{"id":"https://openalex.org/W7203709979","doi":"https://doi.org/10.48550/arxiv.2608.15680","title":"Robo-Dopamine 2.0: History-Conditioned and OOD-Aware Process Reward Modeling for Robotic Manipulation","display_name":"Robo-Dopamine 2.0: History-Conditioned and OOD-Aware Process Reward Modeling for Robotic Manipulation","publication_year":2026,"publication_date":"2026-08-16","ids":{"openalex":"https://openalex.org/W7203709979","doi":"https://doi.org/10.48550/arxiv.2608.15680"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.15680","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.15680","pdf_url":"https://arxiv.org/pdf/2608.15680","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.15680","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5147419410","display_name":"Yijie Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Yijie","raw_affiliation_strings":["EvoPhys AI","State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EvoPhys AI","institution_ids":[]},{"raw_affiliation_string":"State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147417902","display_name":"Haopeng Jin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin, Haopeng","raw_affiliation_strings":["Beijing University of Posts and Telecommunications","Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147398059","display_name":"Run Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou, Run","raw_affiliation_strings":["Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147405695","display_name":"Shengbang Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Shengbang","raw_affiliation_strings":["Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000301628","display_name":"Sixiang Chen","orcid":"https://orcid.org/0009-0003-6837-886X","observed_orcids":["https://orcid.org/0009-0003-6837-886X","https://orcid.org/0000-0002-0910-8945"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Sixiang","raw_affiliation_strings":["EvoPhys AI","State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EvoPhys AI","institution_ids":[]},{"raw_affiliation_string":"State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147393820","display_name":"Hongyang Cheng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Hongyang","raw_affiliation_strings":["EvoPhys AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EvoPhys AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050323233","display_name":"Sicheng Hu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hu, Sicheng","raw_affiliation_strings":["EvoPhys AI","State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EvoPhys AI","institution_ids":[]},{"raw_affiliation_string":"State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033675065","display_name":"Peterson Anjunie Co","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Co, Peterson","raw_affiliation_strings":["EvoPhys AI","State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EvoPhys AI","institution_ids":[]},{"raw_affiliation_string":"State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147392982","display_name":"Jinwen Luo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luo, Jinwen","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112749105","display_name":"Huajie Tan","orcid":"https://orcid.org/0009-0004-3603-1893","observed_orcids":["https://orcid.org/0009-0004-3603-1893"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tan, Huajie","raw_affiliation_strings":["EvoPhys AI","State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EvoPhys AI","institution_ids":[]},{"raw_affiliation_string":"State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5147384015","display_name":"Shanghang Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Shanghang","raw_affiliation_strings":["State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.6894999742507935,"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":0.6894999742507935,"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":0.30640000104904175,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.001500000013038516,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/vision-language-action-models","display_name":"vision-language-action models","score":0.7609999775886536},{"id":"https://openalex.org/keywords/robotic-manipulation","display_name":"robotic manipulation","score":0.9710000157356262},{"id":"https://openalex.org/keywords/out-of-distribution-robustness","display_name":"out-of-distribution robustness","score":0.8849999904632568},{"id":"https://openalex.org/keywords/robotwin","display_name":"RoboTwin","score":0.656000018119812},{"id":"https://openalex.org/keywords/insertion-tasks","display_name":"insertion