{"id":"https://openalex.org/W7167221306","doi":"https://doi.org/10.48550/arxiv.2607.01366","title":"Auto-FL-Research: Agentic Search for Federated Learning Algorithms","display_name":"Auto-FL-Research: Agentic Search for Federated Learning Algorithms","publication_year":2026,"publication_date":"2026-07-01","ids":{"openalex":"https://openalex.org/W7167221306","doi":"https://doi.org/10.48550/arxiv.2607.01366"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.01366","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.01366","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":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.2607.01366","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140018599","display_name":"Holger R. Roth","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roth, Holger R.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073136550","display_name":"Zhewei Xu","orcid":"https://orcid.org/0000-0003-4718-6175"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Ziyue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006909076","display_name":"Chester Chen","orcid":"https://orcid.org/0009-0000-5835-6104"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Chester","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019421104","display_name":"D Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Daguang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043731444","display_name":"Peter Cnudde","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cnudde, Peter","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5083168221","display_name":"A. S. Feng","orcid":"https://orcid.org/0000-0002-6493-3702"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Andrew","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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.6758000254631042,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.6758000254631042,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.03660000115633011,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.029100000858306885,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7296000123023987},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.7276999950408936},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6060000061988831},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.45260000228881836},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.33239999413490295},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.2971999943256378}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7720000147819519},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7296000123023987},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.7276999950408936},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6060000061988831},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.45260000228881836},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42800000309944153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39100000262260437},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3190000057220459},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2883000075817108},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.2824000120162964},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28119999170303345},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2556999921798706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.01366","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.01366","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":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.2607.01366","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.01366","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":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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Federated":[0],"learning":[1],"(FL)":[2],"research":[3],"often":[4],"depends":[5],"on":[6,117,124,143],"many":[7],"small":[8],"but":[9],"consequential":[10],"algorithmic":[11,63],"choices:":[12],"optimizer":[13],"variants,":[14,86],"server":[15,75],"aggregation":[16,76],"rules,":[17,77],"local":[18,81],"training":[19,46,72],"schedules,":[20,80],"normalization,":[21],"regularization,":[22],"and":[23,33,69,83,98,111,123,147,157,210],"model":[24,85,100],"architecture.":[25],"These":[26,187],"choices":[27],"are":[28,174,190],"expensive":[29],"to":[30,35,168],"explore":[31],"manually":[32],"difficult":[34],"compare":[36],"fairly":[37],"when":[38],"candidate":[39,71,105],"changes":[40],"can":[41,200],"also":[42,154],"alter":[43],"the":[44,91,128,134,193],"FL":[45,62,205],"or":[47,180,184],"evaluation":[48],"path.":[49],"In":[50],"this":[51],"work,":[52],"we":[53],"present":[54],"Auto-FL-Research":[55],"(AFR),":[56],"a":[57],"constrained":[58],"coding-agent":[59],"workflow":[60],"for":[61,127],"recipe":[64],"search.":[65],"Agents":[66],"may":[67],"propose":[68],"implement":[70],"algorithms,":[73],"including":[74],"client":[78],"update":[79],"objectives,":[82],"registered":[84],"while":[87,153],"task":[88],"profiles":[89,126],"fix":[90],"mutation":[92],"surface,":[93],"compute":[94],"budget,":[95],"communication":[96],"contract,":[97],"final":[99],"evaluation.":[101,186],"Each":[102],"campaign":[103],"records":[104],"scores,":[106],"runtime,":[107],"edited":[108],"files,":[109],"artifacts,":[110],"failure":[112,159],"status.":[113],"We":[114],"evaluate":[115],"AFR":[116],"five":[118,129,148],"healthcare":[119],"cross-silo":[120],"FLamby":[121,145],"tasks":[122,146],"grouped-client":[125],"fixed":[130],"LEAF":[131,135,151],"datasets":[132],"plus":[133],"synthetic":[136],"task.":[137],"Five-seed":[138],"repeat":[139,183],"evaluations":[140],"support":[141],"gains":[142,166],"four":[144],"of":[149,192],"six":[150],"profiles,":[152],"exposing":[155],"seed-sensitive":[156],"search-selected":[158],"cases.":[160],"Same-budget":[161],"controls":[162,179],"show":[163,196],"that":[164],"several":[165],"correspond":[167],"FL-recipe":[169],"changes,":[170],"whereas":[171],"other":[172],"improvements":[173],"recovered":[175],"by":[176],"fixed-surface":[177,207],"scalar":[178],"fail":[181],"under":[182],"held-out":[185],"mixed":[188],"outcomes":[189],"part":[191],"contribution:":[194],"they":[195],"how":[197],"agent-generated":[198],"candidates":[199],"be":[201],"separated":[202],"into":[203],"repeated":[204],"mechanisms,":[206],"tuning":[208],"effects,":[209],"selected":[211],"single-run":[212],"artifacts.":[213]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-04T00:00:00"}