{"id":"https://openalex.org/W7163647702","doi":"https://doi.org/10.48550/arxiv.2606.06473","title":"MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery","display_name":"MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery","publication_year":2026,"publication_date":"2026-06-04","ids":{"openalex":"https://openalex.org/W7163647702","doi":"https://doi.org/10.48550/arxiv.2606.06473"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.06473","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.06473","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":null,"license_id":null,"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.2606.06473","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022828160","display_name":"Shangheng Du","orcid":"https://orcid.org/0000-0002-5792-631X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Shangheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008886708","display_name":"Xiangchao Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Xiangchao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137954953","display_name":"Jinxin Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Jinxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137939471","display_name":"Zongsheng Cao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Zongsheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102836152","display_name":"Shiyang Feng","orcid":"https://orcid.org/0009-0001-6675-2948"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Shiyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101340514","display_name":"Zichen Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Zichen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138008955","display_name":"Boyuan Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Boyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137977831","display_name":"Tianshuo Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, Tianshuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137962435","display_name":"Yifan Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Yifan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137934435","display_name":"Xin Li (51274)","orcid":"https://orcid.org/0009-0004-2065-9598"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137945908","display_name":"Jie Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Jie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137981095","display_name":"Liang He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Liang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137928704","display_name":"Bo Zhang","orcid":"https://orcid.org/0000-0001-5860-6206"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Bo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137969766","display_name":"Lei Bai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bai, Lei","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/T11948","display_name":"Machine Learning in Materials Science","score":0.15629999339580536,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.15629999339580536,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.12950000166893005,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.10010000318288803,"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/key","display_name":"Key (lock)","score":0.5069000124931335},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4404999911785126},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.44020000100135803},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.38609999418258667},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.36739999055862427},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.3425000011920929}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8100000023841858},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6370000243186951},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6161999702453613},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5069000124931335},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4404999911785126},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.44020000100135803},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.38609999418258667},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37549999356269836},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.36739999055862427},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.3425000011920929},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C207024777","wikidata":"https://www.wikidata.org/wiki/Q621673","display_name":"Search tree","level":3,"score":0.2904999852180481},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2818000018596649},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.2583000063896179}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.06473","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.06473","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.06473","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.06473","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":null,"license_id":null,"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":{"Large":[0],"language":[1],"model":[2],"(LLM)":[3],"agents":[4,30],"are":[5],"increasingly":[6],"applied":[7],"to":[8,66,86,98],"long-horizon":[9,46,127],"tasks":[10],"such":[11],"as":[12],"scientific":[13],"discovery":[14,175],"and":[15,38,78,123,157],"machine":[16,58],"learning":[17,59],"engineering":[18],"(MLE),":[19],"where":[20],"sustained":[21],"self-evolution":[22],"becomes":[23],"a":[24,109,115,162],"key":[25],"capability.":[26],"However,":[27],"existing":[28],"MLE":[29],"suffer":[31],"from":[32,83,134],"inter-branch":[33],"information":[34,72],"isolation,":[35],"memoryless":[36],"search,":[37],"lack":[39],"of":[40],"hierarchical":[41],"control,":[42],"which":[43,107],"together":[44],"hinder":[45],"optimization.":[47],"We":[48],"present":[49],"MLEvolve,":[50],"an":[51,90],"LLM-based":[52],"self-evolving":[53],"multi-agent":[54],"framework":[55],"for":[56,119],"end-to-end":[57],"algorithm":[60,174,181],"discovery.":[61],"By":[62],"extending":[63],"tree":[64],"search":[65,82],"Progressive":[67],"MCGS,":[68],"MLEvolve":[69,146,170],"enables":[70],"cross-branch":[71],"flow":[73],"through":[74],"graph-based":[75],"reference":[76],"edges":[77],"gradually":[79],"shifts":[80],"the":[81,96,166],"broad":[84],"exploration":[85],"focused":[87],"exploitation":[88],"with":[89,100,114,137],"entropy-inspired":[91],"progressive":[92],"schedule.":[93],"To":[94],"allow":[95],"agent":[97],"evolve":[99],"accumulated":[101],"experience,":[102],"we":[103,129],"introduce":[104],"Retrospective":[105],"Memory,":[106],"combines":[108],"cold-start":[110],"domain":[111],"knowledge":[112],"base":[113],"dynamic":[116],"global":[117],"memory":[118],"task-specific":[120],"experience":[121],"retrieval":[122],"reuse.":[124],"For":[125],"stable":[126],"iteration,":[128],"further":[130],"decouple":[131],"strategic":[132],"planning":[133],"code":[135,189],"generation":[136],"adaptive":[138],"coding":[139],"modes.":[140],"Evaluation":[141],"on":[142,179],"MLE-Bench":[143],"shows":[144],"that":[145],"achieves":[147],"state-of-the-art":[148],"performance":[149],"across":[150],"multiple":[151],"dimensions":[152],"including":[153,177],"average":[154],"medal":[155],"rate":[156,160],"valid":[158],"submission":[159],"under":[161],"12-hour":[163],"budget":[164],"(half":[165],"standard":[167],"runtime).":[168],"Moreover,":[169],"also":[171],"outperforms":[172],"specialized":[173],"methods":[176],"AlphaEvolve":[178],"mathematical":[180],"optimization":[182],"tasks,":[183],"demonstrating":[184],"strong":[185],"cross-domain":[186],"generalization.":[187],"Our":[188],"is":[190],"available":[191],"at":[192],"https://github.com/InternScience/MLEvolve.":[193]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-06T00:00:00"}