{"id":"https://openalex.org/W7214780466","doi":"https://doi.org/10.48550/arxiv.2609.33357","title":"DISCERN: Can AI Agents Work Like Scientists and Guide Discovery?","display_name":"DISCERN: Can AI Agents Work Like Scientists and Guide Discovery?","publication_year":2026,"publication_date":"2026-09-27","ids":{"openalex":"https://openalex.org/W7214780466","doi":"https://doi.org/10.48550/arxiv.2609.33357"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.33357","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.33357","pdf_url":"https://arxiv.org/pdf/2609.33357","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.33357","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140573450","display_name":"Nan Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huang, Nan","raw_affiliation_strings":["University of California San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133528522","display_name":"Mario Tapia-Pacheco","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tapia-Pacheco, Mario","raw_affiliation_strings":["University of California San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124915377","display_name":"Kun Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhou, Kun","raw_affiliation_strings":["University of California San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153492622","display_name":"Yiming Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huang, Yiming","raw_affiliation_strings":["University of California San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153462655","display_name":"Kevin Jos\u00e9 Barrientos D\u00edaz","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"D\u00edaz, Kevin Jos\u00e9 Barrientos","raw_affiliation_strings":["Independent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028223846","display_name":"Tiffany Amariuta","orcid":"https://orcid.org/0000-0003-0121-1726","observed_orcids":["https://orcid.org/0000-0003-0121-1726"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amariuta, Tiffany","raw_affiliation_strings":["University of California San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039500313","display_name":"Jingbo Shang","orcid":"https://orcid.org/0000-0002-7249-4404","observed_orcids":["https://orcid.org/0000-0002-7249-4404"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shang, Jingbo","raw_affiliation_strings":["University of California San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.4004000127315521,"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":0.4004000127315521,"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/T13904","display_name":"Artificial Intelligence Applications","score":0.1988999992609024,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.04820000007748604,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/ai-agents","display_name":"AI agents","score":0.6549999713897705},{"id":"https://openalex.org/keywords/hypothesis-generation","display_name":"hypothesis generation","score":0.7749999761581421},{"id":"https://openalex.org/keywords/hypothesis-revision","display_name":"hypothesis revision","score":0.7329999804496765},{"id":"https://openalex.org/keywords/data-integrity-verification","display_name":"data integrity verification","score":0.7229999899864197},{"id":"https://openalex.org/keywords/adversarial-review","display_name":"adversarial review","score":0.722000002861023},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"counterfactual reasoning","score":0.7760000228881836},{"id":"https://openalex.org/keywords/evidence-based-reasoning","display_name":"evidence-based reasoning","score":0.7049999833106995},{"id":"https://openalex.org/keywords/scientific-discovery","display_name":"scientific discovery","score":0.5690000057220459},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.47600001096725464}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.7271000146865845},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6607000231742859},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5759999752044678},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5407999753952026},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.49959999322891235},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4708999991416931},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.45080000162124634},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.4228000044822693},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4138000011444092},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.39590001106262207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3882000148296356},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.37929999828338623},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3772999942302704},{"id":"https://openalex.org/C2778058735","wikidata":"https://www.wikidata.org/wiki/Q4692253","display_name":"Aggregate