{"id":"https://openalex.org/W4412888745","doi":"https://doi.org/10.18653/v1/2025.findings-acl.206","title":"AceMath: Advancing Frontier Math Reasoning with Post-Training and Reward Modeling","display_name":"AceMath: Advancing Frontier Math Reasoning with Post-Training and Reward Modeling","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888745","doi":"https://doi.org/10.18653/v1/2025.findings-acl.206"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.206","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.206","pdf_url":"https://aclanthology.org/2025.findings-acl.206.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.206.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100623107","display_name":"Zihan Liu","orcid":"https://orcid.org/0000-0002-9692-4245"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zihan Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100350505","display_name":"Yang Chen","orcid":"https://orcid.org/0000-0003-4890-313X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072436307","display_name":"Mohammad Shoeybi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohammad Shoeybi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066242985","display_name":"Bryan Catanzaro","orcid":"https://orcid.org/0000-0003-0034-7728"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bryan Catanzaro","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101241909","display_name":"Wei Ping","orcid":"https://orcid.org/0009-0009-1768-3649"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Ping","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":"3993","last_page":"4015"},"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":0.9610000252723694,"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":0.9610000252723694,"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/frontier","display_name":"Frontier","score":0.6838146448135376},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5567408800125122},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5428144931793213},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.4006408154964447},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39098483324050903},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.32895582914352417},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2857731580734253},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2854534685611725}],"concepts":[{"id":"https://openalex.org/C2778571376","wikidata":"https://www.wikidata.org/wiki/Q1355821","display_name":"Frontier","level":2,"score":0.6838146448135376},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5567408800125122},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5428144931793213},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.4006408154964447},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39098483324050903},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.32895582914352417},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2857731580734253},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2854534685611725},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.206","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.206","pdf_url":"https://aclanthology.org/2025.findings-acl.206.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.206","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.206","pdf_url":"https://aclanthology.org/2025.findings-acl.206.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888745.pdf","grobid_xml":"https://content.openalex.org/works/W4412888745.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2347401120","https://openalex.org/W2041961361","https://openalex.org/W2310010941","https://openalex.org/W1988132375","https://openalex.org/W2334292868","https://openalex.org/W579144800","https://openalex.org/W2147233680","https://openalex.org/W2069525434","https://openalex.org/W2046798653","https://openalex.org/W2021057137"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,41,87,108,132],"introduce":[4],"AceMath,":[5],"a":[6,43,65,91,110],"suite":[7],"of":[8,26,69],"frontier":[9],"math":[10,17,39,62,98,116,141],"models":[11,24,100],"that":[12,48],"excel":[13],"in":[14],"solving":[15],"complex":[16],"problems,":[18],"along":[19],"with":[20,130],"highly":[21],"effective":[22],"reward":[23,85,99,117,125],"capable":[25],"evaluating":[27,97],"generated":[28,73],"solutions":[29],"and":[30,71,81,93,104],"reliably":[31],"identifying":[32],"the":[33,37,61,134,140],"correct":[34],"ones.To":[35],"develop":[36,83],"instructiontuned":[38],"models,":[40],"propose":[42],"supervised":[44],"fine-tuning":[45,59],"(SFT)":[46],"process":[47],"first":[49,88],"achieves":[50],"competitive":[51],"performance":[52],"across":[53,101,139],"general":[54],"domains,":[55],"followed":[56],"by":[57],"targeted":[58],"for":[60,96],"domain":[63],"using":[64],"carefully":[66],"curated":[67],"set":[68],"prompts":[70],"synthetically":[72],"responses.The":[74],"resulting":[75,119],"model,":[76,86,120],"AceMath-72B-Instruct":[77,129],"greatly":[78],"outperforms":[79,123],"Qwen2.5-Math-72B-Instruct,GPT-4o":[80],"Claude-3.5Sonnet.To":[82],"math-specialized":[84],"construct":[89],"AceMath-RewardBench,":[90],"comprehensive":[92],"robust":[94],"benchmark":[95],"diverse":[102],"problems":[103],"difficulty":[105],"levels.After":[106],"that,":[107],"present":[109],"systematic":[111],"approach":[112],"to":[113],"build":[114],"our":[115],"models.The":[118],"AceMath-72B-RM,":[121,131],"consistently":[122],"state-of-theart":[124],"models.Furthermore,":[126],"when":[127],"combining":[128],"achieve":[133],"highest":[135],"average":[136],"rm@8":[137],"score":[138],"reasoning":[142],"benchmarks.":[143]},"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"}