{"id":"https://openalex.org/W7154257435","doi":"https://doi.org/10.48550/arxiv.2604.09621","title":"Competing with AI Scientists: Agent-Driven Approach to Astrophysics Research","display_name":"Competing with AI Scientists: Agent-Driven Approach to Astrophysics Research","publication_year":2026,"publication_date":"2026-03-18","ids":{"openalex":"https://openalex.org/W7154257435","doi":"https://doi.org/10.48550/arxiv.2604.09621"},"language":"en","primary_location":{"id":"pmh:oai:HAL:hal-05608160v1","is_oa":false,"landing_page_url":"https://hal.science/hal-05608160","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2026","raw_type":"Preprints, Working Papers, ..."},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.09621","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133618499","display_name":"Thomas Borrett","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Borrett, Thomas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101489913","display_name":"Liang Xu","orcid":"https://orcid.org/0000-0002-8865-7175"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Licong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130568753","display_name":"Andy Nilipour","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nilipour, Andy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005211028","display_name":"Boris Bolliet","orcid":"https://orcid.org/0000-0003-4922-7401"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bolliet, Boris","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130569565","display_name":"Sebastien Pierre","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pierre, Sebastien","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002979974","display_name":"Erwan Allys","orcid":"https://orcid.org/0000-0003-3755-7593"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Allys, Erwan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130559694","display_name":"Celia Lecat","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lecat, Celia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127788194","display_name":"Biwei Dai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai, Biwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101407669","display_name":"Po-Wen Chang","orcid":"https://orcid.org/0000-0003-1134-0652"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chang, Po-Wen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133571188","display_name":"Wahid Bhimji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bhimji, Wahid","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5133618499"],"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":0.1736000031232834,"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":0.1736000031232834,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.04690000042319298,"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/T11937","display_name":"Research Data Management Practices","score":0.03530000150203705,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/workflow","display_name":"Workflow","score":0.6881999969482422},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6557000279426575},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5231999754905701},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.47209998965263367},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.41339999437332153},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.4036000072956085},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.36980000138282776},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.35249999165534973}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6881999969482422},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6787999868392944},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6557000279426575},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5231999754905701},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4837000072002411},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.47209998965263367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.460999995470047},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.41339999437332153},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.4036000072956085},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.36980000138282776},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.35249999165534973},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.3393999934196472},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.32829999923706055},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32350000739097595},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.30809998512268066},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C129916263","wikidata":"https://www.wikidata.org/wiki/Q1141183","display_name":"Backward chaining","level":4,"score":0.27970001101493835},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.26499998569488525},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.25679999589920044}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:HAL:hal-05608160v1","is_oa":false,"landing_page_url":"https://hal.science/hal-05608160","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2026","raw_type":"Preprints, Working Papers, ..."},{"id":"doi:10.48550/arxiv.2604.09621","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.09621","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.09621","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.09621","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":"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":[0,127],"present":[1],"an":[2],"agent-driven":[3,101,166],"approach":[4,59],"to":[5,36,60,103,174],"the":[6,27,49,61,84,94,109,135],"construction":[7],"of":[8,26,96],"parameter":[9,77,156],"inference":[10,78,144,181],"pipelines":[11,179],"for":[12,180],"scientific":[13],"data":[14],"analysis.":[15],"Our":[16,142,162],"method":[17],"leverages":[18],"a":[19,53,68,105,154,171],"multi-agent":[20],"system,":[21],"Cmbagent":[22],"(the":[23],"analysis":[24],"system":[25],"AI":[28],"scientist":[29],"Denario),":[30],"in":[31,108,121,131],"which":[32],"specialized":[33],"agents":[34],"collaborate":[35],"generate":[37],"research":[38,167],"ideas,":[39],"write":[40],"and":[41,46,120,137,158,177],"execute":[42],"code,":[43],"evaluate":[44],"results,":[45],"iteratively":[47],"refine":[48],"overall":[50],"pipeline.":[51],"As":[52],"case":[54],"study,":[55],"we":[56],"apply":[57],"this":[58],"FAIR":[62],"Universe":[63],"Weak":[64],"Lensing":[65],"Uncertainty":[66],"Challenge,":[67],"competition":[69],"under":[70],"time":[71],"constraints":[72],"focused":[73],"on":[74],"robust":[75],"cosmological":[76],"with":[79],"realistic":[80],"observational":[81],"uncertainties.":[82],"While":[83],"fully":[85],"autonomous":[86,136],"exploration":[87,139],"initially":[88],"did":[89],"not":[90],"reach":[91],"expert-level":[92],"performance,":[93],"integration":[95],"human":[97],"intervention":[98],"enabled":[99],"our":[100,129],"workflow":[102,130],"achieve":[104],"first-place":[106],"result":[107],"challenge.":[110],"This":[111],"demonstrates":[112],"that":[113,165],"semi-autonomous":[114,138],"agentic":[115],"systems":[116],"can":[117,169],"compete":[118],"with,":[119],"some":[122],"cases":[123],"surpass,":[124],"expert":[125],"solutions.":[126],"describe":[128],"detail,":[132],"including":[133],"both":[134],"by":[140],"Cmbagent.":[141],"final":[143],"pipeline":[145],"utilizes":[146],"parameter-efficient":[147],"convolutional":[148],"neural":[149],"networks,":[150],"likelihood":[151],"calibration":[152],"over":[153],"known":[155],"grid,":[157],"multiple":[159],"regularization":[160],"techniques.":[161],"results":[163],"suggest":[164],"workflows":[168],"provide":[170],"scalable":[172],"framework":[173],"rapidly":[175],"explore":[176],"construct":[178],"problems.":[182]},"counts_by_year":[],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2026-04-15T00:00:00"}