{"id":"https://openalex.org/W7161739577","doi":"https://doi.org/10.48550/arxiv.2605.17242","title":"From Runnable to Shippable: Multi-Agent Test-Driven Development for Generating Full-Stack Web Applications from Requirements","display_name":"From Runnable to Shippable: Multi-Agent Test-Driven Development for Generating Full-Stack Web Applications from Requirements","publication_year":2026,"publication_date":"2026-05-17","ids":{"openalex":"https://openalex.org/W7161739577","doi":"https://doi.org/10.48550/arxiv.2605.17242"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.17242","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.17242","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.17242","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136467379","display_name":"Yuxuan Wan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wan, Yuxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026107034","display_name":"T. Jake Liang","orcid":"https://orcid.org/0000-0003-3828-702X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Tingshuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136457484","display_name":"Jiakai Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Jiakai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136499689","display_name":"Jingyu Xiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao, Jingyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080873193","display_name":"Yintong Huo","orcid":"https://orcid.org/0009-0006-8798-5667"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huo, Yintong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136479107","display_name":"Michael R Lyu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lyu, Michael R","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":false,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.4259999990463257,"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"}},"topics":[{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.4259999990463257,"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/T10260","display_name":"Software Engineering Research","score":0.1597999930381775,"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.06310000270605087,"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/correctness","display_name":"Correctness","score":0.6184999942779541},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.5860999822616577},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.557699978351593},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.49050000309944153},{"id":"https://openalex.org/keywords/codebase","display_name":"Codebase","score":0.4440999925136566},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.42989999055862427},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.42289999127388},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.39579999446868896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8079000115394592},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6184999942779541},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.5860999822616577},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.557699978351593},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.5210999846458435},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.49050000309944153},{"id":"https://openalex.org/C51929080","wikidata":"https://www.wikidata.org/wiki/Q2425187","display_name":"Codebase","level":3,"score":0.4440999925136566},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.42989999055862427},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.42289999127388},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.39579999446868896},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.38760000467300415},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.3743000030517578},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C120927855","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application development","level":4,"score":0.3452000021934509},{"id":"https://openalex.org/C11392498","wikidata":"https://www.wikidata.org/wiki/Q11288","display_name":"Web server","level":3,"score":0.33649998903274536},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.29820001125335693},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C20574231","wikidata":"https://www.wikidata.org/wiki/Q844605","display_name":"Backward compatibility","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2847000062465668},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C35578498","wikidata":"https://www.wikidata.org/wiki/Q193424","display_name":"Web service","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C91262260","wikidata":"https://www.wikidata.org/wiki/Q528074","display_name":"End user","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.26010000705718994}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.17242","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.17242","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.17242","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.17242","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.6551462411880493}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Coding":[0],"agents":[1,67],"can":[2],"generate":[3],"web":[4,33,139],"applications":[5,17,187],"from":[6,38,191,201,236],"natural-language":[7],"descriptions,":[8],"yet":[9],"a":[10,76,167],"recent":[11],"benchmark":[12],"study":[13,132,223],"shows":[14],"that":[15,32,65,78,174,185,196,225],"generated":[16],"fail":[18],"to":[19,206,219,231,240],"meet":[20],"functional":[21],"requirements":[22,89],"in":[23],"over":[24,166],"70%":[25],"of":[26,133],"cases.":[27],"The":[28,170],"core":[29],"difficulty":[30],"is":[31,97,173],"correctness":[34],"cannot":[35,68],"be":[36,47,57],"assessed":[37],"source":[39],"files":[40],"or":[41],"terminal":[42],"output:":[43],"the":[44,101,120,128,175,180,210,234],"application":[45,102,140],"must":[46,56],"deployed,":[48],"exercised":[49],"through":[50,83,106],"simulated":[51],"browser":[52],"interactions,":[53],"and":[54,103,110,153],"failures":[55,114],"translated":[58],"into":[59,90,115],"actionable":[60],"repair":[61,117],"signals":[62],"--":[63],"steps":[64],"current":[66],"perform":[69],"without":[70],"human":[71],"mediation.":[72],"We":[73],"present":[74],"TDDev,":[75,125],"framework":[77],"automates":[79],"this":[80],"closed":[81],"loop":[82],"three":[84],"stages:":[85],"(1)":[86],"converting":[87],"high-level":[88],"structured":[91,116],"acceptance":[92],"tests":[93],"before":[94],"any":[95],"code":[96,198],"written,":[98],"(2)":[99],"deploying":[100],"validating":[104],"it":[105],"browser-based":[107],"interaction":[108],"simulation,":[109],"(3)":[111],"translating":[112],"browser-observed":[113],"reports":[118],"for":[119,138],"coding":[121,148],"agent.":[122],"Enabled":[123],"by":[124,162],"we":[126],"conduct":[127],"first":[129],"controlled":[130],"empirical":[131],"Test-driven":[134],"development":[135,144],"(TDD)":[136],"strategies":[137],"generation,":[141],"comparing":[142],"four":[143],"protocols":[145],"across":[146],"two":[147,150,154],"agents,":[149],"backbone":[151],"models,":[152],"benchmarks.":[155],"TDD":[156,211],"infrastructure":[157],"consistently":[158],"improves":[159],"generation":[160,182,207],"quality":[161],"34--48":[163],"percentage":[164],"points":[165],"no-TDD":[168],"baseline.":[169],"central":[171],"finding":[172],"optimal":[176],"protocol":[177,205],"depends":[178],"on":[179],"model's":[181],"style:":[183],"models":[184,195],"build":[186],"holistically":[188],"benefit":[189,200,212],"most":[190],"agentic":[192],"enforcement,":[193],"while":[194,214],"extend":[197],"conservatively":[199],"incremental":[202],"enforcement.":[203],"Mismatching":[204],"style":[208],"eliminates":[209],"entirely":[213],"multiplying":[215],"token":[216],"cost":[217],"up":[218],"25-fold.":[220],"A":[221],"user":[222],"confirms":[224],"TDDev":[226],"reduces":[227],"manual":[228],"developer":[229],"intervention":[230],"zero,":[232],"shifting":[233],"workload":[235],"continuous":[237],"prompt":[238],"engineering":[239],"autonomous,":[241],"feedback-driven":[242],"refinement.":[243]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-20T00:00:00"}
