{"id":"https://openalex.org/W7203896718","doi":"https://doi.org/10.48550/arxiv.2608.18574","title":"Beyond Forgetting: Diagnosing and Harnessing Shared Reasoning in Continual RLVR","display_name":"Beyond Forgetting: Diagnosing and Harnessing Shared Reasoning in Continual RLVR","publication_year":2026,"publication_date":"2026-08-19","ids":{"openalex":"https://openalex.org/W7203896718","doi":"https://doi.org/10.48550/arxiv.2608.18574"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.18574","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.18574","pdf_url":"https://arxiv.org/pdf/2608.18574","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/2608.18574","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127962369","display_name":"Lirui Luo","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"]},{"id":"https://openalex.org/I4392738278","display_name":"Beijing Institute for General Artificial Intelligence","ror":"https://ror.org/02kw1ws04","country_code":"CN","type":"government","lineage":["https://openalex.org/I4392738278"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luo, Lirui","raw_affiliation_strings":["State Key Lab of General AI , School of Intelligence Science and Technology , Peking University","State Key Laboratory of General Artificial Intelligence , BIGAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab of General AI , School of Intelligence Science and Technology , Peking University","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"State Key Laboratory of General Artificial Intelligence , BIGAI","institution_ids":["https://openalex.org/I4392738278"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127916793","display_name":"Guoxi Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4392738278","display_name":"Beijing Institute for General Artificial Intelligence","ror":"https://ror.org/02kw1ws04","country_code":"CN","type":"government","lineage":["https://openalex.org/I4392738278"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Guoxi","raw_affiliation_strings":["State Key Laboratory of General Artificial Intelligence , BIGAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of General Artificial Intelligence , BIGAI","institution_ids":["https://openalex.org/I4392738278"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127968880","display_name":"Hongming Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4392738278","display_name":"Beijing Institute for General Artificial Intelligence","ror":"https://ror.org/02kw1ws04","country_code":"CN","type":"government","lineage":["https://openalex.org/I4392738278"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Hongming","raw_affiliation_strings":["State Key Laboratory of General Artificial Intelligence , BIGAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of General Artificial Intelligence , BIGAI","institution_ids":["https://openalex.org/I4392738278"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153453708","display_name":"Rongqing Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Rongqing","raw_affiliation_strings":["Beijing Institute of Technology Project page : https://crg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology Project page : https://crg","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128012948","display_name":"Cong Fang","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":"Fang, Cong","raw_affiliation_strings":["Institute for Artificial Intelligence , Peking University","State Key Lab of General AI , School of Intelligence Science and Technology , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence , Peking University","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"State Key Lab of General AI , School of Intelligence Science and Technology , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5150890124","display_name":"Lifeng Fan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4392738278","display_name":"Beijing Institute for General Artificial Intelligence","ror":"https://ror.org/02kw1ws04","country_code":"CN","type":"government","lineage":["https://openalex.org/I4392738278"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan, Lifeng","raw_affiliation_strings":["State Key Laboratory of General Artificial Intelligence , BIGAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of General Artificial Intelligence , BIGAI","institution_ids":["https://openalex.org/I4392738278"]}]}],"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.8407999873161316,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.8407999873161316,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.0835999995470047,"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":0.036400001496076584,"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/forgetting","display_name":"forgetting","score":0.4909999966621399},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"multi-task learning","score":0.6019999980926514},{"id":"https://openalex.org/keywords/continual-learning","display_name":"continual learning","score":0.4740000069141388},{"id":"https://openalex.org/keywords/task-sequences","display_name":"task sequences","score":0.32100000977516174}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7663000226020813},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.705299973487854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.585099995136261},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.5713000297546387},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5138000249862671},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.4788999855518341},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.45910000801086426},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3865000009536743},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3783000111579895},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3596999943256378},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.35659998655319214},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.34279999136924744},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.3188999891281128},{"id":"https://openalex.org/C2985612853","wikidata":"https://www.wikidata.org/wiki/Q185816","display_name":"Analogical reasoning","level":3,"score":0.29350000619888306},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2581999897956848}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.18574","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.18574","pdf_url":"https://arxiv.org/pdf/2608.18574","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.2608.18574","doi":"https://doi.org/10.48550/arxiv.2608.18574","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.18574","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:2608.18574","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.18574","pdf_url":"https://arxiv.org/pdf/2608.18574","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/W7203896718.pdf","grobid_xml":"https://content.openalex.org/works/W7203896718.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W3177813494","https://openalex.org/W4387561459","https://openalex.org/W4407759434","https://openalex.org/W4414846785"],"related_works":["https://openalex.org/W7161755411","https://openalex.org/W7101718868","https://openalex.org/W7214088552","https://openalex.org/W7128541502","https://openalex.org/W7171321448","https://openalex.org/W7167610484","https://openalex.org/W6948023928","https://openalex.org/W7156264080","https://openalex.org/W7163326836","https://openalex.org/W7166588711"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,158],"with":[2,173],"verifiable":[3],"rewards":[4],"(RLVR)":[5],"commonly":[6],"post-trains":[7],"reasoning":[8,77,133,155],"models":[9],"on":[10,137,143,159],"multiple":[11],"tasks,":[12],"while":[13],"rerunning":[14],"multitask":[15],"RLVR":[16,92],"(MTRL)":[17],"as":[18,37,53,55],"new":[19],"tasks":[20,78,164],"are":[21],"added":[22],"makes":[23],"capability":[24],"expansion":[25],"costly.":[26],"We":[27,145],"therefore":[28,146],"study":[29],"continual":[30],"RLVR,":[31],"which":[32,152],"updates":[33],"the":[34,107,122,126,160,174],"existing":[35],"model":[36,47],"each":[38],"task":[39,81,139],"arrives.":[40],"The":[41],"central":[42],"question":[43],"is":[44],"whether":[45],"a":[46,56,69],"updated":[48],"this":[49,62,84],"way":[50],"can":[51],"perform":[52],"well":[54],"jointly":[57],"trained":[58],"model.":[59],"To":[60,105,124],"answer":[61],"question,":[63],"we":[64,86,109,128],"introduce":[65,147],"Continual":[66,148],"Reasoning":[67],"Gym,":[68],"continual-RLVR":[70],"environment":[71],"that":[72,102,115],"organizes":[73],"text":[74],"and":[75,113,162,169],"visual":[76],"into":[79],"five":[80],"sequences.":[82],"In":[83],"setting,":[85],"identify":[87,129],"two":[88],"key":[89],"observations:":[90],"Sequential":[91],"exhibits":[93],"modest":[94],"forgetting,":[95],"yet":[96],"its":[97],"final":[98,111],"performance":[99,112],"remains":[100],"below":[101],"of":[103,121],"MTRL.":[104],"understand":[106],"latter,":[108],"decompose":[110],"show":[114],"forgetting":[116],"accounts":[117],"for":[118],"only":[119,179],"part":[120],"gap.":[123],"explain":[125],"former,":[127],"shared":[130,154],"reasoning:":[131],"transferable":[132],"structure":[134],"allows":[135],"training":[136],"one":[138],"to":[140,156],"support":[141],"others":[142],"average.":[144],"Prompt":[149],"Replay":[150],"(CPR),":[151],"harnesses":[153],"improve":[157],"arriving":[161],"future":[163],"by":[165],"replaying":[166],"previous-task":[167],"prompts":[168],"regenerating":[170],"their":[171],"responses":[172],"current":[175],"policy.":[176],"On":[177],"average,":[178],"CPR":[180],"reaches":[181],"MTRL-level":[182],"performance.":[183]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-08-22T00:00:00"}