{"id":"https://openalex.org/W7147458481","doi":"https://doi.org/10.48550/arxiv.2603.27630","title":"RTLSeek: Boosting the LLM-Based RTL Generation with Multi-Stage Diversity-Oriented Reinforcement Learning","display_name":"RTLSeek: Boosting the LLM-Based RTL Generation with Multi-Stage Diversity-Oriented Reinforcement Learning","publication_year":2026,"publication_date":"2026-03-29","ids":{"openalex":"https://openalex.org/W7147458481","doi":"https://doi.org/10.48550/arxiv.2603.27630"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.27630","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.27630","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.27630","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5132658838","display_name":"Xinyu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xinyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132683737","display_name":"Zhiteng Chao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao, Zhiteng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132590681","display_name":"Yonghao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yonghao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132634844","display_name":"Bin Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Bin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132551753","display_name":"Tianyun Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Tianyun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132674227","display_name":"Tianmeng Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Tianmeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010522760","display_name":"Jianan Mu","orcid":"https://orcid.org/0000-0001-8513-0792"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mu, Jianan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132642452","display_name":"Jing Justin Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Jing Justin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5132643389","display_name":"Huawei Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Huawei","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":false,"primary_topic":{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.37540000677108765,"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":0.37540000677108765,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.26499998569488525,"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"}},{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.15060000121593475,"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/boosting","display_name":"Boosting (machine learning)","score":0.7027000188827515},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.641700029373169},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5895000100135803},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.44119998812675476},{"id":"https://openalex.org/keywords/high-level-synthesis","display_name":"High-level synthesis","score":0.35269999504089355},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.31279999017715454},{"id":"https://openalex.org/keywords/verifiable-secret-sharing","display_name":"Verifiable secret sharing","score":0.2939999997615814}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7980999946594238},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.7027000188827515},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.641700029373169},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5895000100135803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47920000553131104},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.44119998812675476},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4235999882221222},{"id":"https://openalex.org/C58013763","wikidata":"https://www.wikidata.org/wiki/Q5754574","display_name":"High-level synthesis","level":3,"score":0.35269999504089355},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.2939999997615814},{"id":"https://openalex.org/C157922185","wikidata":"https://www.wikidata.org/wiki/Q173198","display_name":"Logic synthesis","level":3,"score":0.28700000047683716},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.2793999910354614},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.27649998664855957},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C36941000","wikidata":"https://www.wikidata.org/wiki/Q209455","display_name":"VHDL","level":3,"score":0.26510000228881836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.27630","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.27630","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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:10.48550/arxiv.2603.27630","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.27630","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Register":[0],"Transfer":[1],"Level":[2],"(RTL)":[3],"design":[4,51],"translates":[5],"high-level":[6],"specifications":[7],"into":[8],"hardware":[9],"using":[10],"HDLs":[11],"such":[12],"as":[13],"Verilog.":[14],"Although":[15],"LLM-based":[16],"RTL":[17,46,67,113],"generation":[18],"is":[19,136],"promising,":[20],"the":[21,87,94,117,123,129],"scarcity":[22],"of":[23,45,89,119],"functionally":[24],"verifiable":[25],"high-quality":[26],"data":[27],"limits":[28],"both":[29],"accuracy":[30],"and":[31,69,82,115,133],"diversity.":[32,70],"Existing":[33],"post-training":[34,57],"typically":[35],"produces":[36],"a":[37,56,83],"single":[38],"HDL":[39],"implementation":[40],"per":[41],"specification,":[42],"lacking":[43],"awareness":[44],"variations":[47],"needed":[48],"for":[49],"different":[50],"goals.":[52],"We":[53],"propose":[54],"RTLSeek,":[55],"paradigm":[58],"that":[59,98,107],"applies":[60],"rule-based":[61],"Diversity-Oriented":[62],"Reinforcement":[63],"Learning":[64],"to":[65],"improve":[66],"correctness":[68],"Our":[71],"Diversity-Centric":[72],"Multi-Objective":[73],"Reward":[74],"Scheduling":[75],"integrates":[76],"expert":[77],"knowledge":[78],"with":[79,103],"EDA":[80],"feedback,":[81],"three-stage":[84],"framework":[85],"maximizes":[86],"utility":[88],"limited":[90],"data.":[91],"Experiments":[92],"on":[93],"RTLLM":[95],"benchmark":[96],"show":[97],"RTLSeek":[99],"surpasses":[100],"prior":[101],"methods,":[102],"ablation":[104],"results":[105],"confirming":[106],"encouraging":[108],"broader":[109],"design-space":[110],"exploration":[111],"improves":[112],"quality":[114],"achieves":[116],"principle":[118],"\"the":[120],"more":[121],"generated,":[122],"better":[124],"results.\"":[125],"Implementation":[126],"framework,":[127],"including":[128],"dataset,":[130],"source":[131],"code,":[132],"model":[134],"weights,":[135],"shown":[137],"at":[138],"https://anonymous.4open.science/r/DAC2026ID71-ACB4/.":[139]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-02T00:00:00"}