{"id":"https://openalex.org/W4416429681","doi":"https://doi.org/10.1109/iccad66269.2025.11241003","title":"VeriRL: Boosting the LLM-based Verilog Code Generation via Reinforcement Learning","display_name":"VeriRL: Boosting the LLM-based Verilog Code Generation via Reinforcement Learning","publication_year":2025,"publication_date":"2025-10-26","ids":{"openalex":"https://openalex.org/W4416429681","doi":"https://doi.org/10.1109/iccad66269.2025.11241003"},"language":null,"primary_location":{"id":"doi:10.1109/iccad66269.2025.11241003","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad66269.2025.11241003","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM International Conference On Computer Aided Design (ICCAD)","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/A5054421452","display_name":"Teng Fu","orcid":"https://orcid.org/0000-0002-2250-2453"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fu Teng","raw_affiliation_strings":["Zhejiang University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101387223","display_name":"Miao Pan","orcid":"https://orcid.org/0000-0002-2756-5859"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Miao Pan","raw_affiliation_strings":["Zhejiang University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101722406","display_name":"Xuhong Zhang","orcid":"https://orcid.org/0000-0002-8571-9780"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuhong Zhang","raw_affiliation_strings":["Zhejiang University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036755436","display_name":"Zhezhi He","orcid":"https://orcid.org/0000-0002-6357-236X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhezhi He","raw_affiliation_strings":["Shanghai Jiao Tong University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071629642","display_name":"Yiyao Yang","orcid":"https://orcid.org/0000-0002-6311-182X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiyao Yang","raw_affiliation_strings":["Shanghai Jiao Tong University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xinyi Chai","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyi Chai","raw_affiliation_strings":["Zhejiang University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101277570","display_name":"Mengnan Qi","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengnan Qi","raw_affiliation_strings":["Shanghai Jiao Tong University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072265593","display_name":"Liqiang Lu","orcid":"https://orcid.org/0000-0002-3801-6847"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqiang Lu","raw_affiliation_strings":["Zhejiang University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069353502","display_name":"Jianwei Yin","orcid":"https://orcid.org/0000-0003-4703-7348"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianwei Yin","raw_affiliation_strings":["Zhejiang University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9246,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.88773126,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"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/T10260","display_name":"Software Engineering Research","score":0.29269999265670776,"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":0.29269999265670776,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.08529999852180481,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.07599999755620956,"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":0.7441999912261963},{"id":"https://openalex.org/keywords/verilog","display_name":"Verilog","score":0.6766999959945679},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.47119998931884766},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.40939998626708984},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.38029998540878296},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.34529998898506165},{"id":"https://openalex.org/keywords/concurrency","display_name":"Concurrency","score":0.3138999938964844},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.31150001287460327}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8517000079154968},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7441999912261963},{"id":"https://openalex.org/C2779030575","wikidata":"https://www.wikidata.org/wiki/Q827773","display_name":"Verilog","level":3,"score":0.6766999959945679},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.47119998931884766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4108000099658966},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.40939998626708984},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.38029998540878296},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36899998784065247},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.34529998898506165},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.3027999997138977},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3001999855041504},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2897000014781952},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.2678999900817871},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C53942775","wikidata":"https://www.wikidata.org/wiki/Q1211721","display_name":"Code coverage","level":3,"score":0.25589999556541443},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.25360000133514404},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.251800000667572},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccad66269.2025.11241003","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad66269.2025.11241003","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM International Conference On Computer Aided Design (ICCAD)","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":14,"referenced_works":["https://openalex.org/W2204383650","https://openalex.org/W2763110165","https://openalex.org/W4402667093","https://openalex.org/W4402683806","https://openalex.org/W4403023622","https://openalex.org/W4404134046","https://openalex.org/W4406014556","https://openalex.org/W4409285487","https://openalex.org/W4410582555","https://openalex.org/W4411203706","https://openalex.org/W4412889664","https://openalex.org/W4414197610","https://openalex.org/W4414281281","https://openalex.org/W4416037343"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,196,217],"code":[3,49,215],"generation":[4,188,216],"have":[5],"shown":[6],"remarkable":[7],"success":[8],"across":[9],"software":[10],"domains,":[11],"yet":[12],"hardware":[13],"description":[14],"languages":[15],"(HDLs)":[16],"such":[17,152],"as":[18,153],"Verilog":[19,48,62,187],"remain":[20],"underexplored":[21],"due":[22],"to":[23,97,107,149],"their":[24],"concurrency":[25],"semantics,":[26],"syntactic":[27],"rigidity,":[28],"and":[29,70,79,94,101,111,144,162,202],"simulation":[30],"complexity.":[31],"In":[32,147],"this":[33],"work,":[34],"we":[35,83,116],"address":[36],"these":[37],"challenges":[38],"by":[39],"introducing":[40],"a":[41,55,85,118,176],"reinforcement":[42],"learning":[43,125],"(RL)":[44],"framework":[45],"tailored":[46],"for":[47,213],"generation.":[50],"We":[51],"first":[52],"construct":[53],"Veribench-53K,":[54],"high-quality":[56,179],"dataset":[57,180],"curated":[58],"from":[59],"over":[60],"700K":[61],"problems,":[63],"enriched":[64],"with":[65,167,182,193],"structured":[66,214],"prompts,":[67],"complexity":[68],"labels,":[69],"diverse":[71],"testbenches.":[72],"To":[73],"tackle":[74],"the":[75,142,208],"problem":[76],"of":[77,210],"sparse":[78,168],"noisy":[80],"reward":[81,103,145],"signals,":[82],"propose":[84],"Trace-back":[86],"based":[87,127],"Rescore":[88],"mechanism":[89],"that":[90,122,140,165],"leverages":[91],"reasoning":[92],"paths":[93],"iterative":[95,137],"refinement":[96],"enhance":[98],"feedback":[99],"reliability":[100],"support":[102],"model":[104,160],"training.":[105],"Furthermore,":[106],"mitigate":[108],"catastrophic":[109],"forgetting":[110],"overfitting":[112],"during":[113],"RL":[114,138,183],"fine-tuning,":[115],"introduce":[117],"sample-balanced":[119],"weighting":[120],"strategy":[121],"adaptively":[123],"balances":[124],"dynamics":[126],"on":[128,157,186],"reward-probability":[129],"distributions.":[130],"These":[131],"innovations":[132],"are":[133],"integrated":[134],"into":[135],"an":[136],"pipeline":[139],"co-evolves":[141],"policy":[143],"models.":[146],"contrast":[148],"recent":[150],"work":[151],"CraftRTL,":[154],"which":[155],"relies":[156],"large-scale":[158],"closed-source":[159],"distillation,":[161],"DeepSeekstyle":[163],"approaches":[164,212],"struggle":[166],"feedback,":[169],"our":[170],"method":[171],"demonstrates":[172],"superior":[173],"performance":[174],"using":[175],"smaller":[177],"but":[178],"combined":[181],"optimization.":[184],"Experiments":[185],"tasks":[189],"demonstrate":[190],"state-of-the-art":[191],"performance,":[192],"substantial":[194],"gains":[195],"test":[197],"pass":[198],"rate,":[199],"functional":[200],"correctness,":[201],"compilation":[203],"robustness.":[204],"Our":[205],"findings":[206],"highlight":[207],"potential":[209],"RL-driven":[211],"hardware-centric":[218],"domains.":[219],"VeriRL":[220],"is":[221],"publicly":[222],"available":[223],"at":[224],"https://github.com/omniAI-Lab/VeriRL.":[225]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-20T00:00:00"}