{"id":"https://openalex.org/W7204204864","doi":"https://doi.org/10.48550/arxiv.2608.23564","title":"SWE Refactor Bench: Can Coding Agents Complete a Long-Horizon, Whole-Repository Stack Migration?","display_name":"SWE Refactor Bench: Can Coding Agents Complete a Long-Horizon, Whole-Repository Stack Migration?","publication_year":2026,"publication_date":"2026-08-24","ids":{"openalex":"https://openalex.org/W7204204864","doi":"https://doi.org/10.48550/arxiv.2608.23564"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.23564","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23564","pdf_url":"https://arxiv.org/pdf/2608.23564","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.23564","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126139761","display_name":"Deyao Hong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong, Deyao","raw_affiliation_strings":["Navers Lab , Einsia.AI Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Navers Lab , Einsia.AI Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133674494","display_name":"Yizhe Chi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chi, Yizhe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147674761","display_name":"Wenyi Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Wenyi","raw_affiliation_strings":["Navers Lab , Einsia.AI Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Navers Lab , Einsia.AI Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101620861","display_name":"Xiaoqiu Wang","orcid":"https://orcid.org/0000-0003-1355-1947","observed_orcids":["https://orcid.org/0000-0003-1355-1947"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Xiaoqiu","raw_affiliation_strings":["Navers Lab , Einsia.AI Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Navers Lab , Einsia.AI Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147663728","display_name":"Mingju Gao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gao, Mingju","raw_affiliation_strings":["Navers Lab , Einsia.AI Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Navers Lab , Einsia.AI Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014780291","display_name":"Kaisen Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Kaisen","raw_affiliation_strings":["Navers Lab , Einsia.AI Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Navers Lab , Einsia.AI Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139784330","display_name":"Bingxiang He","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He, Bingxiang","raw_affiliation_strings":["Navers Lab , Einsia.AI Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Navers Lab , Einsia.AI Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133701726","display_name":"Youjie Zheng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng, Youjie","raw_affiliation_strings":["Navers Lab , Einsia.AI Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Navers Lab , Einsia.AI Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133677639","display_name":"Calvin Xiao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao, Calvin","raw_affiliation_strings":["Navers Lab , Einsia.AI Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Navers Lab , Einsia.AI Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5133632788","display_name":"Qinhuai Na","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Na, Qinhuai","raw_affiliation_strings":["Navers Lab , Einsia.AI Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Navers Lab , Einsia.AI Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"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/T10260","display_name":"Software Engineering Research","score":0.9994999766349792,"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":0.9994999766349792,"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":9.999999747378752e-05,"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":9.999999747378752e-05,"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":0.8899999856948853},{"id":"https://openalex.org/keywords/software-migration","display_name":"software migration","score":0.6150000095367432},{"id":"https://openalex.org/keywords/technical-debt","display_name":"technical debt","score":0.8240000009536743},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.6039999723434448},{"id":"https://openalex.org/keywords/test-case-generation","display_name":"test case generation","score":0.5460000038146973}],"concepts":[{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7621999979019165},{"id":"https://openalex.org/C152752567","wikidata":"https://www.wikidata.org/wiki/Q116877","display_name":"Code refactoring","level":3,"score":0.7384999990463257},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7246999740600586},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4964999854564667},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.37860000133514404},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.37400001287460327},{"id":"https://openalex.org/C17231256","wikidata":"https://www.wikidata.org/wiki/Q5156540","display_name":"Completeness (order theory)","level":2,"score":0.3677999973297119},{"id":"https://openalex.org/C110251889","wikidata":"https://www.wikidata.org/wiki/Q1569697","display_name":"Model checking","level":2,"score":0.36489999294281006},{"id":"https://openalex.org/C128942645","wikidata":"https://www.wikidata.org/wiki/Q1568346","display_name":"Test