"benchmark-previously":[170],"exceeded":[171],"only":[172],"by":[173],"GPT-5.":[174],"work":[176],"demonstrates":[177],"robust":[179],"verifier":[181],"system":[182],"essential":[184],"for":[185,202],"aligning":[186],"LLM":[187],"capabilities":[188],"applications,":[192],"new":[195],"Pareto":[196],"front":[197],"performance-parameter":[200],"trade-off":[201],"AI":[204],"deployment.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-10T00:00:00"}
