{"id":"https://openalex.org/W7160140912","doi":"https://doi.org/10.48550/arxiv.2605.00803","title":"Can Coding Agents Reproduce Findings in Computational Materials Science?","display_name":"Can Coding Agents Reproduce Findings in Computational Materials Science?","publication_year":2026,"publication_date":"2026-05-01","ids":{"openalex":"https://openalex.org/W7160140912","doi":"https://doi.org/10.48550/arxiv.2605.00803"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2605.00803","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.00803","pdf_url":"https://arxiv.org/pdf/2605.00803","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2605.00803","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057988006","display_name":"Ziyang Huang","orcid":"https://orcid.org/0000-0001-6422-225X","observed_orcids":["https://orcid.org/0000-0001-6422-225X","https://orcid.org/0000-0002-5890-1130"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huang, Ziyang","raw_affiliation_strings":["Johns Hopkins University {zhuang86 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University {zhuang86 ,","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135145155","display_name":"Yi Cao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cao, Yi","raw_affiliation_strings":["Johns Hopkins University {zhuang86 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University {zhuang86 ,","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019562569","display_name":"Ali K. Shargh","orcid":"https://orcid.org/0000-0002-5588-8938","observed_orcids":["https://orcid.org/0000-0002-5588-8938"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shargh, Ali K.","raw_affiliation_strings":["Johns Hopkins University {zhuang86 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University {zhuang86 ,","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135140605","display_name":"Jing Luo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luo, Jing","raw_affiliation_strings":["Johns Hopkins University {zhuang86 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University {zhuang86 ,","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038570187","display_name":"Ruidong Mei","orcid":"https://orcid.org/0000-0002-0434-8659","observed_orcids":["https://orcid.org/0000-0002-0434-8659"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mei, Ruidong","raw_affiliation_strings":["Johns Hopkins University {zhuang86 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University {zhuang86 ,","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135121461","display_name":"Mohd Zaki","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zaki, Mohd","raw_affiliation_strings":["Johns Hopkins University {zhuang86 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University {zhuang86 ,","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112113368","display_name":"Zhan Liu","orcid":"https://orcid.org/0000-0002-4351-1295","observed_orcids":["https://orcid.org/0000-0002-4351-1295"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liu, Zhan","raw_affiliation_strings":["Johns Hopkins University {zhuang86 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University {zhuang86 ,","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094275073","display_name":"Wyatt Bunstine","orcid":"https://orcid.org/0009-0001-4631-7535","observed_orcids":["https://orcid.org/0009-0001-4631-7535"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bunstine, Wyatt","raw_affiliation_strings":["Johns Hopkins University {zhuang86 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University {zhuang86 ,","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077832672","display_name":"William Jurayj","orcid":"https://orcid.org/0009-0001-9278-6068","observed_orcids":["https://orcid.org/0009-0001-9278-6068"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jurayj, William","raw_affiliation_strings":["Johns Hopkins University {zhuang86 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University {zhuang86 ,","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135381091","display_name":"Somdatta Goswami","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Goswami, Somdatta","raw_affiliation_strings":["Johns Hopkins University {zhuang86 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University {zhuang86 ,","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040550673","display_name":"Tyrel M. McQueen","orcid":"https://orcid.org/0000-0002-8493-4630","observed_orcids":["https://orcid.org/0000-0002-8493-4630"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"McQueen, Tyrel","raw_affiliation_strings":["Johns Hopkins University {zhuang86 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University {zhuang86 ,","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137967700","display_name":"Michael Shields","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shields, Michael","raw_affiliation_strings":["Johns Hopkins University {zhuang86 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University {zhuang86 ,","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025017424","display_name":"Jaafar A. El\u2010Awady","orcid":"https://orcid.org/0000-0002-5715-2481","observed_orcids":["https://orcid.org/0000-0002-5715-2481"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"El-Awady, Jaafar","raw_affiliation_strings":["Johns Hopkins University {zhuang86 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University {zhuang86 ,","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030863265","display_name":"Paulette Clancy","orcid":"https://orcid.org/0000-0002-0468-6420","observed_orcids":["https://orcid.org/0000-0002-0468-6420"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Clancy, Paulette","raw_affiliation_strings":["Johns Hopkins University {zhuang86 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University {zhuang86 ,","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135281734","display_name":"Benjamin Van Durme","orcid":"https://orcid.org/0000-0003-4328-4288","observed_orcids":["https://orcid.org/0000-0003-4328-4288"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Van Durme, Benjamin","raw_affiliation_strings":["Johns Hopkins University {zhuang86 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University {zhuang86 ,","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110927976","display_name":"Nicholas Andrews","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrews, Nicholas","raw_affiliation_strings":["Johns Hopkins University {zhuang86 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University {zhuang86 ,","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5097607379","display_name":"William Gantt Walden","orcid":"https://orcid.org/0000-0001-9931-2861","observed_orcids":["https://orcid.org/0000-0001-9931-2861"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Walden, William","raw_affiliation_strings":["Johns Hopkins University {zhuang86 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University {zhuang86 ,","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043628255","display_name":"Daniel Khashabi","orcid":"https://orcid.org/0009-0009-7664-2230","observed_orcids":["https://orcid.org/0009-0009-7664-2230"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Khashabi, Daniel","raw_affiliation_strings":["Johns