{"id":"https://openalex.org/W4415003690","doi":"https://doi.org/10.1109/mlcad65511.2025.11189212","title":"ScaleRTL: Scaling LLMs with Reasoning Data and Test-Time Compute for Accurate RTL Code Generation","display_name":"ScaleRTL: Scaling LLMs with Reasoning Data and Test-Time Compute for Accurate RTL Code Generation","publication_year":2025,"publication_date":"2025-09-08","ids":{"openalex":"https://openalex.org/W4415003690","doi":"https://doi.org/10.1109/mlcad65511.2025.11189212"},"language":"en","primary_location":{"id":"doi:10.1109/mlcad65511.2025.11189212","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlcad65511.2025.11189212","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 ACM/IEEE 7th Symposium on Machine Learning for CAD (MLCAD)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110237905","display_name":"Chenhui Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenhui Deng","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043529733","display_name":"Yun-Da Tsai","orcid":"https://orcid.org/0009-0009-5385-4660"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yun-Da Tsai","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101913598","display_name":"Guanting Liu","orcid":"https://orcid.org/0000-0001-7133-6378"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guan-Ting Liu","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034614246","display_name":"Zhongzhi Yu","orcid":"https://orcid.org/0000-0002-9981-4981"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhongzhi Yu","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029928585","display_name":"Haoxing Ren","orcid":"https://orcid.org/0000-0003-1028-3860"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoxing Ren","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.3516,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.97060218,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.9940000176429749,"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/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.9940000176429749,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9933000206947327,"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":0.9724000096321106,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7506999969482422},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5537999868392944},{"id":"https://openalex.org/keywords/automated-reasoning","display_name":"Automated reasoning","score":0.4571000039577484},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4481000006198883},{"id":"https://openalex.org/keywords/formalism","display_name":"Formalism (music)","score":0.44179999828338623},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.41499999165534973},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.39340001344680786},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.387800008058548}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7950000166893005},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7506999969482422},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5537999868392944},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.4571000039577484},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4481000006198883},{"id":"https://openalex.org/C73301696","wikidata":"https://www.wikidata.org/wiki/Q5469984","display_name":"Formalism (music)","level":3,"score":0.44179999828338623},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.41499999165534973},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.39340001344680786},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.387800008058548},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37869998812675476},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.37689998745918274},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.3619000017642975},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34599998593330383},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C43971567","wikidata":"https://www.wikidata.org/wiki/Q3142865","display_name":"Logical reasoning","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C71559656","wikidata":"https://www.wikidata.org/wiki/Q671298","display_name":"Divide and conquer algorithms","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25429999828338623},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlcad65511.2025.11189212","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlcad65511.2025.11189212","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 ACM/IEEE 7th Symposium on Machine Learning for CAD (MLCAD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W4387321091","https://openalex.org/W4389166737","https://openalex.org/W4393145520","https://openalex.org/W4403024064","https://openalex.org/W4403511190","https://openalex.org/W4409285487","https://openalex.org/W4409369309","https://openalex.org/W4413822481","https://openalex.org/W4414281281"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,18,99],"large":[3],"language":[4],"models":[5],"(LLMs)":[6],"have":[7,35],"enabled":[8],"near-human":[9],"performance":[10,132,161],"on":[11,115,149,162,174,178],"software":[12],"coding":[13,72],"benchmarks,":[14],"but":[15],"their":[16,57],"effectiveness":[17],"RTL":[19,39,71,108,125],"code":[20],"generation":[21],"remains":[22],"limited":[23],"due":[24,55],"to":[25,56,172],"the":[26,46,66,131,143],"scarcity":[27],"of":[28,89,102,123,133],"high-quality":[29,77],"training":[30],"data.":[31],"While":[32],"prior":[33],"efforts":[34],"fine-tuned":[36],"LLMs":[37],"for":[38,52,70],"tasks,":[40],"they":[41],"do":[42],"not":[43],"fundamentally":[44],"overcome":[45],"data":[47,79],"bottleneck":[48],"and":[49,80,150,164,176],"lack":[50],"support":[51],"test-time":[53,81,138],"scaling":[54,139],"non-reasoning":[58],"nature.":[59],"In":[60],"this":[61,116],"work,":[62],"we":[63,84,128],"introduce":[64],"ScaleRTL,":[65],"first":[67],"reasoning":[68,78,92,113,144,153],"LLM":[69],"that":[73,105,120,141,157],"scales":[74],"up":[75,171],"both":[76],"compute.":[82],"Specifically,":[83],"curate":[85],"a":[86,100,111,136],"diverse":[87],"set":[88],"long":[90],"chain-of-thought":[91],"traces":[93],"averaging":[94],"56K":[95],"tokens":[96,104],"each,":[97],"resulting":[98],"dataset":[101],"3.5B":[103],"captures":[106],"rich":[107],"knowledge.":[109],"Fine-tuning":[110],"general-purpose":[112],"model":[114],"corpus":[117],"yields":[118],"ScaleRTL":[119,134,158],"is":[121],"capable":[122],"deep":[124],"reasoning.":[126],"Subsequently,":[127],"further":[129],"enhance":[130],"through":[135],"novel":[137],"strategy":[140],"extends":[142],"process":[145],"via":[146],"iteratively":[147],"reflecting":[148],"self-correcting":[151],"previous":[152],"steps.":[154],"Results":[155],"show":[156],"achieves":[159],"state-of-the-art":[160],"VerilogEval":[163,175],"RTLLM,":[165],"outperforming":[166],"18":[167],"competitive":[168],"baselines":[169],"by":[170],"18.4%":[173],"12.7%":[177],"RTLLM.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}