{"id":"https://openalex.org/W7203880176","doi":"https://doi.org/10.48550/arxiv.2608.19799","title":"SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science?","display_name":"SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science?","publication_year":2026,"publication_date":"2026-08-20","ids":{"openalex":"https://openalex.org/W7203880176","doi":"https://doi.org/10.48550/arxiv.2608.19799"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.19799","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.19799","pdf_url":"https://arxiv.org/pdf/2608.19799","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":"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/2608.19799","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125533133","display_name":"Zhipeng Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4405279436","display_name":"Shanghai Innovation Institute","ror":"https://ror.org/01fatbw66","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405279436"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Zhipeng","raw_affiliation_strings":["Fudan University","Shanghai Innovation Institute ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Innovation Institute ,","institution_ids":["https://openalex.org/I4405279436"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147707335","display_name":"Jiahao Lu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4405279436","display_name":"Shanghai Innovation Institute","ror":"https://ror.org/01fatbw66","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405279436"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu, Jiahao","raw_affiliation_strings":["Fudan University","Shanghai Innovation Institute ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Innovation Institute ,","institution_ids":["https://openalex.org/I4405279436"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147757480","display_name":"Yining Zheng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4405279436","display_name":"Shanghai Innovation Institute","ror":"https://ror.org/01fatbw66","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405279436"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng, Yining","raw_affiliation_strings":["Fudan University","Shanghai Innovation Institute ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Innovation Institute ,","institution_ids":["https://openalex.org/I4405279436"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135901596","display_name":"Yuxin Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4405279436","display_name":"Shanghai Innovation Institute","ror":"https://ror.org/01fatbw66","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405279436"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Yuxin","raw_affiliation_strings":["Fudan University","Shanghai Innovation Institute ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Innovation Institute ,","institution_ids":["https://openalex.org/I4405279436"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125493585","display_name":"Xipeng Qiu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4405279436","display_name":"Shanghai Innovation Institute","ror":"https://ror.org/01fatbw66","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405279436"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiu, Xipeng","raw_affiliation_strings":["Fudan University","Shanghai Innovation Institute ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Innovation Institute ,","institution_ids":["https://openalex.org/I4405279436"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"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/T10260","display_name":"Software Engineering Research","score":0.9916999936103821,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9916999936103821,"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"}},{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.005200000014156103,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.0006000000284984708,"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/ai-coding-agents","display_name":"coding agents","score":0.7770000100135803},{"id":"https://openalex.org/keywords/research-software-engineering","display_name":"research software engineering","score":0.8519999980926514},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.4650000035762787},{"id":"https://openalex.org/keywords/program-repair","display_name":"program repair","score":0.42100000381469727},{"id":"https://openalex.org/keywords/failure-mechanisms","display_name":"failure mechanisms","score":0.7250000238418579},{"id":"https://openalex.org/keywords/token-efficiency","display_name":"token efficiency","score":0.5239999890327454},{"id":"https://openalex.org/keywords/anchoring-effect","display_name":"anchoring effect","score":0.5640000104904175},{"id":"https://openalex.org/keywords/generalization","display_name":"generalization","score":0.453000009059906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7139000296592712},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.5945000052452087},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5511999726295471},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5231000185012817},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.5047000050544739},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47760000824928284},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4320000112056732},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.43050000071525574},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3720000088214874},{"id":"https://openalex.org/C2781083858","wikidata":"https://www.wikidata.org/wiki/Q17327049","display_name":"Scientific