{"id":"https://openalex.org/W7131084482","doi":"https://doi.org/10.48550/arxiv.2602.17684","title":"CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models","display_name":"CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models","publication_year":2026,"publication_date":"2026-02-04","ids":{"openalex":"https://openalex.org/W7131084482","doi":"https://doi.org/10.48550/arxiv.2602.17684"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.17684","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126583596","display_name":"Xiao Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126620550","display_name":"Xinyu Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Xinyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113375392","display_name":"Boyu Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Boyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045240612","display_name":"Hanxu Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Hanxu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126648626","display_name":"Mingzhe Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Mingzhe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126654375","display_name":"Haotian Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Haotian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115588114","display_name":"Huiming Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Huiming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5126604696","display_name":"Zhijiang Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Zhijiang","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22258335,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.3093999922275543,"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":0.3093999922275543,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.13199999928474426,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.10989999771118164,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7821000218391418},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7159000039100647},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6941999793052673},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5956000089645386},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.37709999084472656},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.3630000054836273},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.36090001463890076}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7910000085830688},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7821000218391418},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7159000039100647},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6941999793052673},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5956000089645386},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5827000141143799},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.578000009059906},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.37709999084472656},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.3630000054836273},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.36090001463890076},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.3452000021934509},{"id":"https://openalex.org/C148027188","wikidata":"https://www.wikidata.org/wiki/Q907375","display_name":"Unit testing","level":3,"score":0.2937000095844269},{"id":"https://openalex.org/C2775941552","wikidata":"https://www.wikidata.org/wiki/Q25212305","display_name":"Isolation (microbiology)","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C63435697","wikidata":"https://www.wikidata.org/wiki/Q864135","display_name":"Binary code","level":3,"score":0.26969999074935913},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.26350000500679016}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.17684","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},{"id":"doi:10.48550/arxiv.2602.17684","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.17684","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":"Preprint"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.17684","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"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":{"Reinforcement":[0],"Learning":[1],"from":[2,19,65],"Verifiable":[3],"Rewards":[4],"(RLVR)":[5],"has":[6],"driven":[7],"recent":[8],"progress":[9],"in":[10,150,162,170],"code":[11,54,67,72,164],"large":[12],"language":[13],"models":[14,157],"by":[15,28,93],"leveraging":[16],"execution-based":[17,91],"feedback":[18],"unit":[20,142],"tests,":[21],"but":[22,168],"its":[23],"scalability":[24],"is":[25,57],"fundamentally":[26],"constrained":[27],"the":[29,119,163],"availability":[30],"and":[31,50,69,74,81,98,172],"reliability":[32],"of":[33],"high-quality":[34],"test":[35,125,143],"cases.":[36,126],"We":[37],"propose":[38],"CodeScaler,":[39],"a":[40,147],"reward":[41,76,156],"model":[42,121],"designed":[43],"to":[44,78,106,141],"scale":[45],"both":[46],"reinforcement":[47],"learning":[48],"training":[49],"test-time":[51,135],"inference":[52,128],"for":[53],"generation.":[55],"CodeScaler":[56,88,113,130,153],"trained":[58],"on":[59,96,101,158,177],"carefully":[60],"curated":[61],"preference":[62],"data":[63],"derived":[64],"verified":[66],"problems":[68,108],"incorporates":[70],"syntax-aware":[71],"extraction":[73],"validity-preserving":[75],"shaping":[77],"ensure":[79],"stable":[80],"robust":[82],"optimization.":[83],"Across":[84],"four":[85],"coding":[86],"benchmarks,":[87],"consistently":[89],"outperforms":[90],"RL":[92],"+1.55":[94],"points":[95,100,116,176],"Qwen3-8B-Base":[97],"+4.23":[99],"Qwen3-14B-Base.":[102],"By":[103],"further":[104],"scaling":[105,136],"44K":[107],"with":[109],"additional":[110],"synthetic":[111],"data,":[112],"yields":[114],"+14.64":[115],"improvement":[117],"over":[118],"base":[120],"without":[122],"requiring":[123],"any":[124],"At":[127],"time,":[129],"serves":[131],"as":[132],"an":[133],"effective":[134],"method,":[137],"achieving":[138],"performance":[139],"comparable":[140],"approaches":[144],"while":[145],"providing":[146],"10-fold":[148],"reduction":[149],"latency.":[151],"Moreover,":[152],"surpasses":[154],"existing":[155],"RM-Bench":[159],"not":[160],"only":[161],"domain":[165],"(+3.3":[166],"points),":[167],"also":[169],"general":[171],"reasoning":[173],"domains":[174],"(+2.7":[175],"average).":[178]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2026-02-24T00:00:00"}