{"id":"https://openalex.org/W7166102902","doi":"https://doi.org/10.48550/arxiv.2606.27146","title":"PhysReflect-VLA: Physical Feasibility and Self-Reflective Regulation for Reliable Vision-Language-Action Policies","display_name":"PhysReflect-VLA: Physical Feasibility and Self-Reflective Regulation for Reliable Vision-Language-Action Policies","publication_year":2026,"publication_date":"2026-06-25","ids":{"openalex":"https://openalex.org/W7166102902","doi":"https://doi.org/10.48550/arxiv.2606.27146"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.27146","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.27146","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":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.2606.27146","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100759136","display_name":"Jiayu Yang","orcid":"https://orcid.org/0000-0001-7475-1286"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Jiayu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139419088","display_name":"Tao Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139407105","display_name":"Weijun Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Weijun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019687349","display_name":"Xiang Chang","orcid":"https://orcid.org/0000-0002-5970-7698"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chang, Xiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139458974","display_name":"Fei Chao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao, Fei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039652471","display_name":"Changjing Shang","orcid":"https://orcid.org/0000-0001-6375-6276"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shang, Changjing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139438341","display_name":"Qiang Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Qiang","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/T10653","display_name":"Robot Manipulation and Learning","score":0.4722000062465668,"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":0.4722000062465668,"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":0.2485000044107437,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.07800000160932541,"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/task","display_name":"Task (project management)","score":0.6912000179290771},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.626800000667572},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5949000120162964},{"id":"https://openalex.org/keywords/reflection","display_name":"Reflection (computer programming)","score":0.5105999708175659},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5015000104904175},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.49959999322891235},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4925000071525574},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4677000045776367}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7010999917984009},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6912000179290771},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.626800000667572},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5949000120162964},{"id":"https://openalex.org/C65682993","wikidata":"https://www.wikidata.org/wiki/Q1056451","display_name":"Reflection (computer programming)","level":2,"score":0.5105999708175659},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5015000104904175},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.49959999322891235},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4925000071525574},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4677000045776367},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.45019999146461487},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.44780001044273376},{"id":"https://openalex.org/C161759796","wikidata":"https://www.wikidata.org/wiki/Q3982902","display_name":"Teleoperation","level":3,"score":0.43470001220703125},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.42750000953674316},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3968000113964081},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.37689998745918274},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.36660000681877136},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3634999990463257},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.31839999556541443},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3149000108242035},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28279998898506165},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2732999920845032},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.27090001106262207},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C116672817","wikidata":"https://www.wikidata.org/wiki/Q1454986","display_name":"Physical system","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.26350000500679016}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.27146","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.27146","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.27146","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.27146","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.5131189823150635,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Long-horizon":[0],"robotic":[1,181],"manipulation":[2,126],"is":[3],"highly":[4],"sensitive":[5],"to":[6,100,161],"physically":[7],"infeasible":[8],"transitions,":[9],"contact-induced":[10],"disturbances,":[11],"and":[12,65,92,114,134,156,175],"the":[13,118,168],"lack":[14],"of":[15,147,170],"effective":[16],"self-correction":[17],"during":[18],"execution.":[19],"Although":[20],"Vision-Language-Action":[21],"(VLA)":[22],"models":[23],"provide":[24],"strong":[25],"task":[26,136],"grounding":[27],"through":[28],"multimodal":[29],"learning,":[30],"they":[31],"typically":[32],"generate":[33,101],"actions":[34,79],"in":[35,68,131],"a":[36,52,69],"feed-forward":[37],"manner":[38],"without":[39],"explicitly":[40],"checking":[41,155],"physical":[42,62,172],"feasibility":[43,63,112,154],"or":[44],"diagnosing":[45],"execution":[46,163],"errors":[47],"online.":[48],"We":[49],"present":[50],"PhysReflect-VLA,":[51],"plug-and-play":[53],"execution-time":[54],"reliability":[55],"framework":[56],"that":[57,153],"augments":[58],"VLA":[59,141],"policies":[60],"with":[61,139,143],"evaluation":[64],"structured":[66],"self-reflection":[67,177],"closed-loop":[70],"control":[71,119],"pipeline.":[72],"A":[73,107],"Feasibility":[74],"Operator":[75,88],"evaluates":[76],"whether":[77],"candidate":[78],"induce":[80],"dynamically":[81],"consistent":[82,129],"state":[83,98],"transitions;":[84],"an":[85,93,144],"Action":[86],"Explanation":[87],"verifies":[89],"transition":[90],"coherence;":[91],"LLM-based":[94],"Reflection":[95],"Module":[96],"analyzes":[97],"discrepancies":[99],"corrective":[102],"guidance":[103],"for":[104,178],"subsequent":[105],"actions.":[106],"two-stage":[108],"training":[109],"procedure":[110],"stabilizes":[111],"modeling":[113],"integrates":[115],"reflection":[116],"into":[117],"loop.":[120],"Experiments":[121],"on":[122],"multi-stage,":[123],"contact-rich":[124],"real-world":[125],"tasks":[127],"show":[128],"improvements":[130],"stage-wise":[132],"stability":[133],"overall":[135],"success":[137],"compared":[138],"representative":[140],"baselines":[142],"average":[145],"gain":[146],"5.4\\%.":[148],"Ablation":[149],"results":[150,166],"further":[151],"indicate":[152],"reflection-based":[157],"correction":[158],"both":[159],"contribute":[160],"improved":[162],"robustness.":[164],"These":[165],"highlight":[167],"importance":[169],"embedding":[171],"consistency":[173],"checks":[174],"online":[176],"reliable":[179],"long-horizon":[180],"manipulation.":[182]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-27T00:00:00"}