{"id":"https://openalex.org/W7212106900","doi":"https://doi.org/10.48550/arxiv.2609.09519","title":"HLSFactory-Agent: Large-Scale Agentic HLS Dataset Construction from Academic and Open-Source Projects","display_name":"HLSFactory-Agent: Large-Scale Agentic HLS Dataset Construction from Academic and Open-Source Projects","publication_year":2026,"publication_date":"2026-09-08","ids":{"openalex":"https://openalex.org/W7212106900","doi":"https://doi.org/10.48550/arxiv.2609.09519"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2609.09519","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.09519","pdf_url":"https://arxiv.org/pdf/2609.09519","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.09519","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5151126286","display_name":"Kaushik Chandana","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chandana, Kaushik","raw_affiliation_strings":["Georgia Institute of Technology , Atlanta , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology , Atlanta , USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5151229473","display_name":"Jay Imperatori","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Imperatori, Jay","raw_affiliation_strings":["Georgia Institute of Technology , Atlanta , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology , Atlanta , USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093798441","display_name":"Tanmay Shukla","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shukla, Tanmay","raw_affiliation_strings":["Georgia Institute of Technology , Atlanta , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology , Atlanta , USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5151135131","display_name":"Justin Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhou, Justin","raw_affiliation_strings":["Georgia Institute of Technology , Atlanta , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology , Atlanta , USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076244218","display_name":"Stefan Abi-Karam","orcid":"https://orcid.org/0000-0002-6697-8517","observed_orcids":["https://orcid.org/0000-0002-6697-8517"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"id":"https://openalex.org/I4388482740","display_name":"Georgia Tech Research Institute","ror":"https://ror.org/04qfrh333","country_code":null,"type":"facility","lineage":["https://openalex.org/I130701444","https://openalex.org/I4388482740"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abi-Karam, Stefan","raw_affiliation_strings":["Georgia Institute of Technology , Atlanta , USA","Georgia Tech Research Institute , Atlanta , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology , Atlanta , USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Tech Research Institute , Atlanta , USA","institution_ids":["https://openalex.org/I4388482740"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5095094671","display_name":"Callie Hao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao, Callie","raw_affiliation_strings":["Georgia Institute of Technology , Atlanta , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology , Atlanta , USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.9994999766349792,"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":0.9994999766349792,"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/T11522","display_name":"VLSI and FPGA Design Techniques","score":0.0,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.0,"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/high-level-synthesis","display_name":"high-level synthesis","score":0.9769999980926514},{"id":"https://openalex.org/keywords/data-curation","display_name":"data curation","score":0.7870000004768372},{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.8799999952316284},{"id":"https://openalex.org/keywords/open-source-hardware","display_name":"open-source hardware","score":0.5049999952316284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6879000067710876},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.6413000226020813},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.492900013923645},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4794999957084656},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.4366999864578247},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.42559999227523804},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.4196000099182129},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.413100004196167},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.36250001192092896},{"id":"https://openalex.org/C2777683733","wikidata":"https://www.wikidata.org/wiki/Q201456","display_name":"Directory","level":2,"score":0.35120001435279846},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.35089999437332153},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3352999985218048},{"id":"https://openalex.org/C64260653","wikidata":"https://www.wikidata.org/wiki/Q1194864","display_name":"Electronic