{"id":"https://openalex.org/W4412886699","doi":"https://doi.org/10.18653/v1/2025.acl-long.189","title":"UTBoost: Rigorous Evaluation of Coding Agents on SWE-Bench","display_name":"UTBoost: Rigorous Evaluation of Coding Agents on SWE-Bench","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412886699","doi":"https://doi.org/10.18653/v1/2025.acl-long.189"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.189","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.189","pdf_url":"https://aclanthology.org/2025.acl-long.189.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.189.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100646137","display_name":"Bin Yu","orcid":"https://orcid.org/0000-0002-8888-4060"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boxi Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yuxuan Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxuan Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119180885","display_name":"Pinjia He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pinjia He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5072348548","display_name":"Daniel Kang","orcid":"https://orcid.org/0000-0001-9860-9938"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Kang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3762","last_page":"3774"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.38199999928474426,"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/T10320","display_name":"Neural Networks and Applications","score":0.38199999928474426,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.3375999927520752,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.5781732797622681},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.48361507058143616},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21951067447662354},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09452894330024719}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5781732797622681},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.48361507058143616},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21951067447662354},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09452894330024719}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.189","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.189","pdf_url":"https://aclanthology.org/2025.acl-long.189.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.189","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.189","pdf_url":"https://aclanthology.org/2025.acl-long.189.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7609782405","display_name":null,"funder_award_id":"2024A1515010145","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320315389","display_name":"Open Philanthropy Project","ror":"https://ror.org/004d1k391"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412886699.pdf","grobid_xml":"https://content.openalex.org/works/W4412886699.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0],"advent":[1],"of":[2,11,28,134,139],"Large":[3],"Language":[4],"Models":[5],"(LLMs)":[6],"has":[7],"spurred":[8],"the":[9,24,44,62,66,127],"development":[10],"coding":[12],"agents":[13],"for":[14,22,90,102],"real-world":[15,33,91],"code":[16,25],"generation.As":[17],"a":[18,99],"widely":[19],"used":[20],"benchmark":[21],"evaluating":[23],"generation":[26],"capabilities":[27],"these":[29,51],"agents,":[30],"SWE-Bench":[31,135,140],"uses":[32],"problems":[34],"based":[35],"on":[36,94],"GitHub":[37],"issues":[38],"and":[39,84,117,137,146],"their":[40],"corresponding":[41],"pull":[42,52],"requests.However,":[43],"manually":[45],"written":[46],"test":[47,77,88,103,115],"cases":[48,89,116],"included":[49],"in":[50,126],"requests":[53],"are":[54],"often":[55],"insufficient,":[56],"allowing":[57],"generated":[58],"patches":[59,121],"to":[60,86],"pass":[61],"tests":[63],"without":[64],"resolving":[65],"underlying":[67],"issue.To":[68],"address":[69],"this":[70],"challenge,":[71],"we":[72,96,108],"introduce":[73],"UTGenerator,":[74,95],"an":[75],"LLM-driven":[76],"case":[78,104],"generator":[79],"that":[80],"automatically":[81],"analyzes":[82],"codebases":[83],"dependencies":[85],"generate":[87],"Python":[92],"projects.Building":[93],"propose":[97],"UTBoost,":[98],"comprehensive":[100],"framework":[101],"augmentation.In":[105],"our":[106],"evaluation,":[107],"identified":[109],"36":[110],"task":[111],"instances":[112],"with":[113],"insufficient":[114],"uncovered":[118],"345":[119],"erroneous":[120],"incorrectly":[122],"labeled":[123],"as":[124],"passed":[125],"original":[128],"SWE":[129],"Bench.These":[130],"corrections,":[131],"impacting":[132],"40.9%":[133],"Lite":[136],"24.4%":[138],"Verified":[141],"leaderboard":[142],"entries,":[143],"yield":[144],"18":[145],"11":[147],"ranking":[148],"changes,":[149],"respectively.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}