{"id":"https://openalex.org/W7155527102","doi":"https://doi.org/10.1007/s10462-026-11571-0","title":"From benchmarks to deployment: a comprehensive review of agentic AI evaluation","display_name":"From benchmarks to deployment: a comprehensive review of agentic AI evaluation","publication_year":2026,"publication_date":"2026-04-24","ids":{"openalex":"https://openalex.org/W7155527102","doi":"https://doi.org/10.1007/s10462-026-11571-0"},"language":"en","primary_location":{"id":"doi:10.1007/s10462-026-11571-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-026-11571-0","pdf_url":null,"source":{"id":"https://openalex.org/S122814990","display_name":"Artificial Intelligence Review","issn_l":"0269-2821","issn":["0269-2821","1573-7462"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence Review","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/s10462-026-11571-0","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078206383","display_name":"Tanzila Kehkashan","orcid":"https://orcid.org/0000-0002-6325-4409"},"institutions":[{"id":"https://openalex.org/I160968435","display_name":"University of Sargodha","ror":"https://ror.org/0086rpr26","country_code":"PK","type":"education","lineage":["https://openalex.org/I160968435"]},{"id":"https://openalex.org/I4576418","display_name":"University of Technology Malaysia","ror":"https://ror.org/026w31v75","country_code":"MY","type":"education","lineage":["https://openalex.org/I4576418"]}],"countries":["MY","PK"],"is_corresponding":false,"raw_author_name":"Tanzila Kehkashan","raw_affiliation_strings":["Faculty of Computing, Universiti Teknologi Malaysia, Johor Bahru, 81310, Malaysia","Faculty of Information Technology, University of Lahore, Sargodha, 40100, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computing, Universiti Teknologi Malaysia, Johor Bahru, 81310, Malaysia","institution_ids":["https