{"id":"https://openalex.org/W4412945427","doi":"https://doi.org/10.18653/v1/2025.acl-long.587","title":"ACECODER: Acing Coder RL via Automated Test-Case Synthesis","display_name":"ACECODER: Acing Coder RL via Automated Test-Case Synthesis","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945427","doi":"https://doi.org/10.18653/v1/2025.acl-long.587"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.587","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.587","pdf_url":"https://aclanthology.org/2025.acl-long.587.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.587.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Huaye Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huaye Zeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108899238","display_name":"Dongfu Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongfu Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047021656","display_name":"Haozhe Wang","orcid":"https://orcid.org/0000-0001-5123-1077"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haozhe Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116166906","display_name":"Ping Nie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ping Nie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100739426","display_name":"Xiaotong Chen","orcid":"https://orcid.org/0000-0002-4964-5286"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaotong Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103103242","display_name":"Wenhu Chen","orcid":"https://orcid.org/0000-0002-8609-7821"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenhu Chen","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":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12023","last_page":"12040"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9957000017166138,"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"}},"topics":[{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9957000017166138,"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/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.9866999983787537,"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/T12810","display_name":"Real-time simulation and control systems","score":0.984000027179718,"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":0.6154639720916748},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.4916732907295227},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34919607639312744}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6154639720916748},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.4916732907295227},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34919607639312744},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.587","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.587","pdf_url":"https://aclanthology.org/2025.acl-long.587.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.587","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.587","pdf_url":"https://aclanthology.org/2025.acl-long.587.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945427.pdf","grobid_xml":"https://content.openalex.org/works/W4412945427.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Most":[0],"progress":[1],"in":[2,32,178],"recent":[3],"coder":[4,179],"models":[5,84,119],"has":[6],"been":[7],"driven":[8],"by":[9,42,156,161],"supervised":[10],"fine-tuning":[11],"(SFT),":[12],"while":[13],"the":[14,26,33,104,137,172],"potential":[15,174],"of":[16,28,91,175],"reinforcement":[17,114,176],"learning":[18,115,177],"(RL)":[19],"remains":[20],"largely":[21],"unexplored,":[22],"primarily":[23],"due":[24],"to":[25,48,81,125,140],"lack":[27],"reliable":[29],"reward":[30,83,118],"data/model":[31],"code":[34,50,65],"domain.In":[35],"this":[36,40],"paper,":[37],"we":[38,53,70,112,135],"address":[39],"challenge":[41],"leveraging":[43],"automated":[44],"large-scale":[45],"testcase":[46,121],"synthesis":[47],"enhance":[49],"model":[51,106,153],"training.Specifically,":[52],"design":[54],"a":[55],"pipeline":[56],"that":[57,147],"generates":[58],"extensive":[59],"(question,":[60],"test-cases)":[61],"pairs":[62,73],"from":[63,142],"existing":[64],"data.Using":[66],"these":[67],"test":[68],"cases,":[69],"construct":[71],"preference":[72],"based":[74],"on":[75,107,154],"pass":[76,122],"rates":[77],"over":[78,157],"sampled":[79],"programs":[80],"train":[82],"with":[85,109,116],"Bradley-Terry":[86],"loss.It":[87],"shows":[88],"an":[89],"average":[90],"10-point":[92],"improvement":[93,98],"for":[94,99,163],"Llama-3.1-8B-Ins":[95],"and":[96,120,132,145,159],"5-point":[97],"Qwen2.5-Coder-7B-Insthrough":[100],"best-of-32":[101],"sampling,":[102],"making":[103],"7B":[105],"par":[108],"236B":[110],"DeepSeek-V2.5.Furthermore,":[111],"conduct":[113],"both":[117],"rewards,":[123],"leading":[124],"consistent":[126],"improvements":[127],"across":[128],"HumanEval,":[129],"MBPP,":[130],"Big-CodeBench,":[131],"LiveCodeBench":[133],"(V4).Notably,":[134],"follow":[136],"R1-style":[138],"training":[139,150],"start":[141],"Qwen2.5-Coder-base":[143],"directly":[144],"show":[146],"our":[148,169],"RL":[149],"can":[151],"improve":[152],"HumanEval-plus":[155],"25%":[158],"MBPP-plus":[160],"6%":[162],"merely":[164],"80":[165],"optimization":[166],"steps.We":[167],"believe":[168],"results":[170],"highlight":[171],"huge":[173],"models.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}