{"id":"https://openalex.org/W7203602325","doi":"https://doi.org/10.48550/arxiv.2608.14047","title":"Evolve Vision-Language-Action Model into an Agent with On-the-fly Tool-use","display_name":"Evolve Vision-Language-Action Model into an Agent with On-the-fly Tool-use","publication_year":2026,"publication_date":"2026-08-14","ids":{"openalex":"https://openalex.org/W7203602325","doi":"https://doi.org/10.48550/arxiv.2608.14047"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.14047","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.14047","pdf_url":"https://arxiv.org/pdf/2608.14047","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.14047","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136675514","display_name":"Yi Ding","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi, Ding","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147345141","display_name":"Yanzhao Yu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu, Yanzhao","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071941602","display_name":"Xili Dai","orcid":"https://orcid.org/0000-0001-5526-8934","observed_orcids":["https://orcid.org/0000-0001-5526-8934"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai, Xili","raw_affiliation_strings":["Juxi Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Juxi Tech","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020400305","display_name":"Xianbiao Qi","orcid":"https://orcid.org/0000-0002-8493-1966","observed_orcids":["https://orcid.org/0000-0002-8493-1966"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi, Xianbiao","raw_affiliation_strings":["IntelliFusion Inc "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IntelliFusion Inc ","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124811338","display_name":"Peiwen Sun","orcid":"https://orcid.org/0009-0005-3016-8554","observed_orcids":["https://orcid.org/0009-0005-3016-8554"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Sun, Peiwen","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147328463","display_name":"Xueqian Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Xueqian","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078165161","display_name":"Xiangyu Yue","orcid":"https://orcid.org/0000-0002-6887-2046","observed_orcids":["https://orcid.org/0000-0002-6887-2046"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yue, Xiangyu","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5137104185","display_name":"Jianan Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jianan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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":0.9506999850273132,"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":0.9506999850273132,"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":0.03020000085234642,"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":0.013799999840557575,"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/tool-use","display_name":"tool use","score":0.7480000257492065},{"id":"https://openalex.org/keywords/affordances","display_name":"affordances","score":0.5569999814033508},{"id":"https://openalex.org/keywords/robot-embodiment","display_name":"robot embodiment","score":0.45500001311302185},{"id":"https://openalex.org/keywords/pick-and-place","display_name":"pick-and-place","score":0.6620000004768372}],"concepts":[{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.7087000012397766},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6830000281333923},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6201000213623047},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5803999900817871},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5490000247955322},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5271999835968018},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5117999911308289},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5078999996185303},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.49570000171661377},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4657000005245209},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35179999470710754},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.34929999709129333},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.290800005197525},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C34559072","wikidata":"https://www.wikidata.org/wiki/Q2334061","display_name":"Design of experiments","level":2,"score":0.26339998841285706}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.14047","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.14047","pdf_url":"https://arxiv.org/pdf/2608.14047","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.2608.14047","doi":"https://doi.org/10.48550/arxiv.2608.14047","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.14047","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:2608.14047","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.14047","pdf_url":"https://arxiv.org/pdf/2608.14047","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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203602325.pdf","grobid_xml":"https://content.openalex.org/works/W7203602325.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7161145657","https://openalex.org/W7201856933","https://openalex.org/W4405031329","https://openalex.org/W7138390106","https://openalex.org/W7162331955","https://openalex.org/W7131819932","https://openalex.org/W7081581916","https://openalex.org/W7106819507","https://openalex.org/W7155641921","https://openalex.org/W7214048529"],"abstract_inverted_index":{"This":[0,175],"paper":[1],"integrates":[2],"end-to-end":[3],"Visual-Language-Action":[4],"(VLA)":[5],"models":[6,44],"with":[7,14,45],"agentic":[8],"tool-use":[9,96,119],"to":[10,27,41],"propose":[11],"Agentic":[12],"Robot":[13],"Tool-use":[15],"(ART).":[16],"ART":[17,52,127],"is":[18,102],"a":[19,46,92,114,129],"tool-injection":[20],"framework":[21],"that":[22,126],"tunes":[23],"any":[24],"VLA":[25,43,190],"model":[26],"leverage":[28],"off-the-shelf":[29],"tool":[30,161],"modules":[31],"for":[32,117,185],"low-level":[33],"vision,":[34],"high-level":[35],"affordance,":[36],"and":[37,82,98,139,169,180],"embodiment":[38],"enhancement.":[39],"Compared":[40],"vanilla":[42],"whole":[47],"continuous":[48],"action":[49,58,99],"solution":[50,59],"space,":[51],"reduces":[53,73],"the":[54,57,78,146,154,183,186],"complexity":[55],"of":[56,86,94,156,172,189],"space":[60],"through":[61],"tool-use,":[62],"which":[63,101],"not":[64],"only":[65],"improves":[66],"generalizability":[67,81],"across":[68],"different":[69],"tasks":[70],"but":[71],"also":[72],"data":[74,84],"dependency.":[75],"To":[76],"demonstrate":[77],"advantages":[79],"(high":[80],"low":[83],"dependency)":[85],"this":[87],"framework,":[88],"we":[89],"first":[90],"built":[91],"dataset":[93],"30K":[95],"trajectories":[97],"demonstrations,":[100],"much":[103],"smaller":[104],"than":[105,134],"those":[106],"used":[107],"by":[108],"baseline":[109],"methods.":[110],"We":[111],"then":[112],"designed":[113],"training":[115],"regimen":[116],"long-trajectory":[118],"reasoning":[120],"in":[121,145,192],"challenging":[122],"environments.":[123],"Experiments":[124],"show":[125],"achieves":[128],"20%":[130],"higher":[131],"success":[132],"rate":[133],"mainstream":[135],"baselines":[136],"on":[137],"simulation":[138],"real-world":[140,194],"tasks,":[141],"such":[142],"as":[143],"pick-and-place":[144],"dark":[147],"at":[148],"novel":[149],"viewpoints.":[150],"Empirical":[151],"results":[152],"highlight":[153],"benefits":[155],"an":[157],"agent-based":[158],"approach:":[159],"modular":[160],"utilization":[162],"enables":[163],"more":[164],"efficient":[165],"training,":[166],"lightweight":[167],"deployment,":[168],"scalable":[170],"integration":[171],"new":[173],"tools.":[174],"design":[176],"fosters":[177],"robustness,":[178],"adaptability,":[179],"extensibility,":[181],"paving":[182],"way":[184],"practical":[187],"deployment":[188],"systems":[191],"complex":[193],"scenarios.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-18T00:00:00"}