{"id":"https://openalex.org/W7164023866","doi":"https://doi.org/10.48550/arxiv.2606.08508","title":"ActProbe: Action-Space Probe for Early Failure Detection of Generative Robot Policies","display_name":"ActProbe: Action-Space Probe for Early Failure Detection of Generative Robot Policies","publication_year":2026,"publication_date":"2026-06-07","ids":{"openalex":"https://openalex.org/W7164023866","doi":"https://doi.org/10.48550/arxiv.2606.08508"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.08508","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08508","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.08508","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138219575","display_name":"Bingjia Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Bingjia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138254716","display_name":"Xiangyu Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xiangyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138225463","display_name":"Xiang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138229067","display_name":"Liang Mi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mi, Liang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035312747","display_name":"Zixu Hao","orcid":"https://orcid.org/0000-0002-2465-7627"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao, Zixu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138264430","display_name":"Weijun Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Weijun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138271080","display_name":"Hao Wu","orcid":"https://orcid.org/0000-0002-5213-2959"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138268883","display_name":"Kun Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Kun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138222826","display_name":"Yunxin Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yunxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138203045","display_name":"Ting Cao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Ting","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":false,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.3955000042915344,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.3955000042915344,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.24789999425411224,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.050700001418590546,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.583299994468689},{"id":"https://openalex.org/keywords/commit","display_name":"Commit","score":0.5823000073432922},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.571399986743927},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.49140000343322754},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.43720000982284546},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.43059998750686646},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4255000054836273},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.42100000381469727}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.705299973487854},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.583299994468689},{"id":"https://openalex.org/C153180980","wikidata":"https://www.wikidata.org/wiki/Q19776675","display_name":"Commit","level":2,"score":0.5823000073432922},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.571399986743927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5450000166893005},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.49140000343322754},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.444599986076355},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.43720000982284546},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.43059998750686646},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4255000054836273},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.42100000381469727},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4162999987602234},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.40880000591278076},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.3716999888420105},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.303600013256073},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.08508","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08508","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.08508","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08508","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,"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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4364623427391052}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generative":[0],"robot":[1,58,119],"policies":[2,120],"fail":[3],"unpredictably":[4],"at":[5,9],"deployment:":[6],"they":[7],"hesitate":[8],"critical":[10],"moments,":[11],"drift":[12],"off-task,":[13],"or":[14,30],"commit":[15],"to":[16,27,104,165],"unrecoverable":[17],"actions.":[18],"Existing":[19],"online":[20],"failure":[21,106,138],"detectors":[22],"either":[23],"require":[24],"white-box":[25],"access":[26],"policy":[28],"internals":[29],"add":[31],"runtime":[32],"overhead":[33],"through":[34],"resampling":[35],"and":[36,91,121,150,174],"observation-side":[37],"signals.":[38],"Our":[39],"empirical":[40],"analysis":[41],"shows":[42],"that":[43,72],"emitted":[44],"action":[45,89],"chunks":[46,90],"themselves":[47],"already":[48],"carry":[49],"strong":[50],"predictive":[51],"signal":[52],"for":[53],"impending":[54],"failures":[55,127,168],"in":[56],"generative":[57,118],"policies.":[59],"Motivated":[60],"by":[61,140],"this":[62],"observation,":[63],"we":[64],"introduce":[65],"ActProbe,":[66],"a":[67,79,109,114,154],"lightweight,":[68],"pure":[69],"action-space":[70],"detector":[71],"uses":[73],"two":[74],"compact":[75],"signals":[76,103],"available":[77],"from":[78],"single":[80],"forward":[81],"pass:":[82],"Temporal":[83],"Consistency":[84],"Error":[85],"(TCE)":[86],"between":[87],"consecutive":[88],"Action":[92],"Chunk":[93],"Magnitude":[94],"(ACM)":[95],"of":[96,117,137,145],"the":[97,132],"current":[98],"chunk.":[99],"ActProbe":[100,123,162],"maps":[101],"these":[102],"per-step":[105],"probabilities":[107],"with":[108,153,179],"task-conditioned":[110],"LSTM-MLP":[111],"architecture.":[112],"Across":[113],"diverse":[115],"suite":[116],"benchmarks,":[122],"raises":[124],"alerts":[125],"before":[126],"become":[128],"visually":[129],"recognizable,":[130],"improving":[131],"accuracy":[133],"(F1)-timeliness":[134],"Pareto":[135],"frontier":[136],"detection":[139],"an":[141],"average":[142],"hypervolume":[143],"gain":[144],"+12.7%":[146],"over":[147],"both":[148],"internal-":[149],"external-feature":[151],"baselines,":[152],"+9.0%":[155],"early-detection":[156],"ROC-AUC":[157],"lead":[158],"on":[159,169],"unseen":[160,170],"tasks.":[161],"further":[163],"transfers":[164],"deployment,":[166],"predicting":[167],"real-robot":[171],"pick":[172],"tasks":[173],"accelerating":[175],"RL":[176],"fine-tuning":[177],"(PPO)":[178],"2.9x":[180],"fewer":[181],"environment":[182],"interactions.":[183]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-10T00:00:00"}