{"id":"https://openalex.org/W7101439360","doi":"https://doi.org/10.48550/arxiv.2510.21407","title":"REvolution: An Evolutionary Framework for RTL Generation driven by Large Language Models","display_name":"REvolution: An Evolutionary Framework for RTL Generation driven by Large Language Models","publication_year":2025,"publication_date":"2025-10-24","ids":{"openalex":"https://openalex.org/W7101439360","doi":"https://doi.org/10.48550/arxiv.2510.21407"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2510.21407","doi":"https://doi.org/10.48550/arxiv.2510.21407","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.21407","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2510.21407","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077052572","display_name":"Kyungjun Min","orcid":"https://orcid.org/0000-0002-4965-5484","observed_orcids":["https://orcid.org/0000-0002-4965-5484"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min, Kyungjun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128786413","display_name":"Kyumin Cho","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cho, Kyumin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128723060","display_name":"Junhwan Jang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jang, Junhwan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5044543389","display_name":"Seokhyeong Kang","orcid":"https://orcid.org/0000-0003-3015-1806","observed_orcids":["https://orcid.org/0000-0003-3015-1806"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kang, Seokhyeong","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":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.6991999745368958,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.6991999745368958,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.19740000367164612,"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/T11522","display_name":"VLSI and FPGA Design Techniques","score":0.08009999990463257,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/large-language-models","display_name":"large language models","score":0.9810000061988831},{"id":"https://openalex.org/keywords/evolutionary-computation","display_name":"evolutionary computation","score":0.9559999704360962},{"id":"https://openalex.org/keywords/verilog","display_name":"Verilog","score":0.5329999923706055},{"id":"https://openalex.org/keywords/prompt-strategies","display_name":"prompt strategies","score":0.5040000081062317},{"id":"https://openalex.org/keywords/hardware-design-automation","display_name":"hardware design automation","score":0.6340000033378601},{"id":"https://openalex.org/keywords/functional-correctness","display_name":"functional correctness","score":0.6169999837875366},{"id":"https://openalex.org/keywords/bug-fixing","display_name":"bug fixes","score":0.5180000066757202}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7495999932289124},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7369999885559082},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.48089998960494995},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.48030000925064087},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4578999876976013},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4108999967575073},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.391400009393692},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3880000114440918},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3817000091075897},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.37279999256134033},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.36730000376701355},{"id":"https://openalex.org/C105902424","wikidata":"https://www.wikidata.org/wiki/Q1197129","display_name":"Evolutionary computation","level":2,"score":0.35100001096725464},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.3449999988079071},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3441999852657318},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3294999897480011},{"id":"https://openalex.org/C184408114","wikidata":"https://www.wikidata.org/wiki/Q1502022","display_name":"Generative Design","level":3,"score":0.3292999863624573},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.31790000200271606},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.296099990606308},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2930000126361847},{"id":"https://openalex.org/C8880873","wikidata":"https://www.wikidata.org/wiki/Q187787","display_name":"Genetic algorithm","level":2,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2510.21407","doi":"https://doi.org/10.48550/arxiv.2510.21407","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.21407","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,"listed_in":[],"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:10.48550/arxiv.2510.21407","doi":"https://doi.org/10.48550/arxiv.2510.21407","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.21407","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"are":[4,35],"used":[5],"for":[6,60,99,169],"Register-Transfer":[7],"Level":[8],"(RTL)":[9],"code":[10],"generation,":[11],"but":[12,33],"they":[13,34],"face":[14],"two":[15],"main":[16],"challenges:":[17],"functional":[18],"correctness":[19],"and":[20,23,64,82,96,102,132],"Power,":[21],"Performance,":[22],"Area":[24],"(PPA)":[25],"optimization.":[26,65],"Iterative,":[27],"feedback-based":[28],"methods":[29],"partially":[30],"address":[31],"these,":[32],"limited":[36],"to":[37,124,148,163],"local":[38],"search,":[39],"hindering":[40],"the":[41,116,130,139,167,176,206],"discovery":[42],"of":[43,70,119,143,160,209],"a":[44,51,68,77,88,156,190],"global":[45],"optimum.":[46],"This":[47,187],"paper":[48],"introduces":[49,189],"REvolution,":[50],"framework":[52,86],"that":[53,91,136],"combines":[54],"Evolutionary":[55],"Computation":[56],"(EC)":[57],"with":[58,200],"LLMs":[59,145],"automatic":[61],"RTL":[62,80,178,192],"generation":[63],"REvolution":[66,137],"evolves":[67],"population":[69],"candidates":[71,93],"in":[72],"parallel,":[73],"each":[74,120],"defined":[75],"by":[76,113,146,195],"design":[78,193],"strategy,":[79],"implementation,":[81],"evaluation":[83],"feedback.":[84],"The":[85,152],"includes":[87],"dual-population":[89],"algorithm":[90],"divides":[92],"into":[94],"Fail":[95],"Success":[97],"groups":[98],"bug":[100],"fixing":[101],"PPA":[103,182],"optimization,":[104],"respectively.":[105],"An":[106],"adaptive":[107],"mechanism":[108],"further":[109],"improves":[110],"search":[111,203],"efficiency":[112],"dynamically":[114],"adjusting":[115],"selection":[117],"probability":[118],"prompt":[121],"strategy":[122],"according":[123],"its":[125],"success":[126],"rate.":[127],"Experiments":[128],"on":[129],"VerilogEval":[131],"RTLLM":[133],"benchmarks":[134],"show":[135],"increased":[138],"initial":[140],"pass":[141,158],"rate":[142,159],"various":[144],"up":[147],"24.0":[149],"percentage":[150],"points.":[151],"DeepSeek-V3":[153],"model":[154],"achieved":[155],"final":[157],"95.5\\%,":[161],"comparable":[162],"state-of-the-art":[164],"results,":[165],"without":[166],"need":[168],"separate":[170],"training":[171],"or":[172],"domain-specific":[173],"tools.":[174],"Additionally,":[175],"generated":[177],"designs":[179],"showed":[180],"significant":[181],"improvements":[183],"over":[184],"reference":[185],"designs.":[186],"work":[188],"new":[191],"approach":[194],"combining":[196],"LLMs'":[197],"generative":[198],"capabilities":[199],"EC's":[201],"broad":[202],"power,":[204],"overcoming":[205],"local-search":[207],"limitations":[208],"previous":[210],"methods.":[211]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-28T00:00:00"}