case","level":3,"score":0.34880000352859497},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3285999894142151},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.29319998621940613},{"id":"https://openalex.org/C75606506","wikidata":"https://www.wikidata.org/wiki/Q1049183","display_name":"Formal methods","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C2777062904","wikidata":"https://www.wikidata.org/wiki/Q545406","display_name":"Toolchain","level":3,"score":0.287200003862381},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2637999951839447},{"id":"https://openalex.org/C111498074","wikidata":"https://www.wikidata.org/wiki/Q173326","display_name":"Formal verification","level":2,"score":0.25220000743865967},{"id":"https://openalex.org/C111065885","wikidata":"https://www.wikidata.org/wiki/Q1189053","display_name":"Fuzz testing","level":3,"score":0.2513999938964844}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.23564","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23564","pdf_url":"https://arxiv.org/pdf/2608.23564","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.2608.23564","doi":"https://doi.org/10.48550/arxiv.2608.23564","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.23564","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:2608.23564","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23564","pdf_url":"https://arxiv.org/pdf/2608.23564","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/W7204204864.pdf","grobid_xml":"https://content.openalex.org/works/W7204204864.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7202186081","https://openalex.org/W7140103958","https://openalex.org/W7204760891","https://openalex.org/W7223019374","https://openalex.org/W7133943242","https://openalex.org/W7122833958","https://openalex.org/W7214207320","https://openalex.org/W7202166648","https://openalex.org/W7223020975","https://openalex.org/W4415273522"],"abstract_inverted_index":{"Modern":[0],"software":[1],"systems":[2],"accumulate":[3],"technical":[4,87],"debt":[5],"over":[6],"decades":[7],"of":[8,86,147,156,223],"development,":[9],"which":[10],"makes":[11],"migration":[12,47,95,106,187,236],"expensive":[13],"and":[14,97,141,164,173,188,197,200],"largely":[15],"manual.":[16],"As":[17],"coding":[18,124,264],"agents":[19,55,125,238,265],"become":[20],"increasingly":[21],"capable":[22],"at":[23,191,203],"bug":[24],"fixing,":[25],"can":[26],"they":[27,39],"autonomously":[28],"perform":[29],"such":[30],"migrations?":[31],"Existing":[32],"benchmarks":[33],"cannot":[34,207],"answer":[35],"this":[36,66,70],"question":[37],"because":[38],"evaluate":[40],"only":[41,145,228,246],"behavioural":[42,98,132,174],"correctness,":[43],"not":[44],"whether":[45],"the":[46,57,105,157,165,186,213,224],"actually":[48],"occurred.":[49,107],"This":[50],"leads":[51],"an":[52],"easy":[53],"hack:":[54],"copy":[56],"original":[58],"implementation":[59],"to":[60,126],"make":[61],"tests":[62,129],"pass.":[63],"We":[64],"call":[65],"Blindness.":[67],"To":[68],"address":[69],"problem,":[71],"we":[72],"introduce":[73],"SWE":[74,255],"Refactor":[75,256],"Bench,":[76],"a":[77,114,179,209,259],"benchmark":[78],"comprising":[79],"20":[80,158],"whole-repository":[81,268],"migrations,":[82],"covering":[83],"4":[84],"kinds":[85],"debt.":[88],"A":[89],"three-stage":[90],"evaluation":[91],"protocol":[92],"measures":[93],"both":[94],"completeness":[96,172],"correctness.":[99],"(1)":[100],"Migration":[101,171,192,218],"Audit":[102],"verifies":[103],"that":[104,216],"(2)":[108],"Behavioural":[109,204],"Tests":[110],"measure":[111],"correctness":[112,175],"with":[113],"fixed":[115,225],"test":[116],"suite.":[117],"(3)":[118],"Agentic":[119],"Verification":[120],"uses":[121],"6":[122],"independent":[123],"generate":[127],"targeted":[128],"for":[130,262,266],"hidden":[131],"differences.":[133],"Across":[134],"520":[135,148],"runs":[136,149,181,215],"from":[137],"8":[138],"frontier":[139],"models":[140],"26":[142],"model-effort":[143],"configurations,":[144],"28":[146],"($5.4\\%$)":[150],"pass":[151,217],"all":[152],"three":[153],"stages,":[154],"13":[155],"tasks":[159],"receive":[160],"no":[161],"accepted":[162],"solution,":[163],"best":[166],"model":[167],"(claude-opus-5)":[168],"scores":[169],"$47.0/100$.":[170],"are":[176,189,201],"distinct":[177],"abilities:":[178],"few":[180],"preserve":[182],"behaviour":[183],"by":[184],"skipping":[185],"stopped":[190,202],"Audit;":[193],"most":[194],"attempt":[195],"it":[196],"break":[198],"behaviour,":[199],"Tests.":[205],"Agents":[206],"deliver":[208],"perfect":[210],"migration:":[211],"among":[212],"340":[214],"Audit,":[219],"$58\\%$":[220],"reach":[221,230],"$99\\%$":[222],"checks,":[226],"yet":[227],"$26\\%$":[229],"$100\\%$.":[231],"Agent":[232],"capability":[233],"differs":[234],"across":[235],"categories:":[237],"score":[239],"$31.4$":[240],"on":[241,248],"build":[242],"toolchain":[243],"rewrites":[244],"but":[245],"$5.6$":[247],"language":[249],"rewrites.":[250],"Together,":[251],"these":[252],"findings":[253],"position":[254],"Bench":[257],"as":[258],"rigorous":[260],"testbed":[261],"developing":[263],"reliable":[267],"migrations.":[269]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-26T00:00:00"}