Hopkins University {zhuang86 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University {zhuang86 ,","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":16,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.48170000314712524,"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"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.48170000314712524,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.4171999990940094,"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/T10260","display_name":"Software Engineering Research","score":0.06589999794960022,"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/large-language-models","display_name":"large language models","score":0.7879999876022339},{"id":"https://openalex.org/keywords/ai-coding-agents","display_name":"coding agents","score":0.9129999876022339},{"id":"https://openalex.org/keywords/computational-materials-science","display_name":"computational materials science","score":0.625},{"id":"https://openalex.org/keywords/scientific-reproducibility","display_name":"scientific reproducibility","score":0.8489999771118164},{"id":"https://openalex.org/keywords/artificial-intelligence-in-science","display_name":"artificial intelligence in science","score":0.5529999732971191},{"id":"https://openalex.org/keywords/scientific-claims","display_name":"scientific claims","score":0.375},{"id":"https://openalex.org/keywords/computational-workflows","display_name":"computational workflows","score":0.46799999475479126},{"id":"https://openalex.org/keywords/agentic-systems","display_name":"agentic systems","score":0.44699999690055847},{"id":"https://openalex.org/keywords/error-analysis","display_name":"error analysis","score":0.527999997138977}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7666000127792358},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7419000267982483},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.6507999897003174},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.5658000111579895},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5472000241279602},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.46309998631477356},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4544000029563904},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4032999873161316},{"id":"https://openalex.org/C78780964","wikidata":"https://www.wikidata.org/wiki/Q7233193","display_name":"Position paper","level":2,"score":0.4016000032424927},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3977000117301941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.396699994802475},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.36820000410079956},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3635999858379364},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26589998602867126}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2605.00803","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.00803","pdf_url":"https://arxiv.org/pdf/2605.00803","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.2605.00803","doi":"https://doi.org/10.48550/arxiv.2605.00803","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.00803","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2605.00803","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.00803","pdf_url":"https://arxiv.org/pdf/2605.00803","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":[{"id":"https://openalex.org/G5945091033","display_name":"MRI: Acquisition of an Advanced Computing Instrument to Integrate Data-Driven Research and Data intensive computing at Johns Hopkins University","funder_award_id":"1920103","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7160140912.pdf","grobid_xml":"https://content.openalex.org/works/W7160140912.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W3177813494","https://openalex.org/W4416034058","https://openalex.org/W4417093014","https://openalex.org/W7127380112"],"related_works":["https://openalex.org/W7208704601","https://openalex.org/W7216505180","https://openalex.org/W7150951891","https://openalex.org/W7206199170","https://openalex.org/W4417093014","https://openalex.org/W7140770361","https://openalex.org/W7172433913","https://openalex.org/W7117547917","https://openalex.org/W6979262165","https://openalex.org/W7167233472"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"are":[3],"increasingly":[4],"deployed":[5],"as":[6,212],"autonomous":[7],"coding":[8,38,122,143],"agents":[9,123,156,180],"and":[10,49,92,126,192,203,220],"have":[11],"achieved":[12],"remarkably":[13],"strong":[14,37],"performance":[15],"on":[16,162],"software":[17],"engineering":[18],"benchmarks.":[19],"However,":[20],"it":[21],"is":[22],"unclear":[23],"whether":[24,94,121],"such":[25,136],"success":[26,160,170],"transfers":[27],"to":[28,44,50,73,119,132,198],"computational":[29,77,87,217],"scientific":[30,57,218],"workflows,":[31],"where":[32],"tasks":[33],"require":[34],"not":[35],"only":[36,173],"ability,":[39],"but":[40],"also":[41],"the":[42,54,95,128,165,225],"ability":[43,72],"navigate":[45],"complex,":[46],"domain-specific":[47],"procedures":[48],"interpret":[51],"results":[52,151],"in":[53,231],"context":[55],"of":[56,112,172,228],"claims.":[58,137],"To":[59],"address":[60],"this":[61],"question,":[62],"we":[63,108],"present":[64],"AutoMat,":[65,163],"a":[66,99,110,169,214,221],"benchmark":[67,215],"for":[68,216,223],"evaluating":[69],"LLM-based":[70,155],"agents'":[71],"reproduce":[74],"claims":[75,113],"from":[76,114,188],"materials":[78,116],"science.":[79],"AutoMat":[80,211],"poses":[81],"three":[82],"interrelated":[83],"challenges:":[84],"recovering":[85],"underspecified":[86],"procedures,":[88,200],"navigating":[89],"specialized":[90],"toolchains,":[91],"determining":[93],"resulting":[96],"evidence":[97],"supports":[98],"claim.":[100],"By":[101],"working":[102],"closely":[103],"with":[104,164],"subject":[105],"matter":[106],"experts,":[107],"curate":[109],"set":[111],"real":[115],"science":[117],"papers":[118],"test":[120],"can":[124],"recover":[125],"execute":[127],"end-to-end":[129],"workflow":[130],"needed":[131],"support":[133],"(or":[134],"undermine)":[135],"We":[138],"then":[139],"evaluate":[140],"multiple":[141],"representative":[142],"agent":[144],"settings":[145],"across":[146],"several":[147],"foundation":[148],"models.":[149],"Our":[150],"show":[152],"that":[153,179,193],"current":[154,226],"obtain":[157],"low":[158],"overall":[159],"rates":[161],"best-performing":[166],"setting":[167],"achieving":[168],"rate":[171],"53%.":[174],"Error":[175],"analysis":[176],"further":[177],"reveals":[178],"perform":[181],"worst":[182],"when":[183],"workflows":[184],"must":[185],"be":[186],"reconstructed":[187],"paper":[189],"text":[190],"alone":[191],"they":[194],"fail":[195],"primarily":[196],"due":[197],"incomplete":[199],"methodological":[201],"deviations,":[202],"execution":[204],"fragility.":[205],"Taken":[206],"together,":[207],"these":[208],"findings":[209],"position":[210],"both":[213],"reproducibility":[219],"tool":[222],"diagnosing":[224],"limitations":[227],"agentic":[229],"systems":[230],"AI-for-science":[232],"settings.":[233]},"counts_by_year":[{"year":2026,"cited_by_count":16}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-05-05T00:00:00"}
