{"id":"https://openalex.org/W7203705067","doi":"https://doi.org/10.48550/arxiv.2608.16889","title":"Don't Drop the BATON: Long-Horizon Robot Manipulation via Agentic Subtask Exploration and Transition-aware Memory","display_name":"Don't Drop the BATON: Long-Horizon Robot Manipulation via Agentic Subtask Exploration and Transition-aware Memory","publication_year":2026,"publication_date":"2026-08-17","ids":{"openalex":"https://openalex.org/W7203705067","doi":"https://doi.org/10.48550/arxiv.2608.16889"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.16889","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.16889","pdf_url":"https://arxiv.org/pdf/2608.16889","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/2608.16889","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5147396588","display_name":"Bingxin Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xu, Bingxin","raw_affiliation_strings":["University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123600553","display_name":"Yuzhang Shang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shang, Yuzhang","raw_affiliation_strings":["University of Central Florida"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Central Florida","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078699564","display_name":"Emilio Ferrara","orcid":"https://orcid.org/0000-0002-1942-2831","observed_orcids":["https://orcid.org/0000-0002-1942-2831"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ferrara, Emilio","raw_affiliation_strings":["University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":15,"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":0.9922000169754028,"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":0.9922000169754028,"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":0.005799999926239252,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.0012000000569969416,"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/llm-coding-agents","display_name":"LLM coding agents","score":0.6520000100135803},{"id":"https://openalex.org/keywords/vision-language-action-models","display_name":"vision-language-action models","score":0.9369999766349792},{"id":"https://openalex.org/keywords/world-action-models","display_name":"world action models","score":0.8610000014305115},{"id":"https://openalex.org/keywords/error-attribution","display_name":"error attribution","score":0.3709999918937683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.660099983215332},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6256999969482422},{"id":"https://openalex.org/C75306776","wikidata":"https://www.wikidata.org/wiki/Q7632662","display_name":"Successor cardinal","level":2,"score":0.4092000126838684},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4068000018596649},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38510000705718994},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.35370001196861267},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.32690000534057617},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C149499870","wikidata":"https://www.wikidata.org/wiki/Q1411613","display_name":"Hoist (device)","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C100521375","wikidata":"https://www.wikidata.org/wiki/Q2015382","display_name":"Competence (human resources)","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C95667121","wikidata":"https://www.wikidata.org/wiki/Q7661175","display_name":"Symbolic communication","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2581000030040741},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.16889","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.16889","pdf_url":"https://arxiv.org/pdf/2608.16889","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.2608.16889","doi":"https://doi.org/10.48550/arxiv.2608.16889","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.16889","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:2608.16889","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.16889","pdf_url":"https://arxiv.org/pdf/2608.16889","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/W7203705067.pdf","grobid_xml":"https://content.openalex.org/works/W7203705067.