{"id":"https://openalex.org/W7214719620","doi":"https://doi.org/10.48550/arxiv.2609.34484","title":"ARS: Agentic Reward System for Robot Learning","display_name":"ARS: Agentic Reward System for Robot Learning","publication_year":2026,"publication_date":"2026-09-28","ids":{"openalex":"https://openalex.org/W7214719620","doi":"https://doi.org/10.48550/arxiv.2609.34484"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.34484","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34484","pdf_url":"https://arxiv.org/pdf/2609.34484","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/2609.34484","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153497606","display_name":"Sheng Hu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210093653","display_name":"Midea Group (China)","ror":"https://ror.org/006fm2278","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093653"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hu, Sheng","raw_affiliation_strings":["AIRC , Midea Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AIRC , Midea Group","institution_ids":["https://openalex.org/I4210093653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153476933","display_name":"Weiyi Lu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210093653","display_name":"Midea Group (China)","ror":"https://ror.org/006fm2278","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093653"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu, Weiyi","raw_affiliation_strings":["AIRC , Midea Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AIRC , Midea Group","institution_ids":["https://openalex.org/I4210093653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153433643","display_name":"Lingbing Zeng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210093653","display_name":"Midea Group (China)","ror":"https://ror.org/006fm2278","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093653"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeng, Lingbing","raw_affiliation_strings":["AIRC , Midea Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AIRC , Midea Group","institution_ids":["https://openalex.org/I4210093653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013933437","display_name":"Gan Weng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210093653","display_name":"Midea Group (China)","ror":"https://ror.org/006fm2278","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093653"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weng, Gan","raw_affiliation_strings":["AIRC , Midea Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AIRC , Midea Group","institution_ids":["https://openalex.org/I4210093653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153461377","display_name":"Weiwei Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210093653","display_name":"Midea Group (China)","ror":"https://ror.org/006fm2278","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093653"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Weiwei","raw_affiliation_strings":["AIRC , Midea Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AIRC , Midea Group","institution_ids":["https://openalex.org/I4210093653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153471590","display_name":"Kai Xie","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210093653","display_name":"Midea Group (China)","ror":"https://ror.org/006fm2278","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093653"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xie, Kai","raw_affiliation_strings":["AIRC , Midea Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AIRC , Midea Group","institution_ids":["https://openalex.org/I4210093653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123476396","display_name":"Xiaofeng Mou","orcid":"https://orcid.org/0009-0003-8375-2274","observed_orcids":["https://orcid.org/0009-0003-8375-2274"]},"institutions":[{"id":"https://openalex.org/I4210093653","display_name":"Midea Group (China)","ror":"https://ror.org/006fm2278","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093653"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mou, Xiaofeng","raw_affiliation_strings":["AIRC , Midea Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AIRC , Midea Group","institution_ids":["https://openalex.org/I4210093653"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153460342","display_name":"Yi Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210093653","display_name":"Midea Group (China)","ror":"https://ror.org/006fm2278","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093653"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Yi","raw_affiliation_strings":["AIRC , Midea Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AIRC , Midea Group","institution_ids":["https://openalex.org/I4210093653"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210093653"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"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":0.9800000190734863,"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":0.9800000190734863,"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":0.017899999395012856,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0003000000142492354,"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/robot-learning","display_name":"robot learning","score":0.7789999842643738},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.8610000014305115},{"id":"https://openalex.org/keywords/reward-modeling","display_name":"reward