{"id":"https://openalex.org/W7214722606","doi":"https://doi.org/10.48550/arxiv.2609.35532","title":"ARISE: Adapting to Evolving Capability Gaps in Agentic Reinforcement Learning","display_name":"ARISE: Adapting to Evolving Capability Gaps in Agentic Reinforcement Learning","publication_year":2026,"publication_date":"2026-09-28","ids":{"openalex":"https://openalex.org/W7214722606","doi":"https://doi.org/10.48550/arxiv.2609.35532"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.35532","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.35532","pdf_url":"https://arxiv.org/pdf/2609.35532","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/2609.35532","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153551570","display_name":"Kun Feng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]},{"id":"https://openalex.org/I4405270328","display_name":"Ant Group (China)","ror":"https://ror.org/00g5w7n47","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405270328"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng, Kun","raw_affiliation_strings":["Ant Group","ShanghaiTech University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":["https://openalex.org/I4405270328"]},{"raw_affiliation_string":"ShanghaiTech University","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153422106","display_name":"Yuchen Fang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405270328","display_name":"Ant Group (China)","ror":"https://ror.org/00g5w7n47","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405270328"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fang, Yuchen","raw_affiliation_strings":["Ant Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":["https://openalex.org/I4405270328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137373030","display_name":"Yiyang Tan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tan, Yiyang","raw_affiliation_strings":["ShanghaiTech University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128275892","display_name":"Shuqi Gu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gu, Shuqi","raw_affiliation_strings":["ShanghaiTech University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128200412","display_name":"Yongxiang Zhao","orcid":"https://orcid.org/0009-0006-2988-2483","observed_orcids":["https://orcid.org/0009-0006-2988-2483"]},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao, Yongxiang","raw_affiliation_strings":["ShanghaiTech University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153478528","display_name":"Yu Liu","orcid":"https://orcid.org/0009-0002-4457-114X","observed_orcids":["https://orcid.org/0009-0002-4457-114X"]},"institutions":[{"id":"https://openalex.org/I4405270328","display_name":"Ant Group (China)","ror":"https://ror.org/00g5w7n47","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405270328"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Yu","raw_affiliation_strings":["Ant Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":["https://openalex.org/I4405270328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153405611","display_name":"Xingyu Lu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405270328","display_name":"Ant Group (China)","ror":"https://ror.org/00g5w7n47","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405270328"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu, Xingyu","raw_affiliation_strings":["Ant Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":["https://openalex.org/I4405270328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153463529","display_name":"Lintao Ma","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405270328","display_name":"Ant Group (China)","ror":"https://ror.org/00g5w7n47","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405270328"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ma, Lintao","raw_affiliation_strings":["Ant Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":["https://openalex.org/I4405270328"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102807475","display_name":"Kan Ren","orcid":"https://orcid.org/0000-0002-4032-9615","observed_orcids":["https://orcid.org/0000-0002-4032-9615"]},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ren, Kan","raw_affiliation_strings":["ShanghaiTech University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University","institution_ids":["https://openalex.org/I30809798"]}]}],"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":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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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":0.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0,"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/agentic-reinforcement-learning","display_name":"agentic reinforcement learning","score":0.8989999890327454},{"id":"https://openalex.org/keywords/capability-gaps","display_name":"capability gaps","score":0.8960000276565552},{"id":"https://openalex.org/keywords/exploration-guidance","display_name":"exploration guidance","score":0.5540000200271606},{"id":"https://openalex.org/keywords/long-horizon-agents","display_name":"long-horizon agents","score":0.9169999957084656},{"id":"https://openalex.org/keywords/training-efficiency","display_name":"training