{"id":"https://openalex.org/W4403324055","doi":"https://doi.org/10.48550/arxiv.2410.05080","title":"ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery","display_name":"ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery","publication_year":2024,"publication_date":"2024-10-07","ids":{"openalex":"https://openalex.org/W4403324055","doi":"https://doi.org/10.48550/arxiv.2410.05080"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2410.05080","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.05080","pdf_url":"https://arxiv.org/pdf/2410.05080","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.05080","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060070647","display_name":"Ziru Chen","orcid":"https://orcid.org/0000-0002-9507-6838"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chen, Ziru","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077257714","display_name":"Shijie Chen","orcid":"https://orcid.org/0009-0005-4172-0834"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Shijie","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006948276","display_name":"Yuting Ning","orcid":"https://orcid.org/0000-0001-5713-3531"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ning, Yuting","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052238652","display_name":"Qianheng Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Qianheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103541243","display_name":"Boshi Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Boshi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113429457","display_name":"Botao Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Botao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100355235","display_name":"Yifei Li","orcid":"https://orcid.org/0009-0009-0580-161X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yifei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113429458","display_name":"Zeyi Liao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liao, Zeyi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wei, Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000578418","display_name":"Zitong Lu","orcid":"https://orcid.org/0000-0002-7953-6742"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Zitong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103008061","display_name":"Vishal Dey","orcid":"https://orcid.org/0000-0002-7832-0915"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dey, Vishal","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004227348","display_name":"Mingyi Xue","orcid":"https://orcid.org/0000-0003-1083-0377"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xue, Mingyi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000935700","display_name":"Frazier N. Baker","orcid":"https://orcid.org/0000-0001-5972-1409"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baker, Frazier N.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062537175","display_name":"Benjamin Burns","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Burns, Benjamin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052537844","display_name":"Daniel Adu\u2010Ampratwum","orcid":"https://orcid.org/0000-0001-9392-2431"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adu-Ampratwum, Daniel","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101675744","display_name":"Xuhui Huang","orcid":"https://orcid.org/0000-0003-1477-9572"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Xuhui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ning, Xia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ning, Xia","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101938899","display_name":"Song Gao","orcid":"https://orcid.org/0000-0003-4359-6302"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Song","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075435632","display_name":"Yu Su","orcid":"https://orcid.org/0000-0003-4306-0161"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Su, Yu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5111362039","display_name":"Huan Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Huan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":20,"corresponding_author_ids":["https://openalex.org/A5060070647"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":6,"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/T10028","display_name":"Topic Modeling","score":0.9886000156402588,"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/T10028","display_name":"Topic Modeling","score":0.9886000156402588,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9722999930381775,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9657999873161316,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/scientific-discovery","display_name":"Scientific discovery","score":0.6143126487731934},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5286327600479126},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5243387818336487},{"id":"https://openalex.org/keywords/management-science","display_name":"Management