{"id":"https://openalex.org/W7220374805","doi":"https://doi.org/10.4230/lipics.esem.2026.83","title":"ARIA - An Agentic Framework for Autonomous Testing of Infotainment Systems","display_name":"ARIA - An Agentic Framework for Autonomous Testing of Infotainment Systems","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7220374805","doi":"https://doi.org/10.4230/lipics.esem.2026.83"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.04913","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.04913","pdf_url":"https://arxiv.org/pdf/2609.04913","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.04913","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5144162713","display_name":"Ant\u00f3nio Henrique Martins Azevedo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I182534213","display_name":"Universidade do Porto","ror":"https://ror.org/043pwc612","country_code":"PT","type":"education","lineage":["https://openalex.org/I182534213"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Azevedo, Ant\u00f3nio","raw_affiliation_strings":["Critical Techworks, Porto, Portugal","Faculty of Engineering, University of Porto, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Critical Techworks, Porto, Portugal","institution_ids":[]},{"raw_affiliation_string":"Faculty of Engineering, University of Porto, Portugal","institution_ids":["https://openalex.org/I182534213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020764456","display_name":"Bruno Lima","orcid":"https://orcid.org/0000-0003-2572-047X","observed_orcids":["https://orcid.org/0000-0003-2572-047X"]},"institutions":[{"id":"https://openalex.org/I182534213","display_name":"Universidade do Porto","ror":"https://ror.org/043pwc612","country_code":"PT","type":"education","lineage":["https://openalex.org/I182534213"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Lima, Bruno","raw_affiliation_strings":["LIACC, Faculty of Engineering, University of Porto, Portugal"],"raw_orcid":"https://orcid.org/0000-0003-2572-047X","affiliations":[{"raw_affiliation_string":"LIACC, Faculty of Engineering, University of Porto, Portugal","institution_ids":["https://openalex.org/I182534213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001101188","display_name":"Jo\u00e3o Pascoal Faria","orcid":"https://orcid.org/0000-0003-3825-3954","observed_orcids":["https://orcid.org/0000-0003-3825-3954"]},"institutions":[{"id":"https://openalex.org/I182534213","display_name":"Universidade do Porto","ror":"https://ror.org/043pwc612","country_code":"PT","type":"education","lineage":["https://openalex.org/I182534213"]},{"id":"https://openalex.org/I4210166615","display_name":"INESC TEC","ror":"https://ror.org/05fa8ka61","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210125590","https://openalex.org/I4210166615"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Faria, Jo\u00e3o Pascoal","raw_affiliation_strings":["INESC TEC, Faculty of Engineering, University of Porto, Portugal"],"raw_orcid":"https://orcid.org/0000-0003-3825-3954","affiliations":[{"raw_affiliation_string":"INESC TEC, Faculty of Engineering, University of Porto, Portugal","institution_ids":["https://openalex.org/I182534213","https://openalex.org/I4210166615"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9897000193595886,"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":0.9897000193595886,"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.0017000000225380063,"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/T13287","display_name":"Robotic Process Automation Applications","score":0.0008999999845400453,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/in-vehicle-infotainment","display_name":"infotainment","score":0.8149999976158142},{"id":"https://openalex.org/keywords/autonomous-testing","display_name":"autonomous testing","score":0.7590000033378601},{"id":"https://openalex.org/keywords/multi-agent-llm-framework","display_name":"multi-agent LLM framework","score":0.7889999747276306},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8759999871253967},{"id":"https://openalex.org/keywords/test-report-generation","display_name":"test report generation","score":0.5070000290870667},{"id":"https://openalex.org/keywords/false-positive-rate","display_name":"false positive rate","score":0.6330000162124634},{"id":"https://openalex.org/keywords/over-the-air-updates","display_name":"over-the-air updates","score":0.7900000214576721},{"id":"https://openalex.org/keywords/false-rejection-rate","display_name":"false