modeling","score":0.4659999907016754},{"id":"https://openalex.org/keywords/pick-and-place","display_name":"pick-and-place","score":0.8339999914169312}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7287999987602234},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.66839998960495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5920000076293945},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5863000154495239},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5764999985694885},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5601999759674072},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.555899977684021},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5361999869346619},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.43799999356269836},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4269999861717224},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.40790000557899475},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.40369999408721924},{"id":"https://openalex.org/C2775937380","wikidata":"https://www.wikidata.org/wiki/Q1232589","display_name":"Replica","level":2,"score":0.39079999923706055},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3310999870300293},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.304500013589859},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2921999990940094},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.34484","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34484","pdf_url":"https://arxiv.org/pdf/2609.34484","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.2609.34484","doi":"https://doi.org/10.48550/arxiv.2609.34484","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.34484","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.34484","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34484","pdf_url":"https://arxiv.org/pdf/2609.34484","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214719620.pdf","grobid_xml":"https://content.openalex.org/works/W7214719620.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W4414050916","https://openalex.org/W4414050921","https://openalex.org/W4415272448","https://openalex.org/W4416780398","https://openalex.org/W7118501563","https://openalex.org/W7127385277","https://openalex.org/W7133361213","https://openalex.org/W7138850231","https://openalex.org/W7140222441","https://openalex.org/W7147223856","https://openalex.org/W7160901029","https://openalex.org/W7164479070","https://openalex.org/W7165376596","https://openalex.org/W7166570088","https://openalex.org/W7166834610","https://openalex.org/W7166839567","https://openalex.org/W7166840538","https://openalex.org/W7168371273","https://openalex.org/W7204808299"],"related_works":["https://openalex.org/W7165643088","https://openalex.org/W7118501563","https://openalex.org/W7150898713","https://openalex.org/W7160901029","https://openalex.org/W7131376722","https://openalex.org/W7138850231","https://openalex.org/W7164133502","https://openalex.org/W7171376342","https://openalex.org/W7214944401","https://openalex.org/W6948050170"],"abstract_inverted_index":{"Progress":[0],"reward":[1,42,112,143,214],"modeling":[2,43],"is":[3,217],"the":[4,32,207],"problem":[5],"of":[6,191,209],"estimating":[7,87],"how":[8],"a":[9,58,75,80,118,122,134,187],"robot's":[10],"behavior":[11],"changes":[12,23],"task":[13,59],"progress":[14,41,108,147],"over":[15],"time.":[16],"Reliable":[17],"estimation":[18],"requires":[19],"distinguishing":[20],"meaningful":[21],"state":[22],"from":[24,110,178],"failed":[25],"attempts":[26],"and":[27,57,70,84,97,126,132,161,203],"task-irrelevant":[28],"actions.":[29],"We":[30,114,169],"introduce":[31],"Agentic":[33],"Reward":[34],"System":[35],"(ARS),":[36],"an":[37,54,192],"inference":[38,202],"framework":[39],"for":[40,66,212],"with":[44,117],"general-purpose":[45,210],"vision-language":[46],"models":[47],"(VLMs),":[48],"without":[49],"additional":[50],"reward-model":[51],"training.":[52],"Given":[53],"offline":[55,180],"trajectory":[56],"instruction,":[60],"ARS":[61,90,116,156,173],"uses":[62],"adaptive":[63],"visual":[64,98],"inspection":[65],"both":[67],"event":[68,77],"proposal":[69],"verification.":[71],"A":[72],"subagent":[73],"proposes":[74],"task-relevant":[76],"timeline,":[78],"which":[79],"primary":[81],"agent":[82],"verifies":[83],"revises":[85],"before":[86],"per-frame":[88],"progress.":[89],"can":[91,105,205],"incorporate":[92],"optional":[93],"terminal":[94],"outcome":[95],"labels":[96],"references":[99],"to":[100,148],"inform":[101],"its":[102],"judgments.":[103],"It":[104],"also":[106],"audit":[107],"estimates":[109],"external":[111],"models.":[113],"evaluate":[115],"27B":[119],"VLM":[120],"on":[121,133,182],"controlled":[123],"semantic-mismatch":[124],"benchmark":[125,138],"downstream":[127],"policy":[128,167,176],"learning":[129,177],"in":[130,152,165,186],"simulation":[131,166],"real":[135],"robot.":[136],"The":[137],"reveals":[139],"that":[140,172,200],"several":[141],"evaluated":[142],"baselines":[144,164],"assign":[145],"spurious":[146],"wrong-object":[149],"manipulation":[150],"even":[151],"simple":[153],"pick-and-place":[154],"scenes.":[155],"better":[157],"suppresses":[158],"these":[159,163],"errors":[160],"outperforms":[162],"learning.":[168],"further":[170],"demonstrate":[171],"supports":[174],"long-horizon":[175],"mixed-quality":[179],"experience":[181],"real-robot":[183],"multi-screw":[184],"fastening":[185],"full-scale":[188],"laboratory":[189],"replica":[190],"industrial":[193],"washing-machine":[194],"assembly":[195],"line.":[196],"These":[197],"results":[198],"suggest":[199],"structured":[201],"verification":[204],"improve":[206],"usefulness":[208],"VLMs":[211],"robot":[213],"modeling.":[215],"Code":[216],"at":[218],"https://github.com/midea-ai/ars":[219]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-30T00:00:00"}