science","score":0.3226756453514099},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.16441437602043152},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1258399486541748},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.11579480767250061}],"concepts":[{"id":"https://openalex.org/C2984917352","wikidata":"https://www.wikidata.org/wiki/Q12772819","display_name":"Scientific discovery","level":2,"score":0.6143126487731934},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5286327600479126},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5243387818336487},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.3226756453514099},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.16441437602043152},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1258399486541748},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.11579480767250061}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2410.05080","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.05080","pdf_url":"https://arxiv.org/pdf/2410.05080","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-157729","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-157729","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"},{"id":"doi:10.48550/arxiv.2410.05080","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.05080","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":"pmh:oai:arXiv.org:2410.05080","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.05080","pdf_url":"https://arxiv.org/pdf/2410.05080","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1736414626","display_name":null,"funder_award_id":"2112606","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4403324055.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2126681669","https://openalex.org/W2148010638","https://openalex.org/W2413102523"],"abstract_inverted_index":{"The":[0],"advancements":[1],"of":[2,40,81,122,140,200,230,242,251],"large":[3],"language":[4,14,67,253],"models":[5],"(LLMs)":[6],"have":[7],"piqued":[8],"growing":[9],"interest":[10],"in":[11,45,92,255],"developing":[12],"LLM-based":[13],"agents":[15,41,68,254],"to":[16,101,112,125,149,163,225],"automate":[17],"scientific":[18,47,71,76,155,266],"discovery":[19],"end-to-end,":[20],"which":[21,220],"has":[22],"sparked":[23],"both":[24],"excitement":[25],"and":[26,78,95,118,132,145,154,174,185,204,218],"skepticism":[27],"about":[28],"their":[29],"true":[30],"capabilities.":[31],"In":[32,209],"this":[33,57],"work,":[34],"we":[35,59,84,170,211],"call":[36],"for":[37,65,69,109,190,258,265],"rigorous":[38],"assessment":[39],"on":[42,53],"individual":[43],"tasks":[44,87,202],"a":[46,62,113],"workflow":[48],"before":[49],"making":[50],"bold":[51],"claims":[52],"end-to-end":[54,263],"automation.":[55],"To":[56,73],"end,":[58],"present":[60],"ScienceAgentBench,":[61,169],"new":[63],"benchmark":[64],"evaluating":[66],"data-driven":[70,259],"discovery.":[72],"ensure":[74,150],"the":[75,106,127,193,201,223,228,240,249],"authenticity":[77],"real-world":[79],"relevance":[80],"our":[82,246],"benchmark,":[83],"extract":[85],"102":[86],"from":[88],"44":[89],"peer-reviewed":[90],"publications":[91],"four":[93],"disciplines":[94],"engage":[96],"nine":[97],"subject":[98,146],"matter":[99,147],"experts":[100,148],"validate":[102],"them.":[103],"We":[104,157],"unify":[105],"target":[107],"output":[108],"every":[110],"task":[111,135],"self-contained":[114],"Python":[115],"program":[116],"file":[117],"employ":[119],"an":[120],"array":[121],"evaluation":[123],"metrics":[124],"examine":[126],"generated":[128],"programs,":[129],"execution":[130],"results,":[131],"costs.":[133],"Each":[134],"goes":[136],"through":[137],"multiple":[138],"rounds":[139],"manual":[141],"validation":[142],"by":[143],"annotators":[144],"its":[151],"annotation":[152],"quality":[153],"plausibility.":[156],"also":[158],"propose":[159],"two":[160],"effective":[161],"strategies":[162],"mitigate":[164],"data":[165],"contamination":[166],"concerns.":[167],"Using":[168],"evaluate":[171,212],"five":[172],"open-weight":[173],"proprietary":[175],"LLMs,":[176],"each":[177,191],"with":[178,206,215,235],"three":[179,188],"frameworks:":[180],"direct":[181,216],"prompting,":[182],"OpenHands":[183],"CodeAct,":[184],"self-debug.":[186],"Given":[187],"attempts":[189],"task,":[192],"best-performing":[194],"agent":[195],"can":[196,221],"only":[197],"solve":[198],"32.4%":[199],"independently":[203],"34.3%":[205],"expert-provided":[207],"knowledge.":[208],"addition,":[210],"OpenAI":[213],"o1-preview":[214],"prompting":[217],"self-debug,":[219],"boost":[222],"performance":[224],"42.2%,":[226],"demonstrating":[227],"effectiveness":[229],"increasing":[231],"inference-time":[232],"compute":[233],"but":[234],"more":[236],"than":[237],"10":[238],"times":[239],"cost":[241],"other":[243],"LLMs.":[244],"Still,":[245],"results":[247],"underscore":[248],"limitations":[250],"current":[252],"generating":[256],"code":[257],"discovery,":[260],"let":[261],"alone":[262],"automation":[264],"research.":[267]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}