{"id":"https://openalex.org/W7134076654","doi":"https://doi.org/10.48550/arxiv.2603.05185","title":"Critic in the Loop: A Tri-System VLA Framework for Robust Long-Horizon Manipulation","display_name":"Critic in the Loop: A Tri-System VLA Framework for Robust Long-Horizon Manipulation","publication_year":2026,"publication_date":"2026-03-05","ids":{"openalex":"https://openalex.org/W7134076654","doi":"https://doi.org/10.48550/arxiv.2603.05185"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2603.05185","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128265615","display_name":"Pengfei Yi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yi, Pengfei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128224461","display_name":"Yingjie Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Yingjie","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128222955","display_name":"Wenjiang Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Wenjiang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128236670","display_name":"Yanan Hao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao, Yanan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055067794","display_name":"Shuai Gan","orcid":"https://orcid.org/0000-0002-7603-1271"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gan, Shuai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128223529","display_name":"Wanting Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Wanting","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128241014","display_name":"Shanlin Zhong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong, Shanlin","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5128265615"],"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9156000018119812,"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":0.9156000018119812,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.017899999395012856,"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":0.009999999776482582,"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/robustness","display_name":"Robustness (evolution)","score":0.5914999842643738},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5406000018119812},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.46560001373291016},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.45190000534057617},{"id":"https://openalex.org/keywords/cognitive-architecture","display_name":"Cognitive architecture","score":0.41260001063346863},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.3912999927997589},{"id":"https://openalex.org/keywords/unexpected-events","display_name":"Unexpected events","score":0.3806000053882599}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7635999917984009},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5914999842643738},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5406000018119812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5234000086784363},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.46560001373291016},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.45190000534057617},{"id":"https://openalex.org/C20854674","wikidata":"https://www.wikidata.org/wiki/Q4386060","display_name":"Cognitive architecture","level":3,"score":0.41260001063346863},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.3912999927997589},{"id":"https://openalex.org/C2776544517","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Unexpected events","level":2,"score":0.3806000053882599},{"id":"https://openalex.org/C193611912","wikidata":"https://www.wikidata.org/wiki/Q4677596","display_name":"Active vision","level":2,"score":0.3483999967575073},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.34290000796318054},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3296999931335449},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3179999887943268},{"id":"https://openalex.org/C31531917","wikidata":"https://www.wikidata.org/wiki/Q915157","display_name":"Robust control","level":3,"score":0.3149999976158142},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.31139999628067017},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2897000014781952},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.26269999146461487}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2603.05185","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2603.05185","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.05185","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2603.05185","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Balancing":[0],"high-level":[1],"semantic":[2,38],"reasoning":[3],"with":[4],"low-level":[5],"reactive":[6,83],"control":[7,99],"remains":[8],"a":[9,68,73,79,86],"core":[10,66],"challenge":[11],"in":[12,52,156],"visual":[13,88],"robotic":[14],"manipulation.":[15],"While":[16],"Vision-Language":[17],"Models":[18],"(VLMs)":[19],"excel":[20],"at":[21],"cognitive":[22],"planning,":[23],"their":[24],"inference":[25],"latency":[26],"precludes":[27],"real-time":[28],"execution.":[29],"Conversely,":[30],"fast":[31],"Vision-Language-Action":[32],"(VLA)":[33],"models":[34],"often":[35],"lack":[36],"the":[37,53,93,95,107,115],"depth":[39],"required":[40],"for":[41,76,82,109,117],"complex,":[42],"long-horizon":[43,164],"tasks.":[44],"To":[45],"bridge":[46],"this":[47],"gap,":[48],"we":[49],"introduce":[50],"Critic":[51,96],"Loop,":[54],"an":[55],"adaptive":[56],"hierarchical":[57],"framework":[58],"driven":[59],"by":[60],"dynamic":[61],"VLM-Expert":[62],"scheduling.":[63],"At":[64],"its":[65],"is":[67],"bionic":[69],"Tri-System":[70],"architecture":[71,131],"comprising":[72],"VLM":[74,116,147],"brain":[75],"global":[77],"reasoning,":[78],"VLA":[80,108],"cerebellum":[81],"execution,":[84],"and":[85,112,154],"lightweight":[87],"Critic.":[89],"By":[90],"continuously":[91],"monitoring":[92],"workspace,":[94],"dynamically":[97],"routes":[98],"authority.":[100],"It":[101],"sustains":[102],"rapid":[103],"closed-loop":[104],"execution":[105,121],"via":[106],"routine":[110],"subtasks,":[111],"adaptively":[113],"triggers":[114],"replanning":[118],"upon":[119],"detecting":[120],"anomalies":[122],"such":[123],"as":[124],"task":[125],"stagnation":[126],"or":[127],"failures.":[128],"Furthermore,":[129],"our":[130,169],"seamlessly":[132],"integrates":[133],"human-inspired":[134],"rules":[135],"to":[136],"intuitively":[137],"break":[138],"infinite":[139],"retry":[140],"loops.":[141],"This":[142],"visually-grounded":[143],"scheduling":[144],"minimizes":[145],"expensive":[146],"queries,":[148],"while":[149],"substantially":[150],"enhancing":[151],"system":[152],"robustness":[153],"autonomy":[155],"out-of-distribution":[157],"(OOD)":[158],"scenarios.":[159],"Comprehensive":[160],"experiments":[161],"on":[162],"challenging,":[163],"manipulation":[165],"benchmarks":[166],"reveal":[167],"that":[168],"approach":[170],"achieves":[171],"state-of-the-art":[172],"performance.":[173]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-03-07T00:00:00"}
