{"id":"https://openalex.org/W7211908156","doi":"https://doi.org/10.18653/2026.emnlp-main.1021","title":"RoboSPA: Can VLA Models Go Beyond Simple Scenes and Short-Horizon Tasks?","display_name":"RoboSPA: Can VLA Models Go Beyond Simple Scenes and Short-Horizon Tasks?","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7211908156","doi":"https://doi.org/10.18653/2026.emnlp-main.1021"},"language":"en","primary_location":{"id":"doi:10.18653/2026.emnlp-main.1021","doi":"https://doi.org/10.18653/2026.emnlp-main.1021","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1021","pdf_url":"https://aclanthology.org/2026.emnlp-main.1021.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.emnlp-main.1021.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014529004","display_name":"Zhenxuan Fan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenxuan Fan","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5150596596","display_name":"Bo Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Zhang","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135872234","display_name":"Yutong Lin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutong Lin","raw_affiliation_strings":["Robotics Transformer for Real- World Control at Scale. In Proceedings of Robotics : Science and Systems , Daegu , Republic of Korea","Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics Transformer for Real- World Control at Scale. In Proceedings of Robotics : Science and Systems , Daegu , Republic of Korea","institution_ids":[]},{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121626354","display_name":"Yuqian Yuan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqian Yuan","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124375542","display_name":"Juekai Lin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juekai Lin","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5150695211","display_name":"Liang Liang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Liang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5150588179","display_name":"Zhuoyi Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuoyi Huang","raw_affiliation_strings":["South China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China Normal University","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126224158","display_name":"Wenqiao Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenqiao Zhang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121670167","display_name":"Juncheng Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juncheng Li","raw_affiliation_strings":["Robotics Transformer for Real- World Control at Scale. In Proceedings of Robotics : Science and Systems , Daegu , Republic of Korea","Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics Transformer for Real- World Control at Scale. In Proceedings of Robotics : Science and Systems , Daegu , Republic of Korea","institution_ids":[]},{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130636599","display_name":"Siliang Tang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siliang Tang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125772842","display_name":"Jun Xiao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Xiao","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5133348486","display_name":"Yueting Zhuang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueting Zhuang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.72058027,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23457","last_page":"23492"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9965999722480774,"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":0.9965999722480774,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0017000000225380063,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.0007999999797903001,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/vision-language-action-models","display_name":"vision-language-action models","score":0.9850000143051147},{"id":"https://openalex.org/keywords/robotic-manipulation","display_name":"robotic manipulation","score":0.8999999761581421},{"id":"https://openalex.org/keywords/embodied-reasoning","display_name":"embodied reasoning","score":0.6579999923706055},{"id":"https://openalex.org/keywords/spatial-reasoning","display_name":"spatial reasoning","score":0.7239999771118164},{"id":"https://openalex.org/keywords/procedural-planning","display_name":"procedural planning","score":0.9020000100135803},{"id":"https://openalex.org/keywords/long-horizon-planning","display_name":"long-horizon planning","score":0.9369999766349792},{"id":"https://openalex.org/keywords/diagnostic-benchmark","display_name":"diagnostic benchmark","score":0.4869999885559082},{"id":"https://openalex.org/keywords/task-difficulty","display_name":"task difficulty","score":0.4659999907016754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.746999979019165},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7371000051498413},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7164999842643738},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.6611999869346619},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.64410001039505},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.49559998512268066},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4878999888896942},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4156000018119812},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3889000117778778},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.38589999079704285},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.3750999867916107},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3589000105857849},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3449999988079071},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.3418000042438507},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.33489999175071716},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.26660001277923584},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.26159998774528503}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.emnlp-main.1021","doi":"https://doi.org/10.18653/2026.emnlp-main.1021","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1021","pdf_url":"https://aclanthology.org/2026.emnlp-main.1021.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2609.05324","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.05324","pdf_url":"https://arxiv.org/pdf/2609.05324","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.2609.05324","doi":"https://doi.org/10.48550/arxiv.2609.05324","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.05324","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/2026.emnlp-main.1021","doi":"https://doi.org/10.18653/2026.emnlp-main.1021","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1021","pdf_url":"https://aclanthology.org/2026.emnlp-main.1021.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1781607827","display_name":null,"funder_award_id":"62272411","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6487777669","display_name":null,"funder_award_id":"2025C01030","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7211908156.pdf","grobid_xml":"https://content.openalex.org/works/W7211908156.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7221577967","https://openalex.org/W4417276558","https://openalex.org/W4404216506","https://openalex.org/W7213321780","https://openalex.org/W7167036741","https://openalex.org/W4414943162","https://openalex.org/W4417119772","https://openalex.org/W4405783861","https://openalex.org/W6891886098","https://openalex.org/W7128604160"],"abstract_inverted_index":{"Vision-Language-Action":[0],"(VLA)":[1],"models":[2,113],"have":[3],"shown":[4],"promising":[5],"progress":[6],"in":[7,50],"languageconditioned":[8],"robotic":[9,41],"manipulation.However,":[10],"existing":[11],"datasets":[12],"and":[13,31,44,61,69,87,96,127,143,148],"benchmarks":[14],"mainly":[15],"evaluate":[16],"task":[17,67,73],"completion":[18],"under":[19,28],"predefined":[20],"settings,":[21],"offering":[22],"limited":[23],"insight":[24],"into":[25],"model":[26],"reasoning":[27,49],"increasing":[29,84],"spatial":[30,85,122],"procedural":[32,88],"complexity.We":[33,89],"introduce":[34],"RoboSPA":[35,102,132],"(Robot":[36],"Spatial-Procedural":[37],"Assessment),":[38],"a":[39,134],"large-scale":[40],"manipulation":[42],"dataset":[43],"benchmark":[45,137],"for":[46,106,138],"diagnosing":[47],"embodied":[48,145],"VLA":[51,112],"models.RoboSPA":[52],"focuses":[53],"on":[54,110],"two":[55],"core":[56],"dimensions,":[57],"Fine-Grained":[58],"Spatial":[59],"Reasoning":[60],"Long-Horizon":[62],"Procedural":[63],"Planning,":[64],"covering":[65],"10":[66],"categories":[68],"56":[70],"base":[71],"tasks.Each":[72],"is":[74],"instantiated":[75],"across":[76,93],"five":[77],"difficulty":[78],"levels,":[79],"yielding":[80],"280":[81],"variants":[82],"with":[83,120],"ambiguity":[86],"collect":[90],"527K":[91],"trajectories":[92],"multiple":[94],"embodiments":[95],"diverse":[97],"scenes.Beyond":[98],"binary":[99],"success":[100],"rate,":[101],"introduces":[103],"diagnostic":[104,136],"metrics":[105],"more":[107,140],"detailed":[108],"evaluation.Experiments":[109],"representative":[111],"show":[114],"that":[115],"current":[116],"systems":[117],"still":[118],"struggle":[119],"complex":[121],"relations,":[123],"precise":[124],"low-level":[125],"execution,":[126],"memory-intensive":[128],"planning.These":[129],"results":[130],"establish":[131],"as":[133],"challenging":[135],"developing":[139],"capable,":[141],"reliable,":[142],"generalizable":[144],"agents.Our":[146],"data":[147],"code":[149],"are":[150],"available":[151],"at":[152],"https:":[153],"//github.com/fanzhenxuan/RoboSPA.":[154]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2026-09-08T00:00:00"}