{"id":"https://openalex.org/W7163204375","doi":"https://doi.org/10.48550/arxiv.2606.00053","title":"VLAMotor: Test-Guided Enhancement of Vision-Language-Action Models via Agent-BasedData Synthesis","display_name":"VLAMotor: Test-Guided Enhancement of Vision-Language-Action Models via Agent-BasedData Synthesis","publication_year":2026,"publication_date":"2026-05-16","ids":{"openalex":"https://openalex.org/W7163204375","doi":"https://doi.org/10.48550/arxiv.2606.00053"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.00053","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00053","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.2606.00053","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067714027","display_name":"Zeqin Liao","orcid":"https://orcid.org/0000-0003-0306-7465"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liao, Zeqin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120072370","display_name":"Peifan Ren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren, Peifan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091324096","display_name":"Zixu Gao","orcid":"https://orcid.org/0000-0002-5605-3748"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Zixu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137627602","display_name":"Hongyu Gong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gong, Hongyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137633007","display_name":"Lianyu Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Lianyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022407163","display_name":"Wenbing Tang","orcid":"https://orcid.org/0000-0003-0125-1939"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Wenbing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065097911","display_name":"Yuhong Nan","orcid":"https://orcid.org/0000-0001-9597-9888"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nan, Yuhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137633888","display_name":"Zibin Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Zibin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137683541","display_name":"Yang Liu","orcid":"https://orcid.org/0009-0000-7025-5293"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yang","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/T10653","display_name":"Robot Manipulation and Learning","score":0.4117000102996826,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10653","display_name":"Robot Manipulation and Learning","score":0.4117000102996826,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.061000000685453415,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.05209999904036522,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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":0.6546000242233276},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5899999737739563},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.46630001068115234},{"id":"https://openalex.org/keywords/test-case","display_name":"Test case","score":0.43959999084472656},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.40529999136924744},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.3650999963283539},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.34470000863075256},{"id":"https://openalex.org/keywords/kinematics","display_name":"Kinematics","score":0.34119999408721924}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7027000188827515},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.6546000242233276},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5899999737739563},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.46630001068115234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4478999972343445},{"id":"https://openalex.org/C128942645","wikidata":"https://www.wikidata.org/wiki/Q1568346","display_name":"Test case","level":3,"score":0.43959999084472656},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.4260999858379364},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42170000076293945},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.40529999136924744},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4050000011920929},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.3650999963283539},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.34470000863075256},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.34119999408721924},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.33660000562667847},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C163164238","wikidata":"https://www.wikidata.org/wiki/Q2737027","display_name":"Failure rate","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C3019813237","wikidata":"https://www.wikidata.org/wiki/Q65089264","display_name":"Model validation","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C2779714256","wikidata":"https://www.wikidata.org/wiki/Q25305062","display_name":"Multiple Models","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2529999911785126},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.00053","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00053","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.2606.00053","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00053","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-Language-Action":[0],"(VLA)":[1],"models":[2,202,220,230,239],"follow":[3],"a":[4,58],"data-driven":[5],"paradigm":[6],"and":[7,38,56,85,104,129,144,154,188,245],"are":[8,135,151],"constrained":[9],"by":[10,183,197,221,240],"the":[11,40,70,99,158,178,194,214,228,232,236],"coverage":[12,192],"of":[13,177,218],"training":[14,102],"data,":[15],"making":[16],"them":[17],"prone":[18],"to":[19,33,101,111,156],"failure":[20,36,54,83,123],"on":[21,98,168,225],"edge-case":[22],"configurations":[23],"after":[24],"deployment.":[25],"To":[26],"mitigate":[27],"such":[28],"risks,":[29],"it":[30],"is":[31],"essential":[32],"expose":[34,117],"high-quality":[35],"modes":[37],"convert":[39],"resulting":[41,148],"failures":[42,63],"into":[43,125],"supervisory":[44],"data":[45,87,205],"for":[46,60,64,74,82,89,248],"model":[47,65,80,90],"enhancement.":[48,250],"Existing":[49],"studies":[50],"largely":[51],"stop":[52],"at":[53],"detection":[55],"lack":[57],"mechanism":[59],"leveraging":[61],"discovered":[62],"repair.":[66],"We":[67],"propose":[68],"VLAMotor,":[69],"first":[71],"analysis":[72],"framework":[73],"VLA":[75,160,165,186,201,219,238,249],"enhancement,":[76],"which":[77,134],"integrates":[78],"distance-aware":[79],"testing":[81],"exposure":[84],"agent-based":[86],"synthesis":[88],"finetunning.":[91],"First,":[92],"VLAMotor":[93,121,184,189,211],"estimates":[94],"input":[95],"uncertainty":[96,106],"based":[97],"distance":[100],"samples,":[103],"combines":[105],"ranking":[107],"with":[108,203],"redundancy":[109],"elimination":[110],"build":[112],"compact":[113],"test":[114,180,191,209],"sets":[115],"that":[116,175],"diverse":[118],"failures.":[119],"Then,":[120],"abstracts":[122],"trajectories":[124,140,150],"structured":[126],"semantic":[127],"representations,":[128],"plans":[130],"parameterized":[131],"repair-skill":[132],"sequences,":[133],"then":[136],"realized":[137],"as":[138],"executable":[139],"through":[141],"inverse":[142],"kinematics":[143],"motion":[145],"execution.":[146],"The":[147],"successful":[149],"automatically":[152],"labeled":[153],"used":[155],"fine-tune":[157],"original":[159,237],"model,":[161],"yielding":[162],"an":[163,243],"enhanced":[164],"model.":[166],"Evaluation":[167],"four":[169],"representative":[170],"robotic":[171],"manipulation":[172],"tasks":[173],"shows":[174],"92.33%":[176],"in-simulation":[179],"cases":[181],"generated":[182],"trigger":[185],"failures,":[187],"improves":[190],"over":[193,235],"state-of-the-art":[195],"tool":[196],"18.93%.":[198],"By":[199],"fine-tuning":[200],"synthetic":[204],"derived":[206],"from":[207],"failed":[208],"cases,":[210],"further":[212],"enhances":[213],"overall":[215],"success":[216,233],"rate":[217,234],"49.25%.":[222],"When":[223],"deployed":[224],"real":[226],"hardware,":[227],"simulation-enhanced":[229],"improve":[231],"57.50%,":[241],"demonstrating":[242],"effective":[244],"low-cost":[246],"direction":[247]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-03T00:00:00"}