{"id":"https://openalex.org/W7138461808","doi":"https://doi.org/10.1609/aaai.v40i10.37781","title":"How Foundational Skills Influence VLM-based Embodied Agents: A Native Perspective","display_name":"How Foundational Skills Influence VLM-based Embodied Agents: A Native Perspective","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138461808","doi":"https://doi.org/10.1609/aaai.v40i10.37781"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i10.37781","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37781","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i10.37781","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Bo Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN","US"],"is_corresponding":true,"raw_author_name":"Bo Peng","raw_affiliation_strings":["University of Science and Technology of China\nAlibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China\nAlibaba Group","institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Pi Bu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pi Bu","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Keyu Pan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keyu Pan","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xinrun Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["KY","US"],"is_corresponding":false,"raw_author_name":"Xinrun Xu","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences\nAlibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences\nAlibaba Group","institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I4210086143"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yingxiu Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yingxiu Zhao","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Miao Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miao Chen","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yang Du","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Du","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lin Li","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jun Song","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun Song","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":null,"display_name":"Tong Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Xu","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.75552388,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"10","first_page":"8322","last_page":"8330"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9506999850273132,"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":0.9506999850273132,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.009100000374019146,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.007400000002235174,"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/embodied-cognition","display_name":"Embodied cognition","score":0.9505000114440918},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6449000239372253},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.6330000162124634},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6046000123023987},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.558899998664856},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5023000240325928},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.4652999937534332},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4602000117301941}],"concepts":[{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.9505000114440918},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6449000239372253},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6330000162124634},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6046000123023987},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.558899998664856},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5388000011444092},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5023000240325928},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.4652999937534332},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4602000117301941},{"id":"https://openalex.org/C103683099","wikidata":"https://www.wikidata.org/wiki/Q5370102","display_name":"Embodied agent","level":3,"score":0.39419999718666077},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3718999922275543},{"id":"https://openalex.org/C192327766","wikidata":"https://www.wikidata.org/wiki/Q1038799","display_name":"Cognitive robotics","level":3,"score":0.3691999912261963},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3492000102996826},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.30250000953674316},{"id":"https://openalex.org/C2780342009","wikidata":"https://www.wikidata.org/wiki/Q18387795","display_name":"Perspective-taking","level":3,"score":0.2992999851703644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28360000252723694},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2833999991416931},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.27129998803138733}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i10.37781","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37781","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37781","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37781","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i10.37781","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37781","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.837412416934967,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,90,152],"vision\u2013language":[3],"models":[4],"(VLMs)":[5],"have":[6],"shed":[7],"light":[8],"on":[9,22,42,51,145,166],"human-level":[10],"embodied":[11,18,68,126,141,155,181],"intelligence.":[12],"However,":[13],"existing":[14],"benchmarks":[15,39],"for":[16,66,188],"VLM-driven":[17,67,180],"agents":[19,69],"still":[20],"rely":[21],"high-level":[23,43,88,167],"commands":[24],"or":[25],"discretised":[26],"action":[27,76],"spaces\u2014``non-native''":[28],"settings":[29],"that":[30,70,160],"diverge":[31],"markedly":[32],"from":[33],"the":[34,107,146,174],"real":[35],"world.":[36],"Moreover,":[37],"current":[38,179],"focus":[40],"exclusively":[41],"tasks,":[44,119],"while":[45],"lacking":[46],"joint":[47,129],"evaluation":[48,130],"and":[49,54,100,113,133],"analysis":[50,158],"both":[52],"low-":[53],"high-level.":[55],"To":[56],"bridge":[57],"these":[58,161],"gaps,":[59],"we":[60,104],"present":[61],"\\textbf{NativeEmbodied},":[62],"a":[63,72,123,137],"challenging":[64],"benchmark":[65],"adopts":[71],"unified,":[73],"native":[74],"low-level":[75,118],"space.":[77],"Built":[78],"upon":[79],"diverse":[80],"simulated":[81],"scenes,":[82],"NativeEmbodied":[83,170],"first":[84],"designs":[85],"three":[86],"representative":[87],"tasks":[89,112],"complex":[91,111],"scenarios":[92],"to":[93,122],"evaluate":[94],"overall":[95],"performance.":[96],"For":[97],"more":[98],"detailed":[99],"comprehensive":[101],"performance":[102,165],"analysis,":[103],"further":[105],"decouple":[106],"entangled":[108],"skills":[109],"behind":[110],"construct":[114],"four":[115],"types":[116],"of":[117,140,191],"each":[120],"corresponding":[121],"key":[124,175],"fundamental":[125,154],"skill.":[127],"This":[128],"across":[131],"task":[132],"skill":[134],"granularities":[135],"enables":[136],"fine-grained":[138],"assessment":[139],"agent.":[142],"Comprehensive":[143],"experiments":[144],"best":[147],"VLMs":[148],"reveal":[149],"pronounced":[150],"deficiencies":[151],"certain":[153],"skills.":[156],"Further":[157],"shows":[159],"bottlenecks":[162],"severely":[163],"constrain":[164],"tasks.":[168],"Our":[169],"not":[171],"only":[172],"pinpoints":[173],"challenges":[176],"faced":[177],"by":[178],"agents,":[182],"but":[183],"also":[184],"provides":[185],"valuable":[186],"insight":[187],"future":[189],"development":[190],"this":[192],"field.":[193]},"counts_by_year":[],"updated_date":"2026-06-06T09:05:17.133730","created_date":"2026-03-01T00:00:00"}