{"id":"https://openalex.org/W7159598366","doi":"https://doi.org/10.48550/arxiv.2604.27366","title":"Judge, Then Drive: A Critic-Centric Vision Language Action Framework for Autonomous Driving","display_name":"Judge, Then Drive: A Critic-Centric Vision Language Action Framework for Autonomous Driving","publication_year":2026,"publication_date":"2026-04-30","ids":{"openalex":"https://openalex.org/W7159598366","doi":"https://doi.org/10.48550/arxiv.2604.27366"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.27366","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.27366","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.2604.27366","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006040497","display_name":"Lijin Yang","orcid":"https://orcid.org/0000-0003-3787-6658"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Lijin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134988203","display_name":"Jianing Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Jianing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134952938","display_name":"Zhongzhan Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Zhongzhan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134985086","display_name":"Shu Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Shu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134951423","display_name":"Hao Yang (328526)","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Hao","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9502000212669373,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9502000212669373,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.00430000014603138,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0038999998942017555,"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/limiting","display_name":"Limiting","score":0.6912999749183655},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.651199996471405},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6506999731063843},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6194999814033508},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5774999856948853},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4731999933719635},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.38199999928474426}],"concepts":[{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.6912999749183655},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6736999750137329},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.651199996471405},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6506999731063843},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6194999814033508},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6018999814987183},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5774999856948853},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4731999933719635},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4293999969959259},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.38199999928474426},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.36469998955726624},{"id":"https://openalex.org/C87833898","wikidata":"https://www.wikidata.org/wiki/Q1060280","display_name":"Advanced driver assistance systems","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.32350000739097595},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2736000120639801},{"id":"https://openalex.org/C3018391801","wikidata":"https://www.wikidata.org/wiki/Q741490","display_name":"Self driving","level":2,"score":0.2718999981880188}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.27366","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.27366","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.2604.27366","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.27366","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":[{"id":"https://metadata.un.org/sdg/16","score":0.614490270614624,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,48,56,158],"vision":[3],"language":[4],"action":[5],"(VLA)":[6],"models":[7],"have":[8,27],"shown":[9],"remarkable":[10],"potential":[11],"for":[12],"autonomous":[13],"driving":[14,38,104,123],"by":[15,98],"directly":[16],"mapping":[17],"multimodal":[18,92],"inputs":[19],"to":[20,36,79],"control":[21],"signals.":[22],"However,":[23],"previous":[24],"VLA-based":[25,100],"methods":[26],"not":[28],"explicitly":[29],"exploited":[30],"the":[31,73,127,137],"critic":[32],"capability":[33,43],"of":[34,75,116],"VLAs":[35,76],"refine":[37],"decisions,":[39],"even":[40],"though":[41],"such":[42],"has":[44],"been":[45],"well":[46],"demonstrated":[47],"other":[49],"LLM-based":[50],"domains,":[51],"thereby":[52],"limiting":[53],"their":[54],"performance":[55],"complex":[57],"closed-loop":[58,134],"scenarios.":[59,160],"In":[60],"this":[61,108],"work,":[62],"we":[63,110],"present":[64],"a":[65,84,99,112,148],"theoretically":[66],"inspired":[67],"two-stage":[68],"framework,":[69],"CriticVLA,":[70],"which":[71,125],"extends":[72],"role":[74],"from":[77],"acting":[78],"judging.":[80],"CriticVLA":[81,142],"first":[82],"generates":[83],"rough":[85],"trajectory":[86],"and":[87,94,130,153],"then":[88],"refines":[89],"it":[90],"through":[91],"evaluation":[93],"single-step":[95],"optimization":[96],"guided":[97],"critic,":[101],"yielding":[102],"higher-quality":[103],"behaviors.":[105],"To":[106],"support":[107],"process,":[109],"construct":[111],"large-scale":[113],"synthetic":[114],"dataset":[115],"12.9":[117],"million":[118],"annotated":[119],"trajectories":[120],"covering":[121],"diverse":[122],"scenarios,":[124],"enhances":[126],"critic's":[128],"reasoning":[129],"refinement":[131],"abilities.":[132],"Extensive":[133],"experiments":[135],"on":[136],"Bench2Drive":[138],"benchmark":[139],"show":[140],"that":[141],"significantly":[143],"surpasses":[144],"state-of-the-art":[145],"baselines,":[146],"achieving":[147],"73.33%":[149],"total":[150],"success":[151],"rate":[152],"delivering":[154],"about":[155],"30%":[156],"improvement":[157],"challenging":[159]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-02T00:00:00"}