efficiency","score":0.41999998688697815}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7387999892234802},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6413999795913696},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6061999797821045},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5999000072479248},{"id":"https://openalex.org/C111640148","wikidata":"https://www.wikidata.org/wiki/Q847349","display_name":"Rubric","level":2,"score":0.4562000036239624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3935000002384186},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.38839998841285706},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.36559998989105225},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.358599990606308},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33180001378059387},{"id":"https://openalex.org/C63882131","wikidata":"https://www.wikidata.org/wiki/Q17122954","display_name":"Strengths and weaknesses","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C125014702","wikidata":"https://www.wikidata.org/wiki/Q4680749","display_name":"Adaptive learning","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C52970973","wikidata":"https://www.wikidata.org/wiki/Q2497134","display_name":"Adaptive system","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30230000615119934},{"id":"https://openalex.org/C68784500","wikidata":"https://www.wikidata.org/wiki/Q1570691","display_name":"Adaptive behavior","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.28610000014305115},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.27810001373291016},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2703000009059906},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.26179999113082886}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.35532","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.35532","pdf_url":"https://arxiv.org/pdf/2609.35532","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.2609.35532","doi":"https://doi.org/10.48550/arxiv.2609.35532","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.35532","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:2609.35532","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.35532","pdf_url":"https://arxiv.org/pdf/2609.35532","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":[{"id":"https://openalex.org/F4320318398","display_name":"Ant Group","ror":"https://ror.org/00g5w7n47"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327675","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214722606.pdf","grobid_xml":"https://content.openalex.org/works/W7214722606.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W4414786804","https://openalex.org/W4415235458","https://openalex.org/W7075994024","https://openalex.org/W7133222210","https://openalex.org/W7162781541","https://openalex.org/W7164944187"],"related_works":["https://openalex.org/W7206216304","https://openalex.org/W7220978366","https://openalex.org/W7213286606","https://openalex.org/W7160646979","https://openalex.org/W7170722420","https://openalex.org/W7223018417","https://openalex.org/W7160887731","https://openalex.org/W7214701586","https://openalex.org/W7163174640","https://openalex.org/W7221034380"],"abstract_inverted_index":{"As":[0],"a":[1,32,93],"long-horizon":[2,151],"agent":[3,49,152],"improves":[4],"through":[5],"experience,":[6],"previously":[7],"observed":[8],"weaknesses":[9],"may":[10,73],"recede":[11],"while":[12,51,118],"new":[13],"limitations":[14],"emerge,":[15],"continually":[16,102],"changing":[17],"what":[18],"it":[19],"still":[20],"needs":[21],"to":[22,31,60,101,113,127],"learn.":[23],"Yet":[24],"the":[25,70,76],"learning":[26,95],"process":[27],"often":[28],"remains":[29],"tied":[30],"static":[33],"view":[34],"of":[35],"these":[36],"needs:":[37],"fixed":[38],"behavioral":[39,116],"criteria":[40],"and":[41,108,124,155,166],"training":[42,109,167],"priorities":[43],"can":[44],"become":[45],"misaligned":[46],"with":[47],"evolving":[48],"capabilities,":[50],"sparse":[52],"task-level":[53],"feedback":[54],"makes":[55],"such":[56],"misalignment":[57],"more":[58],"difficult":[59],"detect.":[61],"Even":[62],"when":[63],"capability":[64],"gaps":[65],"are":[66,122],"identified,":[67],"rollouts":[68],"from":[69],"current":[71],"policy":[72],"repeatedly":[74],"reproduce":[75],"same":[77],"failures":[78],"rather":[79],"than":[80],"explore":[81],"better":[82],"alternatives.":[83],"To":[84],"address":[85],"this,":[86],"we":[87],"introduce":[88],"Adaptive":[89],"Rubric-Skill":[90],"Co-Evolution":[91],"(ARISE),":[92],"reinforcement":[94],"framework":[96],"that":[97,141,158],"uses":[98],"rollout":[99],"evidence":[100],"adapt":[103],"evaluation":[104],"criteria,":[105],"exploration":[106,129],"guidance,":[107],"priorities.":[110],"Rubrics":[111],"evolve":[112],"reward":[114],"partial":[115],"progress,":[117],"their":[119],"paired":[120],"skills":[121],"refined":[123],"selectively":[125],"activated":[126],"guide":[128],"toward":[130],"unresolved":[131],"weaknesses.":[132],"Alongside":[133],"this":[134],"co-evolution,":[135],"capability-based":[136],"adaptive":[137],"sampling":[138],"prioritizes":[139],"tasks":[140],"target":[142],"behaviors":[143],"needing":[144],"further":[145],"improvement.":[146],"Experiments":[147],"on":[148],"two":[149],"challenging":[150],"benchmarks,":[153],"SkillsBench":[154],"Terminal-Bench,":[156],"demonstrate":[157],"ARISE":[159],"successfully":[160],"enhances":[161],"both":[162],"overall":[163],"task":[164],"performance":[165],"efficiency.":[168],"The":[169],"project":[170],"page":[171],"is":[172],"at":[173],"https://foundation-model-research.github.io/ARISE":[174],".":[175]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-30T00:00:00"}