tasks","score":0.44600000977516174}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7541999816894531},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.7125999927520752},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6517000198364258},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.646399974822998},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6287000179290771},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5928999781608582},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5720000267028809},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5471000075340271},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5169000029563904},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5144000053405762},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.4339999854564667},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3156999945640564},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.28139999508857727},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C76956256","wikidata":"https://www.wikidata.org/wiki/Q27610560","display_name":"Process modeling","level":3,"score":0.27059999108314514},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.15680","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.15680","pdf_url":"https://arxiv.org/pdf/2608.15680","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.15680","doi":"https://doi.org/10.48550/arxiv.2608.15680","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.15680","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:2608.15680","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.15680","pdf_url":"https://arxiv.org/pdf/2608.15680","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203709979.pdf","grobid_xml":"https://content.openalex.org/works/W7203709979.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7117676596","https://openalex.org/W4414581628","https://openalex.org/W7164133502","https://openalex.org/W7138850231","https://openalex.org/W7130572361","https://openalex.org/W4417516760","https://openalex.org/W7118501563","https://openalex.org/W7168371273","https://openalex.org/W7161108916","https://openalex.org/W7203644814"],"abstract_inverted_index":{"Vision-language-action":[0],"(VLA)":[1],"models":[2,42],"improve":[3,150],"robotic":[4],"manipulation":[5],"but":[6],"remain":[7],"vulnerable":[8],"to":[9,158,165],"compounding":[10],"errors,":[11],"scene":[12],"changes,":[13],"and":[14,36,52,58,71,96,108,121,144,160,202],"off-trajectory":[15],"states.":[16],"Reinforcement":[17],"learning":[18],"can":[19],"refine":[20],"pretrained":[21],"VLA":[22],"policies,":[23],"yet":[24],"sparse":[25],"success":[26,201],"signals":[27],"hinder":[28],"exploration,":[29],"while":[30,103],"engineered":[31],"dense":[32],"rewards":[33,86],"are":[34],"costly":[35],"task-specific.":[37],"Existing":[38],"learned":[39],"visual":[40,152],"reward":[41,74],"often":[43],"rely":[44],"on":[45],"static":[46],"before-after":[47],"observations,":[48],"causing":[49],"temporal":[50],"ambiguity":[51],"weak":[53],"discrimination":[54],"between":[55],"robustness-preserving":[56],"variations":[57],"task-invalid":[59],"failures":[60],"under":[61],"out-of-distribution":[62],"(OOD)":[63],"execution.":[64],"We":[65,137],"introduce":[66],"Robo-Dopamine":[67],"2.0,":[68],"a":[69,77,145,186],"history-":[70],"OOD-aware":[72,111],"process":[73],"model":[75,196],"with":[76,126,175,183],"pairwise":[78,85],"prediction":[79],"interface.":[80],"It":[81],"combines":[82],"(1)":[83],"history-conditioned":[84],"that":[87,115],"use":[88],"source-aligned":[89],"reference":[90],"panels":[91,149],"for":[92,100,185],"synthetic":[93],"OOD":[94,141],"queries":[95],"observed":[97],"rollout":[98],"history":[99],"online":[101],"queries,":[102],"preserving":[104],"the":[105,168,194],"queried":[106],"endpoints,":[107],"(2)":[109],"an":[110,140],"signed":[112],"progress":[113,135],"space":[114],"represents":[116],"valid":[117],"progress,":[118],"robustness,":[119],"failure,":[120],"recovery.":[122],"A":[123],"Signed-Hop":[124,173],"Curriculum":[125],"transition-aware":[127],"replay":[128,177],"learns":[129],"coarse":[130],"execution":[131],"ordering":[132],"before":[133],"fine-grained":[134],"calibration.":[136],"also":[138],"construct":[139],"trajectory":[142],"dataset":[143],"five-family":[146],"benchmark.":[147],"Reference":[148],"mean":[151,180,199],"order":[153],"consistency":[154],"(VOC)":[155],"from":[156,163],"0.967":[157],"0.986":[159],"OOD-robust":[161],"VOC":[162],"0.906":[164],"0.958.":[166],"With":[167],"same":[169],"400K":[170],"pairwise-reward":[171],"budget,":[172],"training":[174],"25%":[176],"reaches":[178],"0.9872":[179],"VOC,":[181],"compared":[182],"0.9858":[184],"matched-pool":[187],"shuffled":[188],"control.":[189],"In":[190],"downstream":[191],"reinforcement":[192],"learning,":[193],"full":[195],"achieves":[197],"86.8%":[198],"RoboTwin":[200],"71/80":[203],"successful":[204],"real-world":[205],"insertions.":[206]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-19T00:00:00"}