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W4226111844","https://openalex.org/W4378505261","https://openalex.org/W4385403811","https://openalex.org/W4385473486","https://openalex.org/W4399695759","https://openalex.org/W4414079054","https://openalex.org/W4414674749","https://openalex.org/W4414901575","https://openalex.org/W4414970058","https://openalex.org/W4415276858","https://openalex.org/W4416045178","https://openalex.org/W7130730707","https://openalex.org/W7133740112","https://openalex.org/W7134037000","https://openalex.org/W7140328093","https://openalex.org/W7157741357","https://openalex.org/W7160621105","https://openalex.org/W7160889634","https://openalex.org/W7160902854","https://openalex.org/W7161145657","https://openalex.org/W7163155583","https://openalex.org/W7164000068","https://openalex.org/W7167029019","https://openalex.org/W7167575744","https://openalex.org/W7167640155","https://openalex.org/W7167682355","https://openalex.org/W7167900256","https://openalex.org/W7169828180"],"related_works":["https://openalex.org/W7123909538","https://openalex.org/W7131648928","https://openalex.org/W7221810922","https://openalex.org/W7106476763","https://openalex.org/W7172396455","https://openalex.org/W7078174358","https://openalex.org/W7094950651","https://openalex.org/W7077865453","https://openalex.org/W7220691198","https://openalex.org/W7203682176"],"abstract_inverted_index":{"Long-horizon":[0],"robot":[1],"manipulation":[2],"chains":[3],"many":[4],"contact-rich":[5,71],"skills":[6],"into":[7,76],"one":[8,35,108,217],"multi-stage":[9],"task.":[10],"Vision-language-action":[11],"(VLA)":[12],"and":[13,34,47,73,122,149,187,211,266,289],"world-action":[14],"models":[15],"(WAMs)":[16],"increasingly":[17],"master":[18],"individual":[19],"skills,":[20],"yet":[21],"the":[22,29,39,45,67,103,118,139,172,174,183,235,238,244,248,263,271,275,280,295],"chain":[23],"still":[24],"fails:":[25],"errors":[26],"compound":[27],"beyond":[28],"policy's":[30],"ability":[31],"to":[32,81,164,216],"correct,":[33],"subtask":[36,151,173,179],"silently":[37],"constrains":[38],"next.":[40],"A":[41],"promising":[42],"pathway":[43],"freezes":[44],"VLA":[46,68,140,239],"puts":[48],"an":[49,143,258],"LLM":[50],"coding":[51],"agent":[52,233],"in":[53,57,60,102,154,182,191],"charge:":[54],"it":[55],"plans":[56],"language,":[58],"moves":[59],"free":[61],"space":[62],"with":[63,224],"analytic":[64],"primitives,":[65],"invokes":[66],"only":[69,242],"for":[70],"segments,":[72],"writes":[74],"adaptation":[75],"language":[77],"memory.":[78,227],"Yet":[79],"applied":[80],"long":[82],"horizons,":[83],"this":[84],"recipe":[85],"breaks":[86],"twice.":[87],"(1)":[88],"Its":[89],"competence":[90],"comes":[91],"from":[92,199],"whole-task":[93],"exploration":[94,223],"at":[95],"test":[96],"time,":[97],"whose":[98,273],"cost":[99,207],"is":[100,180,196,214,240,250],"exponential":[101],"number":[104],"of":[105,120,137,176],"stages:":[106],"if":[107],"stage":[109,129],"needs":[110,116],"T":[111],"episodes,":[112],"a":[113,123,150,155,193,225,229,231,254,267],"K-stage":[114],"task":[115,285],"on":[117],"order":[119],"T^K,":[121],"failure":[124,213],"does":[125],"not":[126],"reveal":[127],"which":[128],"caused":[130],"it.":[131],"(2)":[132],"It":[133],"has":[134],"no":[135,146],"representation":[136],"transitions:":[138],"primitive":[141],"carries":[142],"exit":[144],"but":[145],"entry":[147,259],"condition,":[148],"can":[152,277],"succeed":[153],"form":[156],"its":[157,188],"successor":[158,276],"cannot":[159],"use.":[160],"We":[161],"present":[162],"BATON":[163,170,221,283],"address":[165],"both":[166],"failures.":[167],"Against":[168,219],"(1),":[169],"makes":[171],"unit":[175],"exploration:":[177],"each":[178,212],"explored":[181],"cheap":[184],"short-horizon":[185],"regime":[186],"solution":[189],"stored":[190],"memory;":[192],"long-horizon":[194],"trajectory":[195],"then":[197],"composed":[198],"these":[200],"solutions":[201],"rather":[202],"than":[203],"discovered":[204],"whole.":[205],"Exploration":[206],"becomes":[208],"linear":[209],"(KT),":[210],"attributed":[215],"stage.":[218],"(2),":[220],"equips":[222],"transition-aware":[226],"Within":[228],"subtask,":[230],"verifier":[232],"governs":[234],"invocation":[236],"transition:":[237],"invoked":[241],"after":[243],"wrist":[245],"view":[246],"confirms":[247],"scene":[249],"ready.":[251],"Across":[252],"subtasks,":[253],"handoff":[255],"transition":[256,269],"restores":[257],"state":[260],"disturbed":[261],"by":[262,287,292],"predecessor's":[264],"residue,":[265],"lookahead":[268],"selects":[270],"strategy":[272],"outcome":[274],"inherit.":[278],"On":[279],"RoboMemArena":[281],"benchmark,":[282],"improves":[284],"success":[286,291],"37.7%":[288],"cumulative":[290],"29.7%":[293],"over":[294],"SoTA.":[296]},"counts_by_year":[{"year":2026,"cited_by_count":15}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-08-19T00:00:00"}