data","level":2,"score":0.3634999990463257},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.36320000886917114},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.34769999980926514},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.33000001311302185},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.32190001010894775},{"id":"https://openalex.org/C7493553","wikidata":"https://www.wikidata.org/wiki/Q1520777","display_name":"Certainty","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3176000118255615},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31450000405311584},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C2779010991","wikidata":"https://www.wikidata.org/wiki/Q2720909","display_name":"Artifact (error)","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C124056412","wikidata":"https://www.wikidata.org/wiki/Q3320364","display_name":"Scientific evidence","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2551000118255615}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.33357","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.33357","pdf_url":"https://arxiv.org/pdf/2609.33357","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.33357","doi":"https://doi.org/10.48550/arxiv.2609.33357","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.33357","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,"listed_in":[],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.33357","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.33357","pdf_url":"https://arxiv.org/pdf/2609.33357","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214780466.pdf","grobid_xml":"https://content.openalex.org/works/W7214780466.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7211874068","https://openalex.org/W7213559368","https://openalex.org/W4415329539","https://openalex.org/W7101416451","https://openalex.org/W7164023999","https://openalex.org/W7164577541","https://openalex.org/W4403324055","https://openalex.org/W7127605006","https://openalex.org/W7203676309","https://openalex.org/W7220674086"],"abstract_inverted_index":{"Reliable":[0],"automated":[1,81],"research":[2,82],"requires":[3],"agents":[4,230],"to":[5,25,176,182],"vet":[6],"data,":[7,180],"verify":[8],"analyses,":[9],"and":[10,29,51,59,64,91,96,105,120,131,140,167,188,198,241],"generate":[11],"hypotheses":[12],"grounded":[13],"in":[14,113,157,191,213,217],"trustworthy":[15],"evidence,":[16],"potentially":[17],"reducing":[18],"routine":[19],"scientific":[20,122,226],"workload":[21],"while":[22,99],"allowing":[23],"scientists":[24],"focus":[26],"on":[27,69],"interpretation":[28],"discovery.":[30,239],"Existing":[31],"benchmarks":[32],"often":[33],"only":[34,158],"assess":[35],"analytical":[36],"task":[37],"completion":[38],"or":[39,238],"hypothesis":[40,103,192],"generation":[41,104],"separately":[42],"rather":[43],"than":[44,205,216],"testing":[45],"whether":[46],"reliable":[47,235],"evidence":[48,115,208],"supports":[49],"valid":[50],"novel":[52],"claims.":[53],"We":[54],"introduce":[55],"DISCERN":[56,143],"(Data":[57],"Integrity":[58],"Scientific":[60],"Capability:":[61],"Evidence,":[62],"Reasoning,":[63],"Novelty),":[65],"a":[66],"controlled":[67],"benchmark":[68],"real,":[70],"publicly":[71],"available":[72],"datasets":[73],"that":[74,145],"evaluates":[75],"three":[76],"key":[77],"levels":[78,87],"of":[79,160,164,169,178],"an":[80],"workflow.":[83],"The":[84],"first":[85],"two":[86],"test":[88],"data":[89,119],"integrity":[90],"analysis":[92,237],"verification":[93],"under":[94,107],"confounds":[95],"tool":[97],"traps,":[98],"the":[100],"third":[101],"tests":[102],"revision":[106],"adversarial":[108],"review,":[109],"including":[110],"counterfactual":[111],"cases":[112],"which":[114],"consistent":[116],"with":[117,125,173],"real":[118],"documented":[121],"phenomena":[123],"conflicts":[124],"established":[126],"expectations,":[127],"motivating":[128],"alternative":[129],"explanations":[130],"testable":[132],"hypotheses.":[133],"Across":[134],"203":[135],"tasks,":[136],"eight":[137,141],"life-science":[138],"tracks,":[139],"models,":[142],"shows":[144],"strong":[146],"aggregate":[147],"performance":[148],"can":[149],"mask":[150],"level-specific":[151],"weaknesses.":[152],"Agents":[153],"earn":[154],"perfect":[155],"scores":[156],"60.8%":[159],"Level":[161,165,170],"1,":[162],"34.2%":[163],"2,":[166],"0.6%":[168],"3":[171],"evaluations,":[172],"penalties":[174],"attributed":[175],"rejection":[177],"sound":[179],"failure":[181],"carry":[183],"recognized":[184],"limitations":[185],"into":[186],"conclusions,":[187],"wide":[189],"variation":[190],"production.":[193],"Cross-track":[194],"rankings":[195,206],"by":[196,207],"token":[197],"code":[199],"use":[200],"are":[201],"substantially":[202],"more":[203],"stable":[204],"judgment,":[209],"suggesting":[210],"greater":[211],"consistency":[212],"computational":[214],"effort":[215],"evidence-based":[218],"reasoning.":[219],"These":[220],"profiles":[221],"identify":[222],"opportunities":[223],"for":[224],"supervised":[225],"assistance,":[227],"but":[228],"current":[229],"do":[231],"not":[232],"yet":[233],"demonstrate":[234],"autonomous":[236],"Code":[240],"data:":[242],"https://huggingface.co/datasets/discern-bench-anon/discern-benchmark":[243]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-30T00:00:00"}