{"id":"https://openalex.org/W7167936726","doi":"https://doi.org/10.48550/arxiv.2607.07847","title":"When Does Continual Learning Require Learning","display_name":"When Does Continual Learning Require Learning","publication_year":2026,"publication_date":"2026-07-08","ids":{"openalex":"https://openalex.org/W7167936726","doi":"https://doi.org/10.48550/arxiv.2607.07847"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.07847","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.07847","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2607.07847","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120633019","display_name":"Anne Harrington","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Harrington, Anne","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140442769","display_name":"Nayan Saxena","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saxena, Nayan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140398271","display_name":"Michael Murphy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Murphy, Michael","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123948758","display_name":"Anastasia Borovykh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Borovykh, Anastasia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050829216","display_name":"Zeyu Yun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yun, Zeyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108612574","display_name":"Sridhar Kamath","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kamath, Sridhar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140409957","display_name":"Ara Eindra Kyi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kyi, Ara Eindra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140420686","display_name":"Trevor Darrell","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Darrell, Trevor","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140434775","display_name":"Jitendra Malik","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Malik, Jitendra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5140388188","display_name":"Yutong Bai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bai, Yutong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":0.8134999871253967,"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":0.8134999871253967,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.05640000104904175,"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":0.01119999960064888,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7592999935150146},{"id":"https://openalex.org/keywords/framing","display_name":"Framing (construction)","score":0.6017000079154968},{"id":"https://openalex.org/keywords/competence","display_name":"Competence (human resources)","score":0.4668999910354614},{"id":"https://openalex.org/keywords/proactive-learning","display_name":"Proactive learning","score":0.44620001316070557},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.34880000352859497},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.31279999017715454}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7592999935150146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7382000088691711},{"id":"https://openalex.org/C169087156","wikidata":"https://www.wikidata.org/wiki/Q2131593","display_name":"Framing (construction)","level":2,"score":0.6017000079154968},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5278000235557556},{"id":"https://openalex.org/C100521375","wikidata":"https://www.wikidata.org/wiki/Q2015382","display_name":"Competence (human resources)","level":2,"score":0.4668999910354614},{"id":"https://openalex.org/C12298181","wikidata":"https://www.wikidata.org/wiki/Q7246814","display_name":"Proactive learning","level":5,"score":0.44620001316070557},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.413100004196167},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.29919999837875366},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C60777511","wikidata":"https://www.wikidata.org/wiki/Q3045002","display_name":"Concept drift","level":3,"score":0.2667999863624573},{"id":"https://openalex.org/C5065155","wikidata":"https://www.wikidata.org/wiki/Q1185775","display_name":"Frame problem","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.07847","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.07847","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2607.07847","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.07847","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,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"large":[1],"language":[2],"models":[3,16],"(LLMs)":[4],"become":[5],"increasingly":[6],"capable,":[7],"the":[8,21,50,63,71,178,252],"next":[9],"question":[10],"is":[11,39,43,207],"how":[12],"can":[13,234],"we":[14,113],"enable":[15],"to":[17,167,180,190,196],"continually":[18],"learn?":[19],"Today,":[20],"field":[22],"largely":[23],"frames":[24],"this":[25,37,55,111],"as":[26,49,119],"a":[27,76,124,209],"problem":[28],"of":[29,214,254],"context":[30,143],"management":[31],"and":[32,68,100,122,142,231,248],"mitigating":[33],"forgetting.":[34],"We":[35,53,240],"argue":[36],"framing":[38,80],"incomplete:":[40],"continual":[41,84,205,256],"learning":[42,85,135,139,186,206,257],"fundamentally":[44,218],"about":[45],"increasing":[46],"model":[47,64,229],"competence":[48],"world":[51],"changes.":[52],"disentangle":[54],"change":[56,216],"along":[57],"two":[58],"axes":[59],"--":[60],"space,":[61],"where":[62,70,244],"encounters":[65],"new":[66,89,152,182],"domains,":[67],"time,":[69,93],"underlying":[72],"data":[73],"drifts":[74],"under":[75,86,110],"fixed":[77],"task.":[78],"This":[79],"lets":[81],"us":[82],"study":[83],"realistic":[87],"conditions:":[88],"domains":[90],"arrive":[91],"over":[92],"facts":[94],"drift":[95],"past":[96],"their":[97],"training":[98],"cutoff,":[99],"agentic":[101],"interactions":[102],"accumulate":[103,162],"state":[104],"across":[105],"episodes.":[106],"To":[107],"evaluate":[108],"methods":[109,131,149,161],"setting,":[112],"recast":[114],"widely":[115],"used":[116],"LLM":[117],"benchmarks":[118],"sequential":[120],"problems":[121],"introduce":[123],"single":[125,210],"mechanism-agnostic":[126],"protocol":[127],"that":[128,204,242],"compares":[129],"prompt-based":[130],"(GEPA,":[132],"ACE),":[133],"supervised":[134],"(SFT,":[136],"SDFT),":[137],"reinforcement":[138,185],"(GRPO,":[140],"SDPO),":[141],"compression":[144,172],"(Cartridges,":[145],"In-place":[146],"TTT).":[147],"Prompt-based":[148],"fit":[150],"each":[151,245],"stage":[153],"quickly":[154],"but":[155,165,193],"degrade":[156],"on":[157],"future":[158],"tasks.":[159,183],"Distillation-based":[160],"knowledge":[163,191],"stably":[164],"struggle":[166],"update":[168,220],"outdated":[169],"facts.":[170],"Context":[171],"improves":[173],"efficiency":[174],"without":[175],"substantially":[176],"improving":[177],"ability":[179],"learn":[181],"Online":[184],"adapts":[187],"most":[188],"effectively":[189],"updates":[192],"remains":[194],"sensitive":[195],"noisy":[197],"reward":[198],"signals.":[199],"Overall,":[200],"our":[201],"results":[202],"suggest":[203],"not":[208],"capability:":[211],"different":[212,219],"patterns":[213],"environmental":[215],"require":[217],"behaviors,":[221],"determining":[222],"when":[223,232],"adaptation":[224],"must":[225],"be":[226,235],"learned":[227],"inside":[228],"weights":[230],"it":[233],"achieved":[236],"through":[237],"external":[238],"scaffolding.":[239],"hope":[241],"understanding":[243],"method":[246],"succeeds":[247],"fails":[249],"will":[250],"guide":[251],"design":[253],"stronger":[255],"systems.":[258]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-11T00:00:00"}