{"id":"https://openalex.org/W4417300100","doi":"https://doi.org/10.1145/3787109.3815310","title":"VeriReason: Reinforcement Learning with Testbench Feedback for Reasoning-Enhanced Verilog Generation","display_name":"VeriReason: Reinforcement Learning with Testbench Feedback for Reasoning-Enhanced Verilog Generation","publication_year":2026,"publication_date":"2026-06-18","ids":{"openalex":"https://openalex.org/W4417300100","doi":"https://doi.org/10.1145/3787109.3815310"},"language":"en","primary_location":{"id":"doi:10.1145/3787109.3815310","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3787109.3815310","pdf_url":null,"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 Great Lakes Symposium on VLSI 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3787109.3815310","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yiting Wang","orcid":"https://orcid.org/0009-0000-2614-0341"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiting Wang","raw_affiliation_strings":["University of Maryland, College Park, MD, USA"],"raw_orcid":"https://orcid.org/0009-0000-2614-0341","affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101230023","display_name":"Guoheng Sun","orcid":"https://orcid.org/0009-0004-4346-8516"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guoheng Sun","raw_affiliation_strings":["University of Maryland, College Park, USA"],"raw_orcid":"https://orcid.org/0009-0004-4346-8516","affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019313718","display_name":"Wenjing Ye","orcid":"https://orcid.org/0000-0003-1001-8880"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wanghao Ye","raw_affiliation_strings":["University of Maryland, College Park, MD, USA"],"raw_orcid":"https://orcid.org/0009-0002-7064-2335","affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012474783","display_name":"Gang Qu","orcid":"https://orcid.org/0000-0001-6759-8949"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gang Qu","raw_affiliation_strings":["University of Maryland, College Park, USA"],"raw_orcid":"https://orcid.org/0000-0001-6759-8949","affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100413669","display_name":"Ang Li","orcid":"https://orcid.org/0009-0008-2561-8348"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ang Li","raw_affiliation_strings":["University of Maryland, College Park, MD, USA"],"raw_orcid":"https://orcid.org/0000-0002-4990-1729","affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"948","last_page":"953"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12122","display_name":"Physical Unclonable Functions (PUFs) and Hardware Security","score":0.2921999990940094,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T12122","display_name":"Physical Unclonable Functions (PUFs) and Hardware Security","score":0.2921999990940094,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.1103999987244606,"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/T10142","display_name":"Formal Methods in Verification","score":0.06809999793767929,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/correctness","display_name":"Correctness","score":0.7638000249862671},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6518999934196472},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5895000100135803},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.47519999742507935},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4700999855995178},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4203000068664551}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8346999883651733},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7638000249862671},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6518999934196472},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5895000100135803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5256999731063843},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.47519999742507935},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4700999855995178},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42480000853538513},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4203000068664551},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.38040000200271606},{"id":"https://openalex.org/C2779030575","wikidata":"https://www.wikidata.org/wiki/Q827773","display_name":"Verilog","level":3,"score":0.3709999918937683},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3626999855041504},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.2766999900341034},{"id":"https://openalex.org/C110251889","wikidata":"https://www.wikidata.org/wiki/Q1569697","display_name":"Model checking","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.26409998536109924},{"id":"https://openalex.org/C62460635","wikidata":"https://www.wikidata.org/wiki/Q5508853","display_name":"Functional verification","level":3,"score":0.251800000667572},{"id":"https://openalex.org/C42143788","wikidata":"https://www.wikidata.org/wiki/Q173341","display_name":"Hardware description language","level":3,"score":0.2508000135421753}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3787109.3815310","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3787109.3815310","pdf_url":null,"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 Great Lakes Symposium on VLSI 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.11849","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.11849","pdf_url":"https://arxiv.org/pdf/2505.11849","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.11849","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.11849","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3787109.3815310","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3787109.3815310","pdf_url":null,"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 Great Lakes Symposium on VLSI 2026","raw_type":"proceedings-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":{"Automating":[0],"Register":[1],"Transfer":[2],"Level":[3],"(RTL)":[4],"code":[5,81],"generation":[6],"with":[7,61,73,124],"Large":[8],"Language":[9],"Models":[10],"(LLMs)":[11],"can":[12],"reduce":[13],"manual":[14],"hardware":[15],"design":[16],"effort.":[17],"However,":[18],"current":[19],"LLM-based":[20],"approaches":[21],"face":[22],"four":[23],"challenges:":[24],"limited":[25],"availability":[26],"of":[27,41],"high-quality":[28,84],"training":[29,85],"data,":[30],"weak":[31],"alignment":[32],"between":[33],"natural":[34],"language":[35],"specifications":[36],"and":[37,45,93,102,106],"generated":[38],"code,":[39],"lack":[40],"built-in":[42],"verification":[43],"mechanisms,":[44],"difficulty":[46],"in":[47,151],"adapting":[48],"general-purpose":[49],"models":[50],"to":[51,146,156],"RTL-specific":[52],"constraints.":[53],"Inspired":[54],"by":[55],"DeepSeek-R1,":[56],"which":[57],"combines":[58],"reinforcement":[59,125],"learning":[60,126],"reasoning":[62,104,122],"capabilities,":[63],"we":[64],"introduce":[65],"VeriReason,":[66],"a":[67,87,147],"framework":[68],"that":[69,118],"integrates":[70,120],"supervised":[71],"fine-tuning":[72],"Group":[74],"Relative":[75],"Policy":[76],"Optimization":[77],"(GRPO)":[78],"for":[79,127],"RTL":[80],"generation.":[82,129],"Using":[83],"examples,":[86],"feedback-driven":[88],"reward":[89],"model,":[90],"testbench":[91],"evaluation,":[92],"structural":[94],"heuristics,":[95],"VeriReason":[96,113,132],"improves":[97],"specification-code":[98],"alignment,":[99],"reduces":[100],"hallucinations,":[101],"strengthens":[103],"traces":[105],"first-attempt":[107,152],"functional":[108,153],"correctness.":[109],"To":[110],"our":[111],"knowledge,":[112],"is":[114],"the":[115],"first":[116],"system":[117],"successfully":[119],"explicit":[121],"capabilities":[123],"Verilog":[128],"On":[130],"VerilogEval-Machine,":[131],"reaches":[133],"83.1%":[134],"pass@5,":[135],"while":[136],"consistently":[137],"outperforming":[138],"comparable-sized":[139],"open-source":[140],"models.":[141],"Our":[142],"approach":[143],"demonstrates":[144],"up":[145],"2.8":[148],"\u00d7":[149],"increase":[150],"correctness":[154],"compared":[155],"baseline":[157],"methods.":[158]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}