{"id":"https://openalex.org/W7154093125","doi":"https://doi.org/10.48550/arxiv.2604.08590","title":"AlphaLab: Autonomous Multi-Agent Research Across Optimization Domains with Frontier LLMs","display_name":"AlphaLab: Autonomous Multi-Agent Research Across Optimization Domains with Frontier LLMs","publication_year":2026,"publication_date":"2026-03-31","ids":{"openalex":"https://openalex.org/W7154093125","doi":"https://doi.org/10.48550/arxiv.2604.08590"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.08590","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.08590","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.2604.08590","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133501946","display_name":"Brendan R. Hogan","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hogan, Brendan R.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133488674","display_name":"Xiwen Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Xiwen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129886404","display_name":"James Wilson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wilson, James T.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133514003","display_name":"Kashif Rasul","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rasul, Kashif","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133512071","display_name":"Adel Boyarsky","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boyarsky, Adel","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133480432","display_name":"Thomas Kamei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kamei, Thomas","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018463862","display_name":"Anderson Schneider","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Schneider, Anderson","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133484171","display_name":"Yuriy Nevmyvaka","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nevmyvaka, Yuriy","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5133501946"],"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/T11986","display_name":"Scientific Computing and Data Management","score":0.13989999890327454,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.13989999890327454,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.09390000253915787,"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":0.08079999685287476,"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/pipeline","display_name":"Pipeline (software)","score":0.7300999760627747},{"id":"https://openalex.org/keywords/frontier","display_name":"Frontier","score":0.6837999820709229},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6241000294685364},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5982000231742859},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5852000117301941},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5494999885559082},{"id":"https://openalex.org/keywords/series","display_name":"Series (stratigraphy)","score":0.376800000667572},{"id":"https://openalex.org/keywords/time-series","display_name":"Time series","score":0.3456999957561493}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7300999760627747},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6949999928474426},{"id":"https://openalex.org/C2778571376","wikidata":"https://www.wikidata.org/wiki/Q1355821","display_name":"Frontier","level":2,"score":0.6837999820709229},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6241000294685364},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5982000231742859},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5852000117301941},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5494999885559082},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.376800000667572},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3294999897480011},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29809999465942383},{"id":"https://openalex.org/C92548554","wikidata":"https://www.wikidata.org/wiki/Q2262868","display_name":"Domain model","level":3,"score":0.2955000102519989},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.28790000081062317},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.2827000021934509},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27799999713897705},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2750000059604645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2678999900817871},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.26589998602867126},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26440000534057617},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C3017489831","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Running time","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C51485801","wikidata":"https://www.wikidata.org/wiki/Q16966861","display_name":"Efficient frontier","level":3,"score":0.25780001282691956}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.08590","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.08590","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.2604.08590","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.08590","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,116,210],"present":[1],"AlphaLab,":[2],"an":[3],"autonomous":[4],"research":[5,55],"harness":[6],"that":[7,85,139,203],"leverages":[8],"frontier":[9,121],"LLM":[10,150],"agentic":[11],"capabilities":[12],"to":[13,42,148],"automate":[14],"the":[15,43,47,103,107,153,166,187,220],"full":[16,154],"experimental":[17],"cycle":[18],"in":[19,81,196,219],"quantitative,":[20],"computation-intensive":[21],"domains.":[22],"Given":[23],"only":[24],"a":[25,28,54,75,82,88,162],"dataset":[26],"and":[27,45,52,60,67,124,169,181,222],"natural-language":[29],"objective,":[30],"AlphaLab":[31,118],"proceeds":[32],"through":[33],"three":[34,129],"phases":[35],"without":[36,114],"human":[37],"intervention:":[38],"(1)":[39],"it":[40,58,69,135,173],"adapts":[41],"domain":[44,79,198],"explores":[46],"data,":[48],"writing":[49],"analysis":[50],"code":[51,225],"producing":[53],"report;":[56],"(2)":[57],"constructs":[59],"adversarially":[61],"validates":[62],"its":[63],"own":[64],"evaluation":[65],"framework;":[66],"(3)":[68],"runs":[70],"large-scale":[71],"GPU":[72,137],"experiments":[73],"via":[74],"Strategist/Worker":[76],"loop,":[77],"accumulating":[78],"knowledge":[80],"persistent":[83],"playbook":[84],"functions":[86],"as":[87],"form":[89],"of":[90],"online":[91],"prompt":[92],"optimization.":[93],"All":[94],"domain-specific":[95],"behavior":[96],"is":[97],"factored":[98],"into":[99],"adapters":[100],"generated":[101],"by":[102,177],"model":[104,184],"itself,":[105],"so":[106],"same":[108,167],"pipeline":[109],"handles":[110],"qualitatively":[111,193],"different":[112,194],"tasks":[113],"modification.":[115],"evaluate":[117],"with":[119],"two":[120,190],"LLMs":[122],"(GPT-5.2":[123],"Claude":[125],"Opus":[126],"4.6)":[127],"on":[128,145,214],"domains:":[130],"CUDA":[131],"kernel":[132],"optimization,":[133],"where":[134,152,172],"writes":[136],"kernels":[138],"run":[140],"4.4x":[141],"faster":[142],"than":[143,161],"torch.compile":[144],"average":[146],"(up":[147],"91x);":[149],"pretraining,":[151],"system":[155],"achieves":[156],"22%":[157],"lower":[158],"validation":[159],"loss":[160],"single-shot":[163],"baseline":[164],"using":[165],"model;":[168],"traffic":[170],"forecasting,":[171],"beats":[174],"standard":[175],"baselines":[176],"23-25%":[178],"after":[179],"researching":[180],"implementing":[182],"published":[183],"families":[185],"from":[186],"literature.":[188],"The":[189],"models":[191],"discover":[192],"solutions":[195],"every":[197],"(neither":[199],"dominates":[200],"uniformly),":[201],"suggesting":[202],"multi-model":[204],"campaigns":[205],"provide":[206],"complementary":[207],"search":[208],"coverage.":[209],"additionally":[211],"report":[212],"results":[213],"financial":[215],"time":[216],"series":[217],"forecasting":[218],"appendix,":[221],"release":[223],"all":[224],"at":[226],"https://brendanhogan.github.io/alphalab-paper/.":[227]},"counts_by_year":[],"updated_date":"2026-04-14T06:08:25.285971","created_date":"2026-04-14T00:00:00"}