{"id":"https://openalex.org/W7163708138","doi":"https://doi.org/10.48550/arxiv.2606.05253","title":"Alpha-RTL: Test-Time Training for RTL Hardware Optimization","display_name":"Alpha-RTL: Test-Time Training for RTL Hardware Optimization","publication_year":2026,"publication_date":"2026-06-03","ids":{"openalex":"https://openalex.org/W7163708138","doi":"https://doi.org/10.48550/arxiv.2606.05253"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.05253","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.05253","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2606.05253","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137965391","display_name":"Peilong Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Peilong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101914034","display_name":"Zhirong Chen","orcid":"https://orcid.org/0009-0001-7039-7707"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Zhirong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012732979","display_name":"Cangyuan Li","orcid":"https://orcid.org/0000-0002-7193-464X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Cangyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137991745","display_name":"Haoyu Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Haoyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137988880","display_name":"Kaiyan Chang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chang, Kaiyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137998761","display_name":"Ziming Qu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qu, Ziming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137975481","display_name":"Ying Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Ying","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":0.6444000005722046,"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":0.6444000005722046,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.0778999999165535,"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":0.04910000041127205,"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/executable","display_name":"Executable","score":0.692799985408783},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.5677000284194946},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5636000037193298},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4569000005722046},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.33730000257492065},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.3156999945640564}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7371000051498413},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.692799985408783},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.5677000284194946},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5636000037193298},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4569000005722046},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3693999946117401},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.33009999990463257},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.30090001225471497},{"id":"https://openalex.org/C154690210","wikidata":"https://www.wikidata.org/wiki/Q1668499","display_name":"Rewriting","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.26919999718666077},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2639999985694885},{"id":"https://openalex.org/C58013763","wikidata":"https://www.wikidata.org/wiki/Q5754574","display_name":"High-level synthesis","level":3,"score":0.25870001316070557},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2574999928474426},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.05253","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.05253","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.05253","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.05253","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"have":[4],"shown":[5],"increasing":[6],"promise":[7],"in":[8],"generating":[9],"functionally":[10],"correct":[11],"register-transfer-level":[12],"(RTL)":[13],"hardware":[14],"designs.":[15],"Recent":[16],"systems":[17],"improve":[18],"further":[19],"through":[20,104,119],"EDA-integrated":[21],"reinforcement":[22,49],"learning":[23,50],"with":[24,42,128,224],"syntax,":[25],"simulation,":[26,108],"and":[27,91,107,124,159,205,213],"PPA":[28,114,173],"rewards,":[29,141],"but":[30],"train":[31],"a":[32,43,120,201],"general":[33],"RTL":[34,67,96,231],"generator":[35],"before":[36],"deployment":[37],"while":[38],"test-time":[39,80,222],"approaches":[40],"search":[41],"frozen":[44],"policy.":[45],"We":[46,71],"instead":[47],"perform":[48],"at":[51,69,187],"test":[52],"time,":[53],"allowing":[54],"the":[55,65,77,85,126,150,171,178,181],"LLM":[56,89],"policy":[57,90,127,135,209],"to":[58,60,74],"adapt":[59],"executable":[61,225],"EDA":[62,93,226],"feedback":[63,227],"for":[64,95],"specific":[66],"problem":[68],"hand.":[70],"propose":[72],"TTT-RTL,":[73],"our":[75],"knowledge":[76],"first":[78],"per-design":[79],"training":[81,223],"framework":[82],"that":[83,148,208,221],"closes":[84],"loop":[86],"between":[87],"an":[88,92,129,144,190],"pipeline":[94],"optimization.":[97],"TTT-RTL":[98,169,199],"samples":[99],"candidate":[100],"implementations,":[101],"verifies":[102],"them":[103],"syntax":[105],"checking":[106],"scores":[109],"valid":[110],"designs":[111],"using":[112,153],"synthesis-derived":[113],"product,":[115],"reuses":[116],"high-reward":[117],"variants":[118],"PUCT-indexed":[121],"design-state":[122],"pool,":[123],"updates":[125,136],"entropic":[130],"policy-gradient":[131],"objective.":[132],"To":[133],"stabilize":[134],"under":[137,166,197],"sparse":[138],"or":[139],"plateaued":[140],"we":[142],"introduce":[143],"adaptive":[145],"KL-budget":[146,214],"controller":[147],"adjusts":[149],"entropy":[151],"constraint":[152],"reference":[154],"KL,":[155],"effective":[156],"sample":[157],"size,":[158],"reward":[160],"saturation":[161],"signals.":[162],"On":[163,189],"RTLLM":[164],"v2.0":[165],"Nangate":[167],"45nm,":[168],"reduces":[170],"geometric-mean":[172],"product":[174],"by":[175],"65.1%":[176],"over":[177],"reference,":[179],"outperforming":[180],"strongest":[182],"published":[183],"frozen-policy":[184],"agent":[185],"baseline":[186],"26.1%.":[188],"industrial":[191],"XuanTie":[192],"C910":[193],"FPU":[194],"leading-zero-anticipation":[195],"unit":[196],"Sky130,":[198],"achieves":[200],"59.4%":[202],"ADP":[203],"reduction,":[204],"ablations":[206],"confirm":[207],"adaptation,":[210],"state":[211],"reuse,":[212],"control":[215],"each":[216],"contribute.":[217],"These":[218],"results":[219],"suggest":[220],"can":[228],"move":[229],"LLM-based":[230],"generation":[232],"beyond":[233],"functional":[234],"correctness":[235],"toward":[236],"physically":[237],"optimized":[238],"hardware.":[239]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-06T00:00:00"}