{"id":"https://openalex.org/W4403746689","doi":"https://doi.org/10.48550/arxiv.2409.12122","title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","display_name":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","publication_year":2024,"publication_date":"2024-09-18","ids":{"openalex":"https://openalex.org/W4403746689","doi":"https://doi.org/10.48550/arxiv.2409.12122"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2409.12122","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.12122","pdf_url":"https://arxiv.org/pdf/2409.12122","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2409.12122","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100459632","display_name":"Yang An","orcid":"https://orcid.org/0000-0003-1527-033X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yang, An","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101849101","display_name":"Beichen Zhang","orcid":"https://orcid.org/0000-0001-9378-0250"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Beichen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080628250","display_name":"Binyuan Hui","orcid":"https://orcid.org/0000-0002-2160-7595"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hui, Binyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002310167","display_name":"Bofei Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Bofei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085149388","display_name":"Bowen Yu","orcid":"https://orcid.org/0009-0007-7014-6434"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Bowen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041916202","display_name":"Cheng\u2010Peng Li","orcid":"https://orcid.org/0000-0002-6798-9541"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Chengpeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062188134","display_name":"Dayiheng Liu","orcid":"https://orcid.org/0000-0002-8755-8941"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Dayiheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082583725","display_name":"Jianhong Tu","orcid":"https://orcid.org/0009-0001-1554-1614"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tu, Jianhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057864403","display_name":"Jingren Zhou","orcid":"https://orcid.org/0000-0002-4220-2634"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Jingren","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100612233","display_name":"Junyang Lin","orcid":"https://orcid.org/0000-0001-9931-383X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Junyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110849478","display_name":"Keming Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Keming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085563975","display_name":"Mingfeng Xue","orcid":"https://orcid.org/0000-0002-4801-3754"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xue, Mingfeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003991609","display_name":"Runji Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Runji","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100379446","display_name":"Tianyu Liu","orcid":"https://orcid.org/0000-0002-8716-749X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Tianyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054086732","display_name":"Xingzhang Ren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren, Xingzhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5045476473","display_name":"Zhenru Zhang","orcid":"https://orcid.org/0009-0009-0553-3491"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zhenru","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":16,"corresponding_author_ids":["https://openalex.org/A5100459632"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":12,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.6043000221252441,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.6043000221252441,"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/T14025","display_name":"Educational Technology and Assessment","score":0.5234000086784363,"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"}},{"id":"https://openalex.org/T14470","display_name":"Advanced Data Processing Techniques","score":0.5156999826431274,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.44586479663848877},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.44197335839271545},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3631904125213623},{"id":"https://openalex.org/keywords/management-science","display_name":"Management science","score":0.32624250650405884},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19566985964775085}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44586479663848877},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.44197335839271545},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3631904125213623},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.32624250650405884},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19566985964775085}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2409.12122","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.12122","pdf_url":"https://arxiv.org/pdf/2409.12122","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2409.12122","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2409.12122","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":"pmh:oai:arXiv.org:2409.12122","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.12122","pdf_url":"https://arxiv.org/pdf/2409.12122","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403746689.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4391375266","https://openalex.org/W1979597421","https://openalex.org/W2007980826","https://openalex.org/W2061531152","https://openalex.org/W3002753104","https://openalex.org/W2077600819","https://openalex.org/W2142036596","https://openalex.org/W2072657027"],"abstract_inverted_index":{"In":[0,54],"this":[1],"report,":[2],"we":[3,58,115],"present":[4],"a":[5,60,86,185],"series":[6,21],"of":[7,18,27,79,106,187],"math-specific":[8],"large":[9],"language":[10],"models:":[11],"Qwen2.5-Math":[12],"and":[13,35,95,148,150,159,174,182],"Qwen2.5-Math-Instruct-1.5B/7B/72B.":[14],"The":[15],"core":[16],"innovation":[17],"the":[19,25,30,41,55,76,97,103,111,117,125,130,133,141],"Qwen2.5":[20],"lies":[22],"in":[23,81,100,124,171],"integrating":[24],"philosophy":[26],"self-improvement":[28],"throughout":[29],"entire":[31],"pipeline,":[32],"from":[33,68,189],"pre-training":[34,42],"post-training":[36,56],"to":[37,47,75,92,137,193],"inference:":[38],"(1)":[39],"During":[40],"phase,":[43,57],"Qwen2-Math-Instruct":[44],"is":[45,72,135],"utilized":[46],"generate":[48],"large-scale,":[49],"high-quality":[50],"mathematical":[51,153],"data.":[52],"(2)":[53],"develop":[59],"reward":[61],"model":[62],"(RM)":[63],"by":[64],"conducting":[65],"massive":[66],"sampling":[67],"Qwen2-Math-Instruct.":[69],"This":[70],"RM":[71,119,134],"then":[73],"applied":[74],"iterative":[77],"evolution":[78],"data":[80,108],"supervised":[82],"fine-tuning":[83],"(SFT).":[84],"With":[85],"stronger":[87],"SFT":[88,107,113],"model,":[89,114],"it's":[90],"possible":[91],"iteratively":[93],"train":[94],"update":[96],"RM,":[98],"which":[99],"turn":[101],"guides":[102],"next":[104],"round":[105],"iteration.":[109],"On":[110],"final":[112],"employ":[116],"ultimate":[118],"for":[120],"reinforcement":[121],"learning,":[122],"resulting":[123],"Qwen2.5-Math-Instruct.":[126],"(3)":[127],"Furthermore,":[128],"during":[129],"inference":[131],"stage,":[132],"used":[136],"guide":[138],"sampling,":[139],"optimizing":[140],"model's":[142],"performance.":[143],"Qwen2.5-Math-Instruct":[144],"supports":[145],"both":[146,172],"Chinese":[147],"English,":[149],"possess":[151],"advanced":[152],"reasoning":[154],"capabilities,":[155],"including":[156],"Chain-of-Thought":[157],"(CoT)":[158],"Tool-Integrated":[160],"Reasoning":[161],"(TIR).":[162],"We":[163],"evaluate":[164],"our":[165],"models":[166],"on":[167],"10":[168],"mathematics":[169],"datasets":[170],"English":[173],"Chinese,":[175],"such":[176],"as":[177],"GSM8K,":[178],"MATH,":[179],"GaoKao,":[180],"AMC23,":[181],"AIME24,":[183],"covering":[184],"range":[186],"difficulties":[188],"grade":[190],"school":[191],"level":[192],"math":[194],"competition":[195],"problems.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2024-10-25T00:00:00"}
