{"id":"https://openalex.org/W7162657022","doi":"https://doi.org/10.48550/arxiv.2605.28742","title":"CORE: Contrastive Reflection Enables Rapid Improvements in Reasoning","display_name":"CORE: Contrastive Reflection Enables Rapid Improvements in Reasoning","publication_year":2026,"publication_date":"2026-05-27","ids":{"openalex":"https://openalex.org/W7162657022","doi":"https://doi.org/10.48550/arxiv.2605.28742"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.28742","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.28742","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.28742","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069707664","display_name":"Linas Nasvytis","orcid":"https://orcid.org/0009-0009-3910-2171"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nasvytis, Linas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137247377","display_name":"Simon Jerome Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Simon Jerome","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137228162","display_name":"Ben Prystawski","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prystawski, Ben","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137297168","display_name":"Satchel Grant","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Grant, Satchel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137241224","display_name":"Noah D. Goodman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Goodman, Noah D.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136176527","display_name":"Judith E. Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Judith E.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.39809998869895935,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.39809998869895935,"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":0.25110000371932983,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.07760000228881836,"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/reuse","display_name":"Reuse","score":0.6715999841690063},{"id":"https://openalex.org/keywords/reflection","display_name":"Reflection (computer programming)","score":0.6389999985694885},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5536999702453613},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.5205000042915344},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.4975999891757965},{"id":"https://openalex.org/keywords/case-based-reasoning","display_name":"Case-based reasoning","score":0.4950999915599823},{"id":"https://openalex.org/keywords/verifiable-secret-sharing","display_name":"Verifiable secret sharing","score":0.4577000141143799},{"id":"https://openalex.org/keywords/reasoning-system","display_name":"Reasoning system","score":0.397599995136261}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7085999846458435},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.6715999841690063},{"id":"https://openalex.org/C65682993","wikidata":"https://www.wikidata.org/wiki/Q1056451","display_name":"Reflection (computer programming)","level":2,"score":0.6389999985694885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5716000199317932},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5536999702453613},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.5205000042915344},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4975999891757965},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.4950999915599823},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.4577000141143799},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4212000072002411},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.397599995136261},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.37630000710487366},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.3531000018119812},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.34599998593330383},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34200000762939453},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.2883000075817108},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2628999948501587}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.28742","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.28742","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.28742","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.28742","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Language":[0],"models":[1],"can":[2,181],"use":[3],"verifiable":[4],"rewards":[5],"to":[6,26,70,189],"improve":[7],"at":[8],"a":[9,61,183],"wide":[10],"variety":[11],"of":[12,32,37,76,200],"reasoning":[13,68,77,92,174,202],"tasks.":[14],"However,":[15],"both":[16,103],"parametric":[17,104],"(e.g.":[18,22],"RLVR)":[19],"and":[20,35,47,79,86,106,111,172,178,186],"non-parametric":[21,62,107,148],"prompt":[23,152,195],"optimization)":[24],"approaches":[25],"doing":[27],"so":[28],"typically":[29],"require":[30],"hundreds":[31],"training":[33,127],"samples":[34],"thousands":[36],"model":[38,190],"rollouts,":[39],"making":[40],"them":[41],"expensive":[42],"in":[43,49,134],"the":[44,50,131],"best":[45],"case":[46],"intractable":[48],"worst.":[51],"To":[52],"address":[53],"this":[54],"challenge,":[55],"we":[56,94,139],"introduce":[57],"Contrastive":[58],"Reflection":[59],"(CORE),":[60],"learning":[63],"algorithm":[64],"that":[65,81,96,167],"compares":[66],"past":[67],"traces":[69,175],"generate":[71],"insights:":[72],"short":[73],"natural-language":[74,161],"descriptions":[75],"strategies":[78],"constraints":[80],"capture":[82],"differences":[83],"between":[84,170],"successful":[85,171],"unsuccessful":[87,173],"problem":[88],"attempts.":[89],"Across":[90],"four":[91],"tasks,":[93],"demonstrate":[95],"CORE":[97,129,142],"enables":[98],"more":[99,145,184],"rapid":[100],"improvement":[101],"than":[102,147,192],"(GRPO)":[105],"(GEPA,":[108],"episodic":[109],"RAG,":[110],"MemRL)":[112],"methods,":[113],"while":[114,154],"using":[115],"fewer":[116,151],"rollouts.":[117],"Under":[118],"fixed":[119],"rollout":[120],"budgets":[121],"with":[122],"as":[123,125,158],"few":[124],"five":[126],"samples,":[128],"achieves":[130],"strongest":[132],"performance":[133],"most":[135],"task-data":[136],"regimes.":[137],"Finally,":[138],"highlight":[140],"how":[141],"is":[143],"substantially":[144],"context-efficient":[146],"baselines,":[149],"requiring":[150],"tokens":[153],"storing":[155],"learned":[156],"knowledge":[157],"compact,":[159],"interpretable":[160,187],"insights.":[162],"Our":[163],"results":[164],"therefore":[165],"suggest":[166],"distilling":[168],"contrasts":[169],"into":[176],"abstract":[177],"useful":[179],"insights":[180],"provide":[182],"efficient":[185],"route":[188],"self-improvement":[191],"weight":[193],"updates,":[194],"optimization,":[196],"or":[197],"direct":[198],"reuse":[199],"stored":[201],"traces.":[203]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-29T00:00:00"}