{"id":"https://openalex.org/W4415037181","doi":"https://doi.org/10.52202/085713-1967","title":"rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Dataset","display_name":"rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Dataset","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4415037181","doi":"https://doi.org/10.52202/085713-1967"},"language":"en","primary_location":{"id":"doi:10.52202/085713-1967","doi":"https://doi.org/10.52202/085713-1967","is_oa":true,"landing_page_url":"https://doi.org/10.52202/085713-1967","pdf_url":"https://www.proceedings.com/content/085/085713-1967open.pdf","source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 38","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.proceedings.com/content/085/085713-1967open.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100352545","display_name":"Yifei Liu","orcid":"https://orcid.org/0009-0003-9930-0918","observed_orcids":["https://orcid.org/0009-0003-9930-0918","https://orcid.org/0000-0001-6337-8068"]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifei Liu","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103007399","display_name":"Li Lyna Zhang","orcid":"https://orcid.org/0000-0002-4465-1628","observed_orcids":["https://orcid.org/0000-0002-4465-1628"]},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Lyna Zhang","raw_affiliation_strings":["Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103446004","display_name":"Yi Zhu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Zhu","raw_affiliation_strings":["Research, Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research, Microsoft","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bingcheng Dong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingcheng Dong","raw_affiliation_strings":["Dalian University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008255559","display_name":"Xudong Zhou","orcid":"https://orcid.org/0000-0002-6939-4410","observed_orcids":["https://orcid.org/0000-0002-6939-4410"]},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xudong Zhou","raw_affiliation_strings":["Cornell University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093745146","display_name":"Ning Shang","orcid":"https://orcid.org/0009-0007-5476-3993","observed_orcids":["https://orcid.org/0009-0007-5476-3993"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ning Shang","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025831186","display_name":"Fan Yang","orcid":"https://orcid.org/0000-0002-7883-9573","observed_orcids":["https://orcid.org/0000-0002-7883-9573"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fan Yang","raw_affiliation_strings":["Research, Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research, Microsoft","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5145533703","display_name":"Cheng Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Li","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100438310","display_name":"Mao Yang","orcid":"https://orcid.org/0009-0009-6455-3898","observed_orcids":["https://orcid.org/0009-0009-6455-3898"]},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mao Yang","raw_affiliation_strings":["Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25753802,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"65499","last_page":"65526"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9204000234603882,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9204000234603882,"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/T10533","display_name":"Teaching and Learning Programming","score":0.042500000447034836,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.020400000736117363,"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/code-reasoning","display_name":"code reasoning","score":0.9409999847412109},{"id":"https://openalex.org/keywords/competitive-programming","display_name":"competitive programming","score":0.6869999766349792},{"id":"https://openalex.org/keywords/dataset-construction","display_name":"dataset construction","score":0.4729999899864197},{"id":"https://openalex.org/keywords/livecodebench","display_name":"LiveCodeBench","score":0.8100000023841858},{"id":"https://openalex.org/keywords/qwen","display_name":"Qwen","score":0.5019999742507935},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6700000166893005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7807999849319458},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6198999881744385},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.5618000030517578},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4894999861717224},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4715000092983246},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.4262000024318695},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3677000105381012},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.31040000915527344},{"id":"https://openalex.org/C128942645","wikidata":"https://www.wikidata.org/wiki/Q1568346","display_name":"Test