{"id":"https://openalex.org/W4411523059","doi":"https://doi.org/10.1145/3728922","title":"You Name It, I Run It: An LLM Agent to Execute Tests of Arbitrary Projects","display_name":"You Name It, I Run It: An LLM Agent to Execute Tests of Arbitrary Projects","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W4411523059","doi":"https://doi.org/10.1145/3728922"},"language":"en","primary_location":{"id":"doi:10.1145/3728922","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3728922","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Software Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3728922","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019267326","display_name":"Islem Bouzenia","orcid":"https://orcid.org/0000-0002-3920-3839"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Islem Bouzenia","raw_affiliation_strings":["University of Stuttgart, Stuttgart, Germany"],"raw_orcid":"https://orcid.org/0000-0002-3920-3839","affiliations":[{"raw_affiliation_string":"University of Stuttgart, Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013438083","display_name":"Michael Pradel","orcid":"https://orcid.org/0000-0003-1623-498X"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Pradel","raw_affiliation_strings":["University of Stuttgart, Stuttgart, Germany"],"raw_orcid":"https://orcid.org/0000-0003-1623-498X","affiliations":[{"raw_affiliation_string":"University of Stuttgart, Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I100066346"],"apc_list":null,"apc_paid":null,"fwci":46.4141,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.99815545,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"2","issue":"ISSTA","first_page":"1054","last_page":"1076"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/test-suite","display_name":"Test suite","score":0.8167444467544556},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8008434176445007},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.6811574697494507},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.6309611797332764},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5293458104133606},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5006470680236816},{"id":"https://openalex.org/keywords/code-coverage","display_name":"Code coverage","score":0.46772563457489014},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.46271607279777527},{"id":"https://openalex.org/keywords/test-case","display_name":"Test case","score":0.4444884657859802},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4168856739997864},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.38306620717048645},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.12787047028541565}],"concepts":[{"id":"https://openalex.org/C151552104","wikidata":"https://www.wikidata.org/wiki/Q7705809","display_name":"Test suite","level":4,"score":0.8167444467544556},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8008434176445007},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.6811574697494507},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.6309611797332764},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5293458104133606},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5006470680236816},{"id":"https://openalex.org/C53942775","wikidata":"https://www.wikidata.org/wiki/Q1211721","display_name":"Code coverage","level":3,"score":0.46772563457489014},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.46271607279777527},{"id":"https://openalex.org/C128942645","wikidata":"https://www.wikidata.org/wiki/Q1568346","display_name":"Test case","level":3,"score":0.4444884657859802},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4168856739997864},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.38306620717048645},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.12787047028541565},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3728922","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3728922","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Software Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3728922","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3728922","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Software Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3524015675","display_name":null,"funder_award_id":"851895,101155832","funder_id":"https://openalex.org/F4320334678","funder_display_name":"European Research Council"}],"funders":[{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2956069715","https://openalex.org/W3105943882","https://openalex.org/W4308643019","https://openalex.org/W4309591663","https://openalex.org/W4320165837","https://openalex.org/W4321177655","https://openalex.org/W4378474282","https://openalex.org/W4384009692","https://openalex.org/W4384345748","https://openalex.org/W4389104713","https://openalex.org/W4389158517","https://openalex.org/W4389519225","https://openalex.org/W4390601895","https://openalex.org/W4391558516","https://openalex.org/W4391835904","https://openalex.org/W4394769544","https://openalex.org/W4400484653","https://openalex.org/W4402442868","https://openalex.org/W6891828641"],"related_works":["https://openalex.org/W4295918990","https://openalex.org/W4313447549","https://openalex.org/W2028796071","https://openalex.org/W2410893741","https://openalex.org/W2067499928","https://openalex.org/W1888619389","https://openalex.org/W1968494916","https://openalex.org/W4376482197","https://openalex.org/W2794522096","https://openalex.org/W3022870375"],"abstract_inverted_index":{"The":[0,141,191,229],"ability":[1],"to":[2,16,23,34,75,145,153,174,257,272],"execute":[3,273],"the":[4,43,113,138,149,154,167,195,203,222,233],"test":[5,44,80,109,196,204,209],"suite":[6,45,210],"of":[7,46,198,206,215,241,247,279],"a":[8,47,77,115,125,213,260,276],"project":[9,48,102],"is":[10,124],"essential":[11],"in":[12,52],"many":[13,185],"scenarios,":[14],"e.g.,":[15],"assess":[17],"code":[18,21,25,105],"quality":[19],"and":[20,33,67,106,135,157,184,188,244,268],"coverage,":[22],"validate":[24],"changes":[26],"made":[27],"by":[28,112,227,232],"developers":[29],"or":[30],"automated":[31,93,265],"tools,":[32,267],"ensure":[35],"compatibility":[36],"with":[37,137,212,237],"dependencies.":[38],"Despite":[39],"its":[40,108,161],"importance,":[41],"executing":[42],"can":[49],"be":[50],"challenging":[51],"practice":[53],"because":[54],"different":[55,58,86,181,186],"projects":[56,177],"use":[57,179],"programming":[59,182,266],"languages,":[60],"software":[61],"ecosystems,":[62],"build":[63,187],"systems,":[64],"testing":[65,189],"frameworks,":[66],"other":[68],"tools.":[69,190],"These":[70,218],"challenges":[71],"make":[72],"it":[73,158],"difficult":[74],"create":[76],"reliable,":[78],"universal":[79],"execution":[81,239],"method":[82],"that":[83,95,131,178,270],"works":[84],"across":[85,275],"projects.":[87,280],"This":[88],"paper":[89],"presents":[90],"ExecutionAgent,":[91],"an":[92,100,238],"technique":[94,226],"prepares":[96],"scripts":[97],"for":[98,263],"building":[99],"arbitrary":[101],"from":[103,166],"source":[104],"running":[107],"cases.":[110],"Inspired":[111],"way":[114],"human":[116],"developer":[117],"would":[118],"address":[119],"this":[120],"task,":[121],"our":[122],"approach":[123,192,234],"large":[126],"language":[127],"model":[128],"(LLM)-based":[129],"agent":[130,142],"autonomously":[132],"executes":[133,194],"commands":[134],"interacts":[136],"host":[139],"system.":[140],"uses":[143],"meta-prompting":[144],"gather":[146],"guidelines":[147],"on":[148,164,250],"latest":[150],"technologies":[151],"related":[152],"given":[155],"project,":[156],"iteratively":[159],"refines":[160],"process":[162],"based":[163],"feedback":[165],"previous":[168],"steps.":[169],"Our":[170],"evaluation":[171],"applies":[172],"ExecutionAgent":[173,256],"50":[175],"open-source":[176],"14":[180],"languages":[183],"successfully":[193],"suites":[197],"33/50":[199],"projects,":[200],"while":[201],"matching":[202],"results":[205,219],"ground":[207],"truth":[208],"executions":[211],"deviation":[214],"only":[216],"7.5%.":[217],"improve":[220],"over":[221],"best":[223],"previously":[224],"available":[225],"6.6x.":[228],"costs":[230,246],"imposed":[231],"are":[235],"reasonable,":[236],"time":[240],"74":[242],"minutes":[243],"LLM":[245],"USD":[248],"0.16,":[249],"average":[251],"per":[252],"project.":[253],"We":[254],"envision":[255],"serve":[258],"as":[259],"valuable":[261],"tool":[262],"developers,":[264],"researchers":[269],"need":[271],"tests":[274],"wide":[277],"variety":[278]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":9}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}
