{"id":"https://openalex.org/W7164521445","doi":"https://doi.org/10.48550/arxiv.2606.12616","title":"PersonaDrive: Human-Style Retrieval-Augmented VLA Agents for Closed-Loop Driving Simulation","display_name":"PersonaDrive: Human-Style Retrieval-Augmented VLA Agents for Closed-Loop Driving Simulation","publication_year":2026,"publication_date":"2026-06-10","ids":{"openalex":"https://openalex.org/W7164521445","doi":"https://doi.org/10.48550/arxiv.2606.12616"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.12616","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.12616","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":"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.2606.12616","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5117419829","display_name":"Mahmoud Srewa","orcid":"https://orcid.org/0009-0004-4795-4116"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Srewa, Mahmoud","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138500813","display_name":"Praneetsai Iddamsetty","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Iddamsetty, Praneetsai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138503046","display_name":"Mohammad Abdullah Al Faruque","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Faruque, Mohammad Abdullah Al","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038820344","display_name":"Salma Elmalaki","orcid":"https://orcid.org/0000-0002-0969-0197"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elmalaki, Salma","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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.40880000591278076,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.40880000591278076,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.20479999482631683,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.08299999684095383,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/context","display_name":"Context (archaeology)","score":0.6068999767303467},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5586000084877014},{"id":"https://openalex.org/keywords/retraining","display_name":"Retraining","score":0.49540001153945923},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4684000015258789},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4124000072479248},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.3921999931335449},{"id":"https://openalex.org/keywords/driving-simulator","display_name":"Driving simulator","score":0.36660000681877136}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7067000269889832},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6068999767303467},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5586000084877014},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.49540001153945923},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4684000015258789},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4569000005722046},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4124000072479248},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.3921999931335449},{"id":"https://openalex.org/C2780689630","wikidata":"https://www.wikidata.org/wiki/Q2081815","display_name":"Driving simulator","level":2,"score":0.36660000681877136},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36149999499320984},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3116999864578247},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30149999260902405},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.2903999984264374},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C176809094","wikidata":"https://www.wikidata.org/wiki/Q15401496","display_name":"Traverse","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2606000006198883}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.12616","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.12616","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":"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.2606.12616","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.12616","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":"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":{"Closed-loop":[0],"driving":[1,82,91,122,211,228],"simulators":[2],"typically":[3],"populate":[4],"their":[5],"environments":[6],"with":[7,141],"non-ego":[8,199],"traffic":[9,21],"agents":[10,200],"that":[11,70,77,136],"behave":[12],"largely":[13],"the":[14,170,183,210,226,242,259,262],"same":[15,171],"way,":[16],"produced":[17],"either":[18],"by":[19,24,178,213,246,254],"rule-based":[20],"managers":[22],"or":[23,44],"learned":[25],"models":[26],"trained":[27],"toward":[28],"a":[29,56,75,79,88,107,125,132,142,152,189,234],"single":[30,153],"behavioral":[31,163],"mode.":[32],"Recent":[33],"work":[34],"introduces":[35],"style":[36,57,177,190,223,232,240],"variation":[37],"through":[38],"post-hoc":[39],"labels":[40],"on":[41,84,106,175],"observational":[42],"data":[43,123],"LLM-inferred":[45],"reward":[46,59],"weights,":[47],"but":[48],"these":[49],"signals":[50],"act":[51],"as":[52,161],"proxies":[53],"for":[54,201],"what":[55],"should":[58],"rather":[60],"than":[61],"demonstrations":[62,86,164],"of":[63],"humans":[64],"explicitly":[65],"asked":[66],"to":[67,156,261],"drive":[68,96],"in":[69,93,230],"style.":[71],"We":[72],"introduce":[73],"PersonaDrive,":[74],"pipeline":[76,111],"conditions":[78],"vision-language-action":[80],"(VLA)":[81],"agent":[83],"retrieved":[85,158],"from":[87,258],"style-instructed":[89],"human":[90,121],"dataset,":[92],"which":[94,180],"participants":[95],"CARLA":[97],"leaderboard":[98],"routes":[99],"under":[100,222],"aggressive,":[101],"neutral,":[102],"and":[103,149,217,221,251,256],"conservative":[104,260],"instructions":[105],"driver-in-the-loop":[108],"rig.":[109],"The":[110],"has":[112],"three":[113],"stages:":[114],"(i)":[115],"offline":[116],"triplet":[117],"mining":[118],"over":[119,146,215,219],"per-style":[120,147,181,193],"using":[124],"combined":[126],"image-text":[127],"similarity":[128],"score;":[129],"(ii)":[130],"training":[131],"lightweight":[133],"retrieval":[134,184],"head":[135,185],"fuses":[137],"frozen":[138],"visual":[139],"features":[140],"small":[143],"control":[144],"encoder":[145],"databases;":[148],"(iii)":[150],"fine-tuning":[151],"VLA":[154],"backbone":[155,172],"treat":[157],"context":[159],"points":[160],"in-context":[162],"during":[165],"waypoint":[166],"prediction.":[167],"At":[168],"inference,":[169],"is":[173],"conditioned":[174],"any":[176],"swapping":[179],"database":[182],"queries,":[186],"so":[187],"selecting":[188],"requires":[191],"no":[192],"retraining":[194],"while":[195,248],"enabling":[196],"human-style,":[197],"style-diverse":[198],"closed-loop":[202],"simulation.":[203],"On":[204],"Bench2Drive,":[205],"PersonaDrive":[206],"(no":[207],"style)":[208],"improves":[209],"score":[212,229],"4.6%":[214],"SimLingo":[216],"2.5%":[218],"HiP-AD,":[220],"conditioning":[224],"attains":[225],"highest":[227],"every":[231],"within":[233],"roughly":[235],"2%":[236],"band":[237],"(its":[238],"weakest":[239],"surpassing":[241],"strongest":[243],"baseline,":[244],"DMW,":[245],"5.4%),":[247],"average":[249],"speed":[250],"acceleration":[252],"rise":[253],"18%":[255],"25%":[257],"aggressive":[263],"instruction.":[264]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-13T00:00:00"}