literature","level":2,"score":0.34529998898506165},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3449000120162964},{"id":"https://openalex.org/C195732255","wikidata":"https://www.wikidata.org/wiki/Q981008","display_name":"Sociology of scientific knowledge","level":2,"score":0.32100000977516174},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.30329999327659607},{"id":"https://openalex.org/C2984917352","wikidata":"https://www.wikidata.org/wiki/Q12772819","display_name":"Scientific discovery","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C138379479","wikidata":"https://www.wikidata.org/wiki/Q1116876","display_name":"Scientific modelling","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C124056412","wikidata":"https://www.wikidata.org/wiki/Q3320364","display_name":"Scientific evidence","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C51929080","wikidata":"https://www.wikidata.org/wiki/Q2425187","display_name":"Codebase","level":3,"score":0.2784000039100647},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.2587999999523163},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.19799","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.19799","pdf_url":"https://arxiv.org/pdf/2608.19799","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.19799","doi":"https://doi.org/10.48550/arxiv.2608.19799","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.19799","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:2608.19799","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.19799","pdf_url":"https://arxiv.org/pdf/2608.19799","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":"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/W7203880176.pdf","grobid_xml":"https://content.openalex.org/works/W7203880176.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W3177813494","https://openalex.org/W3195140297","https://openalex.org/W4415252687","https://openalex.org/W4416036949","https://openalex.org/W4416504264","https://openalex.org/W7166849583","https://openalex.org/W7167888896"],"related_works":["https://openalex.org/W7213515565","https://openalex.org/W7208838833","https://openalex.org/W7172433913","https://openalex.org/W7117547917","https://openalex.org/W7140188231","https://openalex.org/W7219155296","https://openalex.org/W7165782405","https://openalex.org/W7202166648","https://openalex.org/W7127418923","https://openalex.org/W4415273522"],"abstract_inverted_index":{"Software":[0],"increasingly":[1],"functions":[2],"as":[3],"part":[4],"of":[5,16,32,79,215],"the":[6,24,87,101,157,210],"scientific":[7,13,27,49,59,71,106,117,136,153,167,219],"instrument":[8],"itself,":[9],"making":[10],"failures":[11,133],"in":[12,116,141,218],"code":[14],"capable":[15],"compromising":[17],"not":[18,170,194],"only":[19],"program":[20],"behavior":[21],"but":[22],"also":[23],"evidence":[25],"underlying":[26],"conclusions.":[28],"Yet":[29],"existing":[30],"evaluations":[31],"coding":[33,216],"agents":[34,45,217],"largely":[35],"emphasize":[36],"aggregate":[37],"task":[38,74],"success,":[39],"providing":[40],"limited":[41],"insight":[42],"into":[43,77],"why":[44],"fail":[46],"when":[47],"repairing":[48],"software.":[50],"We":[51,109,144],"introduce":[52],"\\textbf{SWE-bench":[53],"Science},":[54],"a":[55,96,147,204],"repository-level":[56],"benchmark":[57],"for":[58,207],"software":[60,107,220],"engineering":[61,161],"comprising":[62],"119":[63],"tasks":[64],"from":[65],"98":[66],"GitHub":[67],"repositories":[68],"across":[69],"20":[70],"domains.":[72],"Each":[73],"is":[75,169],"organized":[76],"one":[78],"three":[80],"paradigms:":[81],"Issue-driven,":[82],"Expert-exploratory,":[83],"and":[84,132,159,178,182,192,212],"Engineering-integration.":[85],"Even":[86],"best-performing":[88],"agent,":[89],"\\textbf{Claude":[90],"Code":[91],"with":[92],"Opus-5":[93],"(max),":[94],"achieves":[95],"pass@1":[97],"below":[98],"50\\%},":[99],"highlighting":[100],"substantial":[102],"challenges":[103],"posed":[104],"by":[105],"engineering.":[108,221],"identify":[110],"four":[111],"recurring":[112],"failure":[113,213],"mechanisms:":[114],"deficits":[115],"knowledge":[118,137,168],"or":[119,123,129],"abstraction,":[120],"misguided":[121],"exploration":[122],"surface-level":[124],"repair,":[125],"incomplete":[126],"repair":[127,177,198],"coverage":[128],"system":[130],"integration,":[131],"to":[134],"generalize":[135],"beyond":[138],"observed":[139],"cases":[140],"our":[142],"analysis.":[143],"further":[145],"conduct":[146],"paired":[148],"ablation":[149],"that":[150,166],"removes":[151],"explicit":[152],"guidance":[154,188],"while":[155],"preserving":[156],"repository":[158],"executable":[160],"context.":[162],"The":[163],"results":[164],"show":[165],"uniformly":[171],"beneficial:":[172],"well-grounded":[173],"information":[174],"can":[175,189],"constrain":[176],"improve":[179,196],"average":[180],"performance":[181],"token":[183],"efficiency,":[184],"whereas":[185],"poorly":[186],"aligned":[187],"induce":[190],"anchoring":[191],"does":[193],"necessarily":[195],"exact":[197],"success.":[199],"Together,":[200],"SWE-bench":[201],"Science":[202],"provides":[203],"broad":[205],"testbed":[206],"studying":[208],"both":[209],"capabilities":[211],"mechanisms":[214]},"counts_by_year":[{"year":2026,"cited_by_count":7}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-22T00:00:00"}
