{"id":"https://openalex.org/W7204959989","doi":"https://doi.org/10.48550/arxiv.2608.30536","title":"Behavior-Skill: A Fine-Grained Benchmark for Evaluating Vision-Language-Action Policies in Long-Horizon Tasks","display_name":"Behavior-Skill: A Fine-Grained Benchmark for Evaluating Vision-Language-Action Policies in Long-Horizon Tasks","publication_year":2026,"publication_date":"2026-08-31","ids":{"openalex":"https://openalex.org/W7204959989","doi":"https://doi.org/10.48550/arxiv.2608.30536"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.30536","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.30536","pdf_url":"https://arxiv.org/pdf/2608.30536","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/2608.30536","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148935991","display_name":"Chunyun Ma","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Chunyun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074706210","display_name":"Lun Luo","orcid":"https://orcid.org/0000-0002-0531-9171","observed_orcids":["https://orcid.org/0000-0002-0531-9171"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Lun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103735462","display_name":"Xuqiong Luo","orcid":"https://orcid.org/0000-0002-3547-4586","observed_orcids":["https://orcid.org/0000-0002-3547-4586"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Xingjian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041347071","display_name":"Xiexing Feng","orcid":"https://orcid.org/0000-0003-1771-2955","observed_orcids":["https://orcid.org/0000-0003-1771-2955"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Xiexing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148920896","display_name":"Hang Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Hang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148857441","display_name":"Wei Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130092002","display_name":"Feng Qiao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiao, Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124179882","display_name":"Yaonan Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yaonan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148875664","display_name":"Huimin Lu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Huimin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5148846090","display_name":"Xieyuanli Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Xieyuanli","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":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":0.9818999767303467,"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":0.9818999767303467,"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":0.013899999670684338,"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-policies","display_name":"vision-language-action policies","score":0.9110000133514404},{"id":"https://openalex.org/keywords/skill-decomposition","display_name":"skill decomposition","score":0.5429999828338623},{"id":"https://openalex.org/keywords/housework","display_name":"housework","score":0.531000018119812},{"id":"https://openalex.org/keywords/contact-rich-manipulation","display_name":"contact-rich manipulation","score":0.5370000004768372}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.9136999845504761},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8173999786376953},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.7648000121116638},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7390000224113464},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.7002999782562256},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4603999853134155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41609999537467957},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.38989999890327454},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3346000015735626},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C34585555","wikidata":"https://www.wikidata.org/wiki/Q1368723","display_name":"Learning curve","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.30536","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.30536","pdf_url":"https://arxiv.org/pdf/2608.30536","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.2608.30536","doi":"https://doi.org/10.48550/arxiv.2608.30536","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.30536","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":"pmh:oai:arXiv.org:2608.30536","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.30536","pdf_url":"https://arxiv.org/pdf/2608.30536","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204959989.pdf","grobid_xml":"https://content.openalex.org/works/W7204959989.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W4396822572","https://openalex.org/W4402354047","https://openalex.org/W4402354166","https://openalex.org/W4409015946","https://openalex.org/W4414674749","https://openalex.org/W4414881418","https://openalex.org/W4414901575","https://openalex.org/W4416045178","https://openalex.org/W4416095924","https://openalex.org/W4416780398","https://openalex.org/W4416878674","https://openalex.org/W4417119772","https://openalex.org/W4417293723","https://openalex.org/W4417300156","https://openalex.org/W6929480010","https://openalex.org/W6948104436","https://openalex.org/W6966661786","https://openalex.org/W7083290300","https://openalex.org/W7106591914","https://openalex.org/W7111056175","https://openalex.org/W7125820564"],"related_works":["https://openalex.org/W7221156363","https://openalex.org/W7221810922","https://openalex.org/W7155087617","https://openalex.org/W7167682355","https://openalex.org/W7133216487","https://openalex.org/W4297675755","https://openalex.org/W7222144906","https://openalex.org/W7131648928","https://openalex.org/W3206737393","https://openalex.org/W7078174358"],"abstract_inverted_index":{"Reliable":[0],"execution":[1],"of":[2,18,54],"long-horizon":[3,55,172],"mobile":[4],"manipulation":[5,150],"tasks":[6,56,72],"remains":[7],"challenging":[8],"because":[9],"overall":[10],"task":[11,123],"success":[12,101],"depends":[13],"on":[14,28,135],"the":[15,50,136],"successful":[16],"completion":[17],"multiple":[19],"constituent":[20,59],"skills.":[21,60],"Existing":[22],"benchmarks,":[23],"however,":[24],"still":[25],"rely":[26],"primarily":[27],"full-task":[29,161],"rollouts":[30],"and":[31,41,52,73,89,98,114,133,170],"aggregate":[32,122],"task-level":[33],"metrics,":[34],"making":[35],"intermediate":[36,96,165],"failures":[37,142],"difficult":[38],"to":[39,103,117],"observe":[40],"analyze.":[42],"We":[43,110],"present":[44],"Behavior-Skill,":[45],"a":[46,81,94,99],"benchmark":[47,139],"that":[48,141,158],"reformulates":[49],"learning":[51],"evaluation":[53,106,162],"around":[57],"executable":[58],"It":[61],"contains":[62],"235,492":[63],"skill":[64,76,82,100],"instances":[65],"from":[66],"10,000":[67],"demonstrations":[68],"across":[69,127,146],"50":[70],"household":[71],"34":[74],"semantic":[75],"categories.":[77],"Each":[78],"instance":[79],"pairs":[80],"instruction":[83],"with":[84,93,148],"an":[85],"aligned":[86],"observation-action":[87],"segment,":[88],"is":[90,176],"further":[91,111],"associated":[92],"restorable":[95],"state":[97],"condition":[102],"enable":[104],"independent":[105],"under":[107],"valid":[108],"preconditions.":[109],"introduce":[112],"trajectory-level":[113],"skill-level":[115],"metrics":[116],"characterize":[118],"policy":[119],"capability":[120,166],"beyond":[121],"success.":[124],"Extensive":[125],"experiments":[126],"representative":[128],"VLA":[129,173],"policies":[130],"including":[131],"pi0.5":[132],"GR00T":[134],"complete":[137],"50-task":[138],"show":[140],"are":[143],"highly":[144],"non-uniform":[145],"skills,":[147],"contact-rich":[149],"skills":[151],"forming":[152],"persistent":[153],"bottlenecks.":[154],"These":[155],"results":[156],"demonstrate":[157],"Behavior-Skill":[159,175],"complements":[160],"by":[163],"exposing":[164],"profiles":[167],"for":[168],"analyzing":[169],"improving":[171],"policies.":[174],"publicly":[177],"available":[178],"at":[179],"https://github.com/nubot-nudt/Behavior-Skill.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-02T00:00:00"}