{"id":"https://openalex.org/W7204875813","doi":"https://doi.org/10.48550/arxiv.2608.31167","title":"SUN: Agentic Robot Policy Learning with Persistent Task Programs","display_name":"SUN: Agentic Robot Policy Learning with Persistent Task Programs","publication_year":2026,"publication_date":"2026-08-31","ids":{"openalex":"https://openalex.org/W7204875813","doi":"https://doi.org/10.48550/arxiv.2608.31167"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.31167","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.31167","pdf_url":"https://arxiv.org/pdf/2608.31167","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.31167","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148842592","display_name":"Weiqi Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Weiqi","raw_affiliation_strings":["University of California , Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148850498","display_name":"Zhi Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Zhi","raw_affiliation_strings":["University of California , Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148918154","display_name":"Yudong Lei","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei, Yudong","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148867724","display_name":"David Martinez","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martinez, David","raw_affiliation_strings":["University of California , Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148916037","display_name":"Xiaofeng Gao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gao, Xiaofeng","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148874706","display_name":"Yuxin Jiang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiang, Yuxin","raw_affiliation_strings":["University of California , Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123974411","display_name":"Chenfanfu Jiang","orcid":"https://orcid.org/0000-0003-3506-0583","observed_orcids":["https://orcid.org/0000-0003-3506-0583"]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiang, Chenfanfu","raw_affiliation_strings":["University of California , Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148863449","display_name":"Yingnian Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wu, Yingnian","raw_affiliation_strings":["University of California , Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034397232","display_name":"Demetri Terzopoulos","orcid":"https://orcid.org/0000-0003-4672-1279","observed_orcids":["https://orcid.org/0000-0003-4672-1279"]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Terzopoulos, Demetri","raw_affiliation_strings":["University of California , Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130185857","display_name":"Ran Gong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405258407","display_name":"Robotics and AI Institute","ror":"https://ror.org/00kqcs728","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gong, Ran","raw_affiliation_strings":["Robotics and AI Institute Project website : https:// kuafu-robo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics and AI Institute Project website : https:// kuafu-robo","institution_ids":["https://openalex.org/I4405258407"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":0.6474999785423279,"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":0.6474999785423279,"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":0.3452000021934509,"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":0.003800000064074993,"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/model-predictive-control","display_name":"model predictive control","score":0.7319999933242798},{"id":"https://openalex.org/keywords/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":0.6079999804496765},{"id":"https://openalex.org/keywords/long-horizon-manipulation","display_name":"long-horizon manipulation","score":0.8040000200271606},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.6489999890327454},{"id":"https://openalex.org/keywords/symbolic-planning","display_name":"symbolic planning","score":0.4569999873638153},{"id":"https://openalex.org/keywords/telerobotics","display_name":"telerobotics","score":0.5059999823570251}],"concepts":[{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.7541999816894531},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7102000117301941},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6638000011444092},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6464999914169312},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.6212000250816345},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.4950999915599823},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4390999972820282},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.4140999913215637},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4099000096321106},{"id":"https://openalex.org/C156325763","wikidata":"https://www.wikidata.org/wiki/Q1930895","display_name":"Operational semantics","level":3,"score":0.3693000078201294},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3659999966621399},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3653999865055084},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.32820001244544983},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3158999979496002},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.272599995136261}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.31167","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.31167","pdf_url":"https://arxiv.org/pdf/2608.31167","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.2608.31167","doi":"https://doi.org/10.48550/arxiv.2608.31167","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.31167","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:2608.31167","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.31167","pdf_url":"https://arxiv.org/pdf/2608.31167","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204875813.pdf","grobid_xml":"https://content.openalex.org/works/W7204875813.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7212839358","https://openalex.org/W7170084358","https://openalex.org/W7171561828","https://openalex.org/W7126116787","https://openalex.org/W7092294240","https://openalex.org/W3038245394","https://openalex.org/W4367365563","https://openalex.org/W7134067401","https://openalex.org/W6884980669","https://openalex.org/W4416967268"],"abstract_inverted_index":{"Model-based":[0],"control":[1,40],"can":[2,9],"directly":[3],"execute":[4],"specified":[5],"objectives,":[6,41],"while":[7],"learning":[8,45],"amortize":[10],"such":[11],"behaviors":[12],"into":[13,37],"reactive":[14],"policies,":[15],"making":[16],"their":[17],"combination":[18],"a":[19,51,55],"natural":[20],"solution":[21],"to":[22,58,73,80,136],"multi-stage":[23,94],"manipulation.":[24],"We":[25],"introduce":[26],"Semantically":[27],"UNified":[28],"(SUN)":[29],"Programs,":[30],"typed":[31],"executables":[32],"that":[33,120],"compile":[34],"grounded":[35],"relations":[36],"aligned":[38],"optimal":[39],"satisfaction":[42],"predicates,":[43],"and":[44,65,77,139],"rewards.":[46],"Our":[47],"harness,":[48],"Kuafu,":[49],"equips":[50],"foundation":[52],"model":[53],"as":[54],"task-level":[56],"agent":[57,69],"orchestrate":[59],"scene":[60],"preparation,":[61],"verification,":[62],"residual":[63],"RL,":[64],"data":[66,119],"production.":[67],"The":[68,132],"uses":[70],"program":[71],"feedback":[72],"repair":[74],"candidate":[75],"programs":[76],"training":[78],"diagnostics":[79],"calibrate":[81],"relative":[82],"reward":[83],"weights,":[84],"retaining":[85],"accepted":[86],"task":[87],"semantics":[88],"across":[89],"tool":[90],"calls.":[91],"Across":[92],"nine":[93],"manipulation":[95],"tasks,":[96],"Kuafu":[97],"achieves":[98],"82.03%":[99],"average":[100],"success":[101,123],"rate,":[102,117],"significantly":[103],"outperforming":[104],"all":[105],"learned":[106,109],"baselines.":[107],"Its":[108],"controllers":[110],"generate":[111],"demonstrations":[112],"at":[113],"10.57x":[114],"the":[115,129],"human-teleoperation":[116],"yielding":[118],"improve":[121],"visualpolicy":[122],"by":[124],"23.6":[125],"percentage":[126],"points":[127],"over":[128],"strongest":[130],"baseline.":[131],"policies":[133],"transfer":[134],"zero-shot":[135],"physical":[137],"Franka":[138],"Kinova":[140],"robots,":[141],"demonstrating":[142],"sim-to-real":[143],"generalization.":[144]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-02T00:00:00"}
