{"id":"https://openalex.org/W7204458710","doi":"https://doi.org/10.48550/arxiv.2608.25585","title":"RA-VLA: Retrieval-Augmented VLA for Test-Time Adaptation","display_name":"RA-VLA: Retrieval-Augmented VLA for Test-Time Adaptation","publication_year":2026,"publication_date":"2026-08-26","ids":{"openalex":"https://openalex.org/W7204458710","doi":"https://doi.org/10.48550/arxiv.2608.25585"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.25585","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.25585","pdf_url":"https://arxiv.org/pdf/2608.25585","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.25585","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108909328","display_name":"Sanghwan Jang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jang, Sanghwan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113307636","display_name":"Minjin Jeon","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeon, Minjin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136425058","display_name":"Minsoo Kim","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Minsoo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148410732","display_name":"Seongjin Choi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Choi, Seongjin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147123433","display_name":"Dongha Kim","orcid":"https://orcid.org/0009-0003-6676-1187","observed_orcids":["https://orcid.org/0009-0003-6676-1187"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Dongha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5148468237","display_name":"Hwanjo Yu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Hwanjo","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":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/T10653","display_name":"Robot Manipulation and Learning","score":0.9951000213623047,"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":0.9951000213623047,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.0024999999441206455,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0010999999940395355,"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/vision-language-action-models","display_name":"vision-language-action models","score":0.8709999918937683},{"id":"https://openalex.org/keywords/retrieval-augmented-learning","display_name":"retrieval-augmented learning","score":0.8109999895095825},{"id":"https://openalex.org/keywords/test-time-adaptation","display_name":"test-time adaptation","score":0.8859999775886536},{"id":"https://openalex.org/keywords/libero-benchmark","display_name":"LIBERO benchmark","score":0.6800000071525574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7251999974250793},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.6722999811172485},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6542999744415283},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6247000098228455},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6137999892234802},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6072999835014343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5800999999046326},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5608999729156494},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.47369998693466187},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4731000065803528},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.450300008058548},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3952000141143799},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.3799000084400177},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C152752567","wikidata":"https://www.wikidata.org/wiki/Q116877","display_name":"Code refactoring","level":3,"score":0.3005000054836273},{"id":"https://openalex.org/C81444415","wikidata":"https://www.wikidata.org/wiki/Q7243535","display_name":"Priming (agriculture)","level":3,"score":0.3000999987125397},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2759000062942505},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2596000134944916}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.25585","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.25585","pdf_url":"https://arxiv.org/pdf/2608.25585","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.25585","doi":"https://doi.org/10.48550/arxiv.2608.25585","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.25585","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":"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.25585","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.25585","pdf_url":"https://arxiv.org/pdf/2608.25585","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204458710.pdf","grobid_xml":"https://content.openalex.org/works/W7204458710.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7162331955","https://openalex.org/W4416157228","https://openalex.org/W4415955379","https://openalex.org/W7123834068","https://openalex.org/W4414757762","https://openalex.org/W4417101780","https://openalex.org/W7222308244","https://openalex.org/W7211991055","https://openalex.org/W7125931475","https://openalex.org/W7220712189"],"abstract_inverted_index":{"Vision-Language-Action":[0],"(VLA)":[1],"models":[2],"provide":[3],"a":[4,28,76,86,98,118,133],"versatile":[5],"foundation":[6],"for":[7,136],"general":[8],"robotic":[9,138],"manipulation,":[10],"yet":[11],"they":[12],"exhibit":[13],"significant":[14],"brittleness":[15],"when":[16],"confronted":[17],"with":[18,85],"novel":[19],"task":[20,104],"distributions.":[21],"While":[22],"In-Context":[23],"Imitation":[24],"Learning":[25],"(ICIL)":[26],"offers":[27],"training-free":[29,137],"alternative,":[30],"existing":[31],"frameworks":[32],"suffer":[33],"from":[34,52],"an":[35,57],"adaptation":[36,105],"bottleneck":[37],"that":[38,61,80,123],"hinders":[39],"the":[40,63,114],"effective":[41],"translation":[42],"of":[43],"expert":[44],"context":[45,83],"to":[46,65,94],"executable":[47],"actions.":[48],"This":[49],"failure":[50],"originates":[51],"superficial":[53],"retrieval":[54,84],"mechanisms":[55],"and":[56,117,129],"inherent":[58],"behavioral":[59],"inertia":[60],"anchors":[62],"policy":[64],"its":[66],"pre-trained":[67],"priors.":[68],"To":[69],"address":[70],"these":[71],"limitations,":[72],"we":[73],"present":[74],"RA-VLA,":[75],"retrieval-augmented":[77],"VLA":[78],"framework":[79,135],"integrates":[81],"behavior-aligned":[82],"grounded":[87],"execution":[88],"pipeline.":[89],"By":[90],"enforcing":[91],"faithful":[92],"adherence":[93],"functional":[95],"cues":[96],"within":[97],"scalable":[99],"architecture,":[100],"RA-VLA":[101,124],"facilitates":[102],"seamless":[103],"while":[106],"preserving":[107],"inference":[108],"efficiency.":[109],"Our":[110],"empirical":[111],"evaluations":[112],"across":[113],"LIBERO":[115],"benchmark":[116],"real-world":[119],"UR5e":[120],"environment":[121],"demonstrate":[122],"achieves":[125],"superior":[126],"success":[127],"rates":[128],"computational":[130],"efficiency,":[131],"establishing":[132],"robust":[134],"adaptation.":[139]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-08-28T00:00:00"}