{"id":"https://openalex.org/W7150828934","doi":"https://doi.org/10.48550/arxiv.2604.03128","title":"Self-Distilled RLVR","display_name":"Self-Distilled RLVR","publication_year":2026,"publication_date":"2026-04-03","ids":{"openalex":"https://openalex.org/W7150828934","doi":"https://doi.org/10.48550/arxiv.2604.03128"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2604.03128","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2604.03128","pdf_url":"https://arxiv.org/pdf/2604.03128","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/2604.03128","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133013498","display_name":"Chenxu Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Chenxu","raw_affiliation_strings":["Institute of Information Engineering , Chinese Academy of Sciences , Beijing , China,","School of Cyber Security , University of Chinese Academy of Sciences , Beijing , China,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering , Chinese Academy of Sciences , Beijing , China,","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"raw_affiliation_string":"School of Cyber Security , University of Chinese Academy of Sciences , Beijing , China,","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124402667","display_name":"Chuanyu Qin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin, Chuanyu","raw_affiliation_strings":["Institute of Information Engineering , Chinese Academy of Sciences , Beijing , China,","School of Cyber Security , University of Chinese Academy of Sciences , Beijing , China,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering , Chinese Academy of Sciences , Beijing , China,","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"raw_affiliation_string":"School of Cyber Security , University of Chinese Academy of Sciences , Beijing , China,","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013535642","display_name":"Qingyi Si","orcid":"https://orcid.org/0000-0001-8433-0215","observed_orcids":["https://orcid.org/0000-0001-8433-0215"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Si, Qingyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120604377","display_name":"Minghui Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Minghui","raw_affiliation_strings":["Institute of Information Engineering , Chinese Academy of Sciences , Beijing , China,","School of Cyber Security , University of Chinese Academy of Sciences , Beijing , China,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering , Chinese Academy of Sciences , Beijing , China,","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"raw_affiliation_string":"School of Cyber Security , University of Chinese Academy of Sciences , Beijing , China,","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112974314","display_name":"Naibin Gu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gu, Naibin","raw_affiliation_strings":["Institute of Information Engineering , Chinese Academy of Sciences , Beijing , China,","School of Cyber Security , University of Chinese Academy of Sciences , Beijing , China,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering , Chinese Academy of Sciences , Beijing , China,","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"raw_affiliation_string":"School of Cyber Security , University of Chinese Academy of Sciences , Beijing , China,","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013346368","display_name":"Dingyu Yao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao, Dingyu","raw_affiliation_strings":["Institute of Information Engineering , Chinese Academy of Sciences , Beijing , China,","School of Cyber Security , University of Chinese Academy of Sciences , Beijing , China,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering , Chinese Academy of Sciences , Beijing , China,","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"raw_affiliation_string":"School of Cyber Security , University of Chinese Academy of Sciences , Beijing , China,","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148437336","display_name":"Zheng Lin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin, Zheng","raw_affiliation_strings":["Institute of Information Engineering , Chinese Academy of Sciences , Beijing , China,","School of Cyber Security , University of Chinese Academy of Sciences , Beijing , China,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering , Chinese Academy of Sciences , Beijing , China,","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"raw_affiliation_string":"School of Cyber Security , University of Chinese Academy of Sciences , Beijing , China,","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100442321","display_name":"Weiping Wang","orcid":"https://orcid.org/0000-0002-8618-4992","observed_orcids":["https://orcid.org/0000-0002-8618-4992"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Weiping","raw_affiliation_strings":["Institute of Information Engineering , Chinese Academy of Sciences , Beijing , China,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering , Chinese Academy of Sciences , Beijing , China,","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133035995","display_name":"Jiaqi Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jiaqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138266330","display_name":"Nan