{"id":"https://openalex.org/W7164881436","doi":"https://doi.org/10.48550/arxiv.2606.16140","title":"VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models","display_name":"VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164881436","doi":"https://doi.org/10.48550/arxiv.2606.16140"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.16140","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.16140","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.16140","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053837667","display_name":"S Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Sen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100625473","display_name":"Shixi Liu","orcid":"https://orcid.org/0000-0003-4083-6737"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Shixi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138702837","display_name":"Wei Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138757404","display_name":"Jixin Min","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min, Jixin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124624181","display_name":"Y Sophia Dai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai, Yingwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077933413","display_name":"Zhibin Yin","orcid":"https://orcid.org/0000-0002-2434-4495"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin, Zhibin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138702779","display_name":"Yirong Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yirong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113903386","display_name":"X J Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138726107","display_name":"Junlin Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Junlin","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/T10028","display_name":"Topic Modeling","score":0.23890000581741333,"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/T10028","display_name":"Topic Modeling","score":0.23890000581741333,"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":0.22380000352859497,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.09790000319480896,"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/verifiable-secret-sharing","display_name":"Verifiable secret sharing","score":0.8086000084877014},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4627000093460083},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.42419999837875366},{"id":"https://openalex.org/keywords/automated-reasoning","display_name":"Automated reasoning","score":0.3725999891757965},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.367000013589859},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.3395000100135803}],"concepts":[{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.8086000084877014},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6552000045776367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5048999786376953},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4627000093460083},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.42419999837875366},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.3725999891757965},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.367000013589859},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.3395000100135803},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33719998598098755},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3246999979019165},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C73301696","wikidata":"https://www.wikidata.org/wiki/Q5469984","display_name":"Formalism (music)","level":3,"score":0.27559998631477356},{"id":"https://openalex.org/C116222747","wikidata":"https://www.wikidata.org/wiki/Q220888","display_name":"Falsifiability","level":2,"score":0.2712000012397766}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.16140","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.16140","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.16140","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.16140","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5346047282218933}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0,103,192],"technical":[1],"report":[2],"introduces":[3],"VibeThinker-3B,":[4],"a":[5,23,69,94,136,204],"compact":[6,173,196],"dense":[7],"model":[8,37],"with":[9,78,93],"3B":[10],"parameters":[11],"developed":[12],"to":[13,76],"investigate":[14],"how":[15],"far":[16],"verifiable":[17,64,168],"reasoning":[18,113,146,169,174],"can":[19],"be":[20],"pushed":[21],"within":[22],"strictly":[24],"small-model":[25],"regime.":[26],"Building":[27],"upon":[28],"the":[29,36,108,162],"Spectrum-to-Signal":[30],"post-training":[31],"paradigm,":[32],"we":[33],"systematically":[34],"enhance":[35],"through":[38],"an":[39,82],"optimized":[40],"pipeline":[41],"that":[42,56,120,143,195],"includes":[43],"curriculum-based":[44],"supervised":[45],"fine-tuning,":[46],"multi-domain":[47],"reinforcement":[48],"learning,":[49],"and":[50,88,131,179,189],"offline":[51],"self-distillation.":[52],"Experimental":[53],"evaluations":[54],"demonstrate":[55],"VibeThinker-3B":[57],"achieves":[58],"frontier-level":[59,208],"performance":[60,109,209],"on":[61,73,85,98,140],"highly":[62],"demanding":[63],"tasks.":[65],"Specifically,":[66],"it":[67,106],"attains":[68],"score":[70,137],"of":[71,111,123,138],"94.3":[72],"AIME26":[74],"(improving":[75],"97.1":[77],"claim-level":[79],"test-time":[80],"scaling),":[81],"80.2":[83],"Pass@1":[84],"LiveCodeBench":[86],"v6,":[87],"exhibits":[89],"strong":[90],"out-of-distribution":[91],"generalization":[92],"96.1\\%":[95],"acceptance":[96],"rate":[97],"recent":[99],"unseen":[100],"LeetCode":[101],"contests.":[102],"effectively":[104],"places":[105],"in":[107,210],"band":[110],"first-tier":[112],"systems,":[114],"matching":[115],"or":[116],"exceeding":[117],"flagship":[118],"models":[119,197],"are":[121,198],"orders":[122],"magnitude":[124],"larger,":[125],"such":[126],"as":[127,170],"DeepSeek":[128],"V3.2,":[129],"GLM-5,":[130],"Gemini":[132],"3":[133],"Pro.":[134],"Furthermore,":[135],"93.4":[139],"IFEval":[141],"confirms":[142],"this":[144],"extreme":[145],"enhancement":[147],"does":[148],"not":[149,199],"compromise":[150],"strict":[151],"instruction":[152],"controllability.":[153],"Extending":[154],"our":[155],"previous":[156],"1.5B":[157],"work,":[158],"these":[159],"findings":[160],"motivate":[161],"Parametric":[163],"Compression-Coverage":[164],"Hypothesis,":[165],"which":[166],"views":[167],"compressible":[171],"into":[172],"cores,":[175],"while":[176],"open-domain":[177],"knowledge":[178],"general-purpose":[180],"competence":[181],"require":[182],"broad":[183],"parameter":[184],"coverage":[185],"over":[186],"facts,":[187],"concepts,":[188],"long-tail":[190],"scenarios.":[191],"perspective":[193],"suggests":[194],"merely":[200],"deployment-efficient":[201],"substitutes,":[202],"but":[203],"complementary":[205],"path":[206],"toward":[207],"parameter-dense":[211],"capability":[212],"regimes.":[213]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-17T00:00:00"}