{"id":"https://openalex.org/W7225458917","doi":"https://doi.org/10.5281/zenodo.24042076","title":"AgentTest: An Intelligent Platform for Testing and Evaluating AI Agents Using Execution-Level Analysis","display_name":"AgentTest: An Intelligent Platform for Testing and Evaluating AI Agents Using Execution-Level Analysis","publication_year":2026,"publication_date":"2026-11-07","ids":{"openalex":"https://openalex.org/W7225458917","doi":"https://doi.org/10.5281/zenodo.24042076"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24042076","doi":"https://doi.org/10.5281/zenodo.24042076","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24042076","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"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":"JournalArticle"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.24042076","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5161238096","display_name":"Rounak Mishra","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mishra, Rounak","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161207551","display_name":"Nitin Aryan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aryan, Nitin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161200637","display_name":"Aashish Kumar","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kumar, Aashish","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161219276","display_name":"Dhananjay Shukla","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shukla, Dhananjay","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5010053170","display_name":"Yusuf Perwej","orcid":"https://orcid.org/0000-0001-8377-5829","observed_orcids":["https://orcid.org/0000-0001-8377-5829"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Perwej, Yusuf","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9932000041007996,"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":0.9932000041007996,"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":0.0019000000320374966,"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"}},{"id":"https://openalex.org/T13904","display_name":"Artificial Intelligence Applications","score":0.0017000000225380063,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.8149999976158142},{"id":"https://openalex.org/keywords/hallucination-detection","display_name":"hallucination detection","score":0.7710000276565552},{"id":"https://openalex.org/keywords/safety-compliance","display_name":"safety compliance","score":0.5820000171661377},{"id":"https://openalex.org/keywords/automatic-test-generation","display_name":"automated test generation","score":0.6859999895095825},{"id":"https://openalex.org/keywords/regression-testing","display_name":"regression testing","score":0.972000002861023},{"id":"https://openalex.org/keywords/production-monitoring","display_name":"production monitoring","score":0.8169999718666077}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7968999743461609},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7128999829292297},{"id":"https://openalex.org/C4438859","wikidata":"https://www.wikidata.org/wiki/Q186117","display_name":"Timeline","level":2,"score":0.6955999732017517},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.5370000004768372},{"id":"https://openalex.org/C161821725","wikidata":"https://www.wikidata.org/wiki/Q917415","display_name":"Regression testing","level":5,"score":0.5041000247001648},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4823000133037567},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45170000195503235},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.3862999975681305},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.37369999289512634},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C128942645","wikidata":"https://www.wikidata.org/wiki/Q1568346","display_name":"Test case","level":3,"score":0.31859999895095825},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C11066294","wikidata":"https://www.wikidata.org/wiki/Q1518244","display_name":"Business rule","level":4,"score":0.2955999970436096},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2915000021457672},{"id":"https://openalex.org/C85345410","wikidata":"https://www.wikidata.org/wiki/Q851587","display_name":"Business process","level":3,"score":0.2872999906539917},{"id":"https://openalex.org/C144559511","wikidata":"https://www.wikidata.org/wiki/Q2986279","display_name":"Principal (computer security)","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2581000030040741},{"id":"https://openalex.org/C4924752","wikidata":"https://www.wikidata.org/wiki/Q184148","display_name":"Plug-in","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24042076","doi":"https://doi.org/10.5281/zenodo.24042076","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24042076","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"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":"JournalArticle"},{"id":"doi:10.5281/zenodo.24042077","doi":"https://doi.org/10.5281/zenodo.24042077","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24042077","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"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":"JournalArticle"}],"best_oa_location":{"id":"doi:10.5281/zenodo.24042076","doi":"https://doi.org/10.5281/zenodo.24042076","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24042076","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"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":"JournalArticle"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7155074625","https://openalex.org/W7168263593","https://openalex.org/W7221041534","https://openalex.org/W7223575517","https://openalex.org/W7223130808","https://openalex.org/W7212078847","https://openalex.org/W7215040486","https://openalex.org/W7204604445","https://openalex.org/W7202186449","https://openalex.org/W4408893253"],"abstract_inverted_index":{"Agents":[0],"built":[1],"on":[2,27,47,127,173],"large":[3],"language":[4],"models":[5],"(LLMs)":[6],"are":[7,143],"now":[8],"trusted":[9],"with":[10,160],"tasks":[11],"such":[12,75],"as":[13],"order":[14],"handling,":[15],"refunds":[16],"and":[17,25,78,120,123,135,138,152,166,170,175,191,201],"customer":[18],"support":[19],"because":[20],"they":[21],"can":[22],"call":[23],"tools":[24],"APIs":[26],"behalf":[28],"of":[29,89],"an":[30,106,149],"organisation.":[31],"Their":[32],"behaviour,":[33],"however,":[34],"is":[35,158,171],"difficult":[36],"to":[37,186],"predict.":[38],"An":[39],"agent":[40,92,107],"may":[41],"select":[42],"the":[43,71,87,125,167],"wrong":[44,48],"tool,":[45],"act":[46],"data,":[49],"break":[50],"a":[51,59,90,94,102,146,153,183,193],"business":[52,96],"rule,":[53],"hallucinate,":[54],"or":[55],"claim":[56],"success":[57],"after":[58],"failed":[60],"operation,":[61],"while":[62],"its":[63,112],"final":[64,121],"reply":[65,72],"still":[66],"reads":[67],"convincingly.":[68],"Testing":[69],"only":[70],"therefore":[73],"leaves":[74],"faults":[76],"hidden,":[77],"existing":[79],"benchmarks":[80],"mostly":[81],"measure":[82],"general":[83],"capability":[84],"rather":[85],"than":[86],"correctness":[88],"particular":[91,95],"inside":[93],"workflow.":[97],"This":[98],"paper":[99],"presents":[100],"AgentTest,":[101],"platform":[103,157],"that":[104],"executes":[105],"against":[108],"realistic":[109],"scenarios,":[110],"records":[111],"complete":[113],"execution":[114,150],"(input,":[115],"tool":[116,118],"calls,":[117],"results":[119],"response),":[122],"judges":[124],"run":[126],"four":[128],"criteria:":[129],"task":[130],"success,":[131],"action":[132],"correctness,":[133],"policy":[134],"safety":[136],"compliance,":[137],"final-response":[139],"accuracy.":[140],"Failed":[141],"runs":[142],"explained":[144],"through":[145],"likely-cause":[147],"analysis,":[148],"timeline":[151],"consolidated":[154],"report.":[155],"The":[156,178],"designed":[159],"React.js,":[161],"Node.js,":[162],"Express.js,":[163],"MongoDB":[164],"Atlas":[165],"OpenAI/Gemini":[168],"APIs,":[169],"illustrated":[172],"order-management":[174],"refund":[176],"agents.":[177],"proposed":[179],"approach":[180],"gives":[181],"developers":[182],"dependable":[184],"way":[185],"verify":[187],"agents":[188],"before":[189],"deployment":[190],"forms":[192],"base":[194],"for":[195],"automatic":[196],"test":[197],"generation,":[198],"regression":[199],"testing":[200],"production":[202],"monitoring.":[203]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-11-08T00:00:00"}