{"id":"https://openalex.org/W4409495635","doi":"https://doi.org/10.1109/icstw64639.2025.10962485","title":"Mutation Testing via Iterative Large Language Model-Driven Scientific Debugging","display_name":"Mutation Testing via Iterative Large Language Model-Driven Scientific Debugging","publication_year":2025,"publication_date":"2025-03-31","ids":{"openalex":"https://openalex.org/W4409495635","doi":"https://doi.org/10.1109/icstw64639.2025.10962485"},"language":"en","primary_location":{"id":"doi:10.1109/icstw64639.2025.10962485","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icstw64639.2025.10962485","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013475041","display_name":"Philipp Straubinger","orcid":"https://orcid.org/0000-0002-9265-5789"},"institutions":[{"id":"https://openalex.org/I186354981","display_name":"University of Passau","ror":"https://ror.org/05ydjnb78","country_code":"DE","type":"education","lineage":["https://openalex.org/I186354981"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Philipp Straubinger","raw_affiliation_strings":["University of Passau,Passau,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Passau,Passau,Germany","institution_ids":["https://openalex.org/I186354981"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068148900","display_name":"Marvin Kreis","orcid":null},"institutions":[{"id":"https://openalex.org/I186354981","display_name":"University of Passau","ror":"https://ror.org/05ydjnb78","country_code":"DE","type":"education","lineage":["https://openalex.org/I186354981"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marvin Kreis","raw_affiliation_strings":["University of Passau,Passau,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Passau,Passau,Germany","institution_ids":["https://openalex.org/I186354981"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020418691","display_name":"Stephan Lukasczyk","orcid":"https://orcid.org/0000-0002-0092-3476"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stephan Lukasczyk","raw_affiliation_strings":["JetBrains Research,Munich,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JetBrains Research,Munich,Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079261847","display_name":"Gordon Fraser","orcid":"https://orcid.org/0000-0002-4364-6595"},"institutions":[{"id":"https://openalex.org/I186354981","display_name":"University of Passau","ror":"https://ror.org/05ydjnb78","country_code":"DE","type":"education","lineage":["https://openalex.org/I186354981"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gordon Fraser","raw_affiliation_strings":["University of Passau,Passau,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Passau,Passau,Germany","institution_ids":["https://openalex.org/I186354981"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.6921,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.96568318,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"358","last_page":"367"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9894999861717224,"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":0.9894999861717224,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9700000286102295,"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/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.9526000022888184,"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/debugging","display_name":"Debugging","score":0.7507473230361938},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7472032904624939},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.6879111528396606},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.43664056062698364}],"concepts":[{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.7507473230361938},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7472032904624939},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6879111528396606},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.43664056062698364}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icstw64639.2025.10962485","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icstw64639.2025.10962485","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1526710119","https://openalex.org/W1971650562","https://openalex.org/W1977321274","https://openalex.org/W2066536303","https://openalex.org/W2096274199","https://openalex.org/W2107147876","https://openalex.org/W2114869486","https://openalex.org/W2135841285","https://openalex.org/W2586946380","https://openalex.org/W2743165481","https://openalex.org/W2765527199","https://openalex.org/W2774185825","https://openalex.org/W3108032709","https://openalex.org/W3116061526","https://openalex.org/W3170092793","https://openalex.org/W3211801722","https://openalex.org/W3212260724","https://openalex.org/W4220699888","https://openalex.org/W4220709169","https://openalex.org/W4239170027","https://openalex.org/W4308731473","https://openalex.org/W4313563520","https://openalex.org/W4377942506","https://openalex.org/W4384304865","https://openalex.org/W4387711873","https://openalex.org/W4389104713","https://openalex.org/W4391974543","https://openalex.org/W4393305539","https://openalex.org/W4394015350","https://openalex.org/W4398239306","https://openalex.org/W4400485000","https://openalex.org/W4400582690","https://openalex.org/W4400798705","https://openalex.org/W4401042243","https://openalex.org/W4405556610","https://openalex.org/W6636084041","https://openalex.org/W6637688222","https://openalex.org/W6739901393","https://openalex.org/W6778883912","https://openalex.org/W6810738896","https://openalex.org/W6852119581","https://openalex.org/W6869682623","https://openalex.org/W6873146318","https://openalex.org/W6875278526"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4321442002","https://openalex.org/W2015265939","https://openalex.org/W2284072287","https://openalex.org/W2061417947","https://openalex.org/W2621101275","https://openalex.org/W4321782533","https://openalex.org/W3096156304"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"can":[4,71],"generate":[5,11,76,96,123],"plausible":[6],"test":[7,136,193,200],"code.":[8],"Intuitively":[9],"they":[10,101],"this":[12,55,112],"by":[13],"imitating":[14],"tests":[15,38,77,99,131,178],"seen":[16],"in":[17,43,176],"their":[18],"training":[19],"data,":[20],"rather":[21],"than":[22],"reasoning":[23,29],"about":[24,87],"execution":[25],"semantics.":[26],"However,":[27],"such":[28],"is":[30,195],"important":[31,196],"when":[32,69,130],"applying":[33],"mutation":[34,150],"testing,":[35],"where":[36],"individual":[37],"need":[39],"to":[40,66,75,89,114,122,159],"demonstrate":[41,165],"differences":[42],"program":[44,48],"behavior":[45],"between":[46],"a":[47],"and":[49,93,97,133,156,183],"specific":[50,91],"artificial":[51],"defects":[52],"(mutants).":[53],"In":[54,80],"paper,":[56],"we":[57,186],"evaluate":[58,142],"whether":[59],"Scientific":[60],"Debugging,":[61],"which":[62],"has":[63],"been":[64],"shown":[65],"help":[67,73],"LLMs":[68,84],"debugging,":[70],"also":[72],"them":[74],"for":[78,107,197],"mutants.":[79,162],"the":[81,120,128,157,189],"resulting":[82],"approach,":[83],"form":[85],"hypotheses":[86],"how":[88],"kill":[90],"mutants,":[92],"then":[94],"iteratively":[95],"refine":[98],"until":[100],"succeed,":[102],"all":[103],"with":[104,138,179],"detailed":[105],"explanations":[106],"each":[108],"step.":[109],"We":[110],"compare":[111],"method":[113],"three":[115],"baselines:":[116],"(1)":[117],"directly":[118],"asking":[119],"LLM":[121,129],"tests,":[124],"(2)":[125],"repeatedly":[126],"querying":[127],"fail,":[132],"(3)":[134],"search-based":[135],"generation":[137],"Pynguin.":[139],"Our":[140],"experiments":[141],"these":[143],"methods":[144],"based":[145],"on":[146],"several":[147],"factors,":[148],"including":[149],"score,":[151],"code":[152],"coverage,":[153],"success":[154],"rate,":[155],"ability":[158],"identify":[160],"equivalent":[161],"The":[163],"results":[164],"that":[166,188],"LLMs,":[167],"although":[168],"requiring":[169],"higher":[170],"computational":[171],"cost,":[172],"consistently":[173],"outperform":[174],"Pynguin":[175],"generating":[177],"better":[180],"fault":[181],"detection":[182],"coverage.":[184],"Importantly,":[185],"observe":[187],"iterative":[190],"refinement":[191],"of":[192],"cases":[194],"achieving":[198],"high-quality":[199],"suites.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}