design automation","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C2780615140","wikidata":"https://www.wikidata.org/wiki/Q920419","display_name":"Upgrade","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.3124000132083893},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3102000057697296},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3012999892234802},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C58013763","wikidata":"https://www.wikidata.org/wiki/Q5754574","display_name":"High-level synthesis","level":3,"score":0.2994999885559082},{"id":"https://openalex.org/C2777002779","wikidata":"https://www.wikidata.org/wiki/Q42478","display_name":"Perl","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.29510000348091125},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28110000491142273},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2655999958515167},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C154690210","wikidata":"https://www.wikidata.org/wiki/Q1668499","display_name":"Rewriting","level":2,"score":0.2554999887943268}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.09519","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.09519","pdf_url":"https://arxiv.org/pdf/2609.09519","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.09519","doi":"https://doi.org/10.48550/arxiv.2609.09519","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.09519","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":"pmh:oai:arXiv.org:2609.09519","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.09519","pdf_url":"https://arxiv.org/pdf/2609.09519","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7212106900.pdf","grobid_xml":"https://content.openalex.org/works/W7212106900.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Building":[0],"large,":[1],"diverse":[2],"datasets":[3,36],"of":[4,25,148,192,208,215],"high-level":[5],"synthesis":[6],"(HLS)":[7],"designs":[8,62,72,108,151,194,217],"beyond":[9],"common":[10],"community":[11],"benchmarks":[12],"remains":[13],"an":[14,96],"open":[15,67,222],"challenge.":[16],"This":[17,129],"challenge":[18],"is":[19,78],"made":[20],"urgent":[21],"by":[22,105],"the":[23,114,157],"rise":[24],"deep":[26],"learning":[27],"and":[28,41,66,80,86,124,144,168,175,190,225],"LLMs":[29,43],"for":[30,186,195],"hardware":[31],"design,":[32],"which":[33],"demand":[34],"such":[35],"to":[37,50,122,134,142,153,166],"train":[38],"QoR":[39],"models":[40],"benchmark":[42],"on":[44,57],"HLS":[45,61,102,150,183,193],"tasks.":[46],"Despite":[47],"ongoing":[48],"efforts":[49],"broaden":[51],"sources,":[52],"dataset":[53,103,159],"curation":[54,104,191],"still":[55],"depends":[56],"manual":[58],"work:":[59],"locating":[60],"across":[63,204],"academic":[64],"publications":[65],"source,":[68],"then":[69],"extracting":[70,106],"standalone":[71,107],"from":[73,109,171,201,218],"larger":[74,110],"codebases.":[75,111,220],"The":[76],"process":[77],"error-prone":[79],"demands":[81],"expert":[82],"knowledge,":[83],"iterative":[84],"testing,":[85],"substantial":[87],"per-repository":[88],"engineering.":[89],"To":[90],"address":[91],"this,":[92],"we":[93,162],"present":[94],"HLSFactory-Agent,":[95],"LLM":[97],"agent":[98,117],"that":[99,178],"automates":[100],"large-scale":[101],"HLSFactory-Agent":[112,143,203,224],"runs":[113],"open-source":[115,164],"Pi":[116],"framework":[118],"inside":[119],"Docker":[120],"containers":[121],"build":[123],"evaluate":[125],"each":[126],"extracted":[127,149],"design.":[128],"turnkey":[130],"automation":[131],"allows":[132],"users":[133],"pass":[135],"a":[136,146,205],"GitHub":[137],"link":[138],"or":[139,181],"code":[140],"directory":[141],"receive":[145],"folder":[147],"ready":[152],"be":[154],"integrated":[155],"into":[156],"HLSFactory":[158],"framework.":[160],"Additionally,":[161],"provide":[163],"scripts":[165,227],"scrape":[167],"index":[169],"papers":[170],"computer":[172],"architecture,":[173],"EDA,":[174],"FPGA":[176],"conferences":[177],"possibly":[179],"implement":[180],"use":[182],"designs,":[184],"allowing":[185],"faster":[187],"human":[188],"discovery":[189],"HLSFactory-Agent.":[196],"We":[197,221],"report":[198],"initial":[199],"results":[200],"running":[202],"small":[206],"subset":[207],"our":[209],"indexed":[210],"repositories,":[211],"demonstrating":[212],"successful":[213],"extraction":[214],"synthesizable":[216],"structured":[219],"source":[223],"indexing":[226],"at":[228],"https://github.com/sharc-lab/hlsfactory-agent.":[229]},"counts_by_year":[],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2026-09-11T00:00:00"}