case","level":3,"score":0.3003000020980835},{"id":"https://openalex.org/C53942775","wikidata":"https://www.wikidata.org/wiki/Q1211721","display_name":"Code coverage","level":3,"score":0.30000001192092896},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2791000008583069},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26660001277923584},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2644999921321869},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2581000030040741}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/085713-1967","doi":"https://doi.org/10.52202/085713-1967","is_oa":true,"landing_page_url":"https://doi.org/10.52202/085713-1967","pdf_url":"https://www.proceedings.com/content/085/085713-1967open.pdf","source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 38","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.21297","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.21297","pdf_url":"https://arxiv.org/pdf/2505.21297","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.21297","doi":"https://doi.org/10.48550/arxiv.2505.21297","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.21297","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.52202/085713-1967","doi":"https://doi.org/10.52202/085713-1967","is_oa":true,"landing_page_url":"https://doi.org/10.52202/085713-1967","pdf_url":"https://www.proceedings.com/content/085/085713-1967open.pdf","source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 38","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415037181.pdf","grobid_xml":"https://content.openalex.org/works/W4415037181.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W6929653358","https://openalex.org/W6966662053","https://openalex.org/W4414690726","https://openalex.org/W4414856067","https://openalex.org/W7166863347","https://openalex.org/W4417538327","https://openalex.org/W4416035104","https://openalex.org/W6967084484","https://openalex.org/W7154465631","https://openalex.org/W4414881822"],"abstract_inverted_index":{"Advancing":[0],"code":[1,37,49,73,127,199],"reasoning":[2,38,128,142,200],"in":[3],"large":[4],"language":[5],"models":[6,123],"(LLMs)":[7],"is":[8,62,189],"fundamentally":[9],"limited":[10],"by":[11,40,166],"the":[12,94,131,168,185],"scarcity":[13],"of":[14,46,59,133,182],"high-difficulty":[15],"datasets,":[16],"especially":[17],"those":[18],"with":[19,55,115,144],"verifiable":[20],"input-output":[21,87],"test":[22,57,88],"cases":[23,58],"necessary":[24],"for":[25,107],"rigorous":[26],"solution":[27],"validation":[28],"at":[29,192],"scale.We":[30],"introduce":[31,84],"rStar-Coder,":[32],"which":[33],"significantly":[34,145],"improves":[35,151],"LLM":[36],"capabilities":[39],"constructing":[41],"a":[42,85,97,103],"large-scale,":[43],"verified":[44],"dataset":[45,188],"418K":[47],"competitionlevel":[48],"problems,":[50],"580K":[51],"long-reasoning":[52,118],"solutions":[53,76],"along":[54],"rich":[56],"varying":[60],"difficulty.This":[61],"achieved":[63],"through":[64],"three":[65],"core":[66],"contributions:":[67],"(1)":[68],"we":[69,83,112],"curate":[70],"competitive":[71],"programming":[72],"problems":[74,114],"and":[75,102,158],"to":[77,140,154,161],"synthesize":[78],"new,":[79],"solvable":[80],"problems;":[81],"(2)":[82],"reliable":[86],"case":[89],"synthesis":[90],"pipeline":[91],"that":[92],"decouples":[93],"generation":[95,100],"into":[96],"three-step":[98],"input":[99],"method":[101],"mutual":[104],"verification":[105],"mechanism":[106],"effective":[108],"output":[109],"labeling;":[110],"(3)":[111],"augment":[113],"high-quality,":[116],"test-case-verified":[117],"solutions.Extensive":[119],"experiments":[120],"on":[121,198],"Qwen":[122],"(1.5B-14B)":[124],"across":[125],"various":[126],"benchmarks":[129],"demonstrate":[130],"superiority":[132],"rStar-Coder":[134,150],"dataset,":[135],"achieving":[136],"leading":[137],"performance":[138],"comparable":[139],"frontier":[141],"LLMs":[143],"smaller":[146],"model":[147,176],"sizes.On":[148],"LiveCodeBench,":[149],"Qwen2.5-7Bfrom":[152],"17.4%":[153],"an":[155,178],"impressive":[156],"57.3%,":[157],"Qwen2.5-14Bfrom":[159],"23.3%":[160],"62.5%,":[162],"surpassing":[163],"o3-mini":[164],"(low)":[165],"3.1%.On":[167],"more":[169],"challenging":[170],"USA":[171],"Computing":[172],"Olympiad,":[173],"our":[174],"7B":[175],"achieves":[177],"average":[179],"pass@1":[180],"accuracy":[181,197],"16.15%,":[183],"outperforming":[184],"frontier-level":[186],"QWQ-32B.rStar-Coder":[187],"publicly":[190],"available":[191],"https://huggingface.co/datasets/microsoft/rStar-Coder.":[193],"Figure":[194],"1:":[195],"Pass@1":[196],"benchmarks.":[201]},"counts_by_year":[],"updated_date":"2026-10-26T11:51:55.731654","created_date":"2025-10-10T00:00:00"}