rejection rate","score":0.4659999907016754},{"id":"https://openalex.org/keywords/llm-hallucination","display_name":"LLM hallucination","score":0.47999998927116394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6019999980926514},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5494999885559082},{"id":"https://openalex.org/C526921623","wikidata":"https://www.wikidata.org/wiki/Q190117","display_name":"Automotive industry","level":2,"score":0.48820000886917114},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.48570001125335693},{"id":"https://openalex.org/C14185376","wikidata":"https://www.wikidata.org/wiki/Q30232","display_name":"Agile software development","level":2,"score":0.43790000677108765},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4352000057697296},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4058000147342682},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.3919999897480011},{"id":"https://openalex.org/C7166840","wikidata":"https://www.wikidata.org/wiki/Q1199682","display_name":"System testing","level":2,"score":0.38850000500679016},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.3874000012874603},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3720000088214874},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.36899998784065247},{"id":"https://openalex.org/C105446022","wikidata":"https://www.wikidata.org/wiki/Q445962","display_name":"Legacy system","level":3,"score":0.36149999499320984},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.36079999804496765},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.34360000491142273},{"id":"https://openalex.org/C145644426","wikidata":"https://www.wikidata.org/wiki/Q169411","display_name":"Unified Modeling Language","level":3,"score":0.3197000026702881},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.29989999532699585},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C180152950","wikidata":"https://www.wikidata.org/wiki/Q2904257","display_name":"Software development process","level":4,"score":0.29440000653266907},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C165825675","wikidata":"https://www.wikidata.org/wiki/Q1399743","display_name":"Model-based testing","level":4,"score":0.2784000039100647},{"id":"https://openalex.org/C179768478","wikidata":"https://www.wikidata.org/wiki/Q1120057","display_name":"Cyber-physical system","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C110251889","wikidata":"https://www.wikidata.org/wiki/Q1569697","display_name":"Model checking","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C111065885","wikidata":"https://www.wikidata.org/wiki/Q1189053","display_name":"Fuzz testing","level":3,"score":0.2572999894618988},{"id":"https://openalex.org/C25344961","wikidata":"https://www.wikidata.org/wiki/Q192726","display_name":"Virtual machine","level":2,"score":0.25540000200271606}],"mesh":[],"locations_count":5,"locations":[{"id":"pmh:oai:arXiv.org:2609.04913","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.04913","pdf_url":"https://arxiv.org/pdf/2609.04913","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:drops-oai.dagstuhl.de:28051","doi":null,"is_oa":true,"landing_page_url":"https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ESEM.2026.83","pdf_url":"https://drops.dagstuhl.de/storage/00lipics/lipics-vol394-esem2026/LIPIcs.ESEM.2026.83/LIPIcs.ESEM.2026.83.pdf","source":{"id":"https://openalex.org/S4377196569","display_name":"DROPS (Schloss Dagstuhl \u2013 Leibniz Center for Informatics)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2799853480","host_organization_name":"Schloss Dagstuhl \u2013 Leibniz Center for Informatics","host_organization_lineage":["https://openalex.org/I2799853480"],"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":"InProceedings"},{"id":"pmh:oai:repositorio-aberto.up.pt:10216/175555","doi":null,"is_oa":false,"landing_page_url":"https://hdl.handle.net/10216/175555","pdf_url":null,"source":{"id":"https://openalex.org/S4306402433","display_name":"Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"master thesis"},{"id":"doi:10.48550/arxiv.2609.04913","doi":"https://doi.org/10.48550/arxiv.2609.04913","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.04913","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.4230/lipics.esem.2026.83","doi":"https://doi.org/10.4230/lipics.esem.2026.83","is_oa":true,"landing_page_url":"https://doi.org/10.4230/lipics.esem.2026.83","pdf_url":null,"source":{"id":"https://openalex.org/S4393917817","display_name":"Leibniz international proceedings in informatics","issn_l":"1868-8969","issn":["1868-8969"],"is_oa":true,"is_in_doaj":true,"is_core":false,"listed_in":["doaj","jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"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":"ConferencePaper"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.04913","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.04913","pdf_url":"https://arxiv.org/pdf/2609.04913","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220374805.pdf","grobid_xml":"https://content.openalex.org/works/W7220374805.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4200101789","https://openalex.org/W4417172242","https://openalex.org/W4412742939","https://openalex.org/W7162394683","https://openalex.org/W4406892642","https://openalex.org/W7124458316","https://openalex.org/W7154215291","https://openalex.org/W7160296492","https://openalex.org/W7212026816","https://openalex.org/W7216906481"],"abstract_inverted_index":{"Automotive":[0],"infotainment":[1,68,88,134,182],"validation":[2,57],"still":[3],"relies":[4],"on":[5,86,129,202],"manual":[6],"testing,":[7],"slow,":[8],"costly,":[9],"and":[10,15,56,63,118,123,174,235],"incompatible":[11],"with":[12,51,143,225,244],"agile":[13],"releases":[14],"OTA":[16],"updates.":[17],"Scripted":[18],"automation":[19],"only":[20],"partly":[21],"helps:":[22],"it":[23,212],"couples":[24],"test":[25],"logic":[26],"to":[27,61,250],"implementation,":[28],"yielding":[29],"brittle,":[30],"high-maintenance":[31],"suites.":[32],"Existing":[33],"LLM-driven":[34],"frameworks":[35],"mostly":[36],"target":[37],"web/mobile":[38],"apps,":[39],"using":[40,93],"single-":[41],"or":[42,48],"dual-agent":[43],"setups":[44],"that":[45,81,240],"overload":[46],"one":[47],"two":[49],"models":[50],"perception,":[52],"planning,":[53],"action":[54],"selection,":[55],"at":[58],"once,":[59],"prone":[60],"hallucinations":[62],"unproductive":[64],"exploration":[65],"loops":[66],"given":[67],"complexity.":[69],"We":[70,228],"present":[71],"ARIA":[72,114,139],"(Autonomous":[73],"Real-time":[74],"Infotainment":[75],"Assessment),":[76],"a":[77,94,104,130,144,190,214],"multi-agent":[78,178,199],"LLM":[79],"framework":[80],"autonomously":[82],"runs":[83,115,239],"end-to-end":[84],"tests":[85,183],"Android":[87,133],"systems":[89],"via":[90,237],"visual":[91,124,254],"interaction,":[92],"closed-loop":[95],"pipeline":[96],"of":[97,149,189,253],"four":[98],"specialized":[99],"agents":[100],"per":[101,126,233],"step":[102],"plus":[103],"report":[105,229],"stage.":[106],"From":[107],"single-sentence":[108],"scenarios":[109],"(path,":[110],"action,":[111],"expected":[112],"outcome),":[113],"the":[116,187,198,203,210],"interactions":[117],"produces":[119],"reports,":[120],"reproducible":[121],"scripts,":[122],"evidence":[125],"step.":[127],"Evaluated":[128],"manufacturer's":[131],"physical":[132],"system":[135,226],"across":[136],"30":[137],"scenarios,":[138],"completed":[140],"28":[141],"(93.3%)":[142],"verdict":[145],"(2":[146],"errored),":[147],"20":[148],"which":[150],"(71.4%)":[151],"matched":[152],"ground":[153],"truth.":[154],"It":[155],"caught":[156],"all":[157],"5":[158],"known":[159],"defects,":[160],"no":[161],"fault":[162,245],"passed":[163],"as":[164],"working;":[165],"its":[166],"8":[167],"false":[168],"positives":[169],"stem":[170],"from":[171],"navigation/image":[172],"limits":[173],"unsupported":[175],"gestures,":[176],"showing":[177],"LLMs":[179],"can":[180],"run":[181],"industrially":[184],"while":[185],"exposing":[186],"cost":[188],"low":[191],"false-positive":[192,217],"tolerance.":[193],"A":[194],"single-agent":[195],"baseline":[196],"confirms":[197],"design's":[200],"value:":[201],"first":[204],"pass,":[205],"before":[206],"stronger-model":[207],"revisitation":[208],"narrows":[209],"gap,":[211],"shows":[213],"far":[215],"higher":[216],"rate":[218],"(72.0%":[219],"vs.":[220],"52.6%),":[221],"conflating":[222],"navigational":[223],"difficulty":[224],"failure.":[227],"first-pass/post-revisitation":[230],"results,":[231],"token/call/cost":[232],"scenario,":[234],"show":[236],"repeated":[238],"stability":[241],"tracks":[242],"complexity,":[243],"detection":[246],"perfectly":[247],"consistent,":[248],"pointing":[249],"CI":[251],"integration":[252],"testing.":[255]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-10-06T00:00:00"}