Duan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duan, Nan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.6312999725341797,"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":0.6312999725341797,"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/T10028","display_name":"Topic Modeling","score":0.19380000233650208,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.05480000004172325,"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/on-policy-distillation","display_name":"on-policy distillation","score":0.7400000095367432},{"id":"https://openalex.org/keywords/self-distillation","display_name":"self-distillation","score":0.8450000286102295},{"id":"https://openalex.org/keywords/reinforcement-learning-with-verifiable-rewards","display_name":"reinforcement learning with verifiable rewards","score":0.9879999756813049},{"id":"https://openalex.org/keywords/information-leakage","display_name":"information leakage","score":0.7099999785423279},{"id":"https://openalex.org/keywords/training-stability","display_name":"training stability","score":0.734000027179718},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.5759999752044678},{"id":"https://openalex.org/keywords/self-evolution","display_name":"self-evolution","score":0.5889999866485596}],"concepts":[{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.8169000148773193},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7337999939918518},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5985000133514404},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5146999955177307},{"id":"https://openalex.org/C2777489069","wikidata":"https://www.wikidata.org/wiki/Q1589822","display_name":"Ceiling (cloud)","level":2,"score":0.43860000371932983},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.3955000042915344},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38830000162124634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3725000023841858},{"id":"https://openalex.org/C89246107","wikidata":"https://www.wikidata.org/wiki/Q1398821","display_name":"Rule of thumb","level":2,"score":0.3416000008583069},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2700999975204468}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2604.03128","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2604.03128","pdf_url":"https://arxiv.org/pdf/2604.03128","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.2604.03128","doi":"https://doi.org/10.48550/arxiv.2604.03128","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.03128","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:2604.03128","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2604.03128","pdf_url":"https://arxiv.org/pdf/2604.03128","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":[{"score":0.4156000018119812,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7150828934.pdf","grobid_xml":"https://content.openalex.org/works/W7150828934.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7221788125","https://openalex.org/W7211880912","https://openalex.org/W7214931014","https://openalex.org/W7161258139","https://openalex.org/W7163590749","https://openalex.org/W7167917130","https://openalex.org/W7204222579","https://openalex.org/W7220652251","https://openalex.org/W7202213136","https://openalex.org/W7148703720"],"abstract_inverted_index":{"On-policy":[0],"distillation":[1],"(OPD)":[2],"has":[3,54],"become":[4],"a":[5,16,162],"popular":[6],"training":[7,168],"paradigm":[8,14],"in":[9,31,48,96],"the":[10,20,49,52,60,70,92,107,154],"LLM":[11],"community.":[12],"This":[13,83,148],"selects":[15],"larger":[17],"model":[18,62],"as":[19,64,77],"teacher":[21,66,71,94],"to":[22,33,80,122,134,137,151],"provide":[23],"dense,":[24],"fine-grained":[25,129],"signals":[26,44,88],"for":[27,110,127],"each":[28],"sampled":[29],"trajectory,":[30],"contrast":[32],"reinforcement":[34],"learning":[35,87],"with":[36,69,116],"verifiable":[37,46],"rewards":[38],"(RLVR),":[39],"which":[40],"only":[41],"obtains":[42],"sparse":[43],"from":[45,91,142],"outcomes":[47],"environment.":[50],"Recently,":[51],"community":[53],"explored":[55],"on-policy":[56],"self-distillation":[57,111,121],"(OPSD),":[58],"where":[59],"same":[61],"serves":[63],"both":[65,157],"and":[67,100,112,159,166],"student,":[68],"receiving":[72],"additional":[73],"privileged":[74,93],"information":[75,98],"such":[76],"reference":[78],"answers":[79],"enable":[81],"self-evolution.":[82],"paper":[84],"demonstrates":[85],"that":[86],"solely":[89],"derived":[90],"result":[95],"severe":[97],"leakage":[99],"unstable":[101],"long-term":[102],"training.":[103],"Accordingly,":[104],"we":[105,119],"identify":[106],"optimal":[108],"niche":[109],"propose":[113],"\\textbf{RLSD}":[114],"(\\textbf{RL}VR":[115],"\\textbf{S}elf-\\textbf{D}istillation).":[117],"Specifically,":[118],"leverage":[120],"obtain":[123],"token-level":[124],"policy":[125],"differences":[126],"determining":[128],"update":[130,140],"magnitudes,":[131],"while":[132],"continuing":[133],"use":[135],"RLVR":[136,158],"derive":[138],"reliable":[139],"directions":[141],"environmental":[143],"feedback":[144],"(e.g.,":[145],"response":[146],"correctness).":[147],"enables":[149],"RLSD":[150],"simultaneously":[152],"harness":[153],"strengths":[155],"of":[156],"OPSD,":[160],"achieving":[161],"higher":[163],"convergence":[164],"ceiling":[165],"superior":[167],"stability.":[169]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-04-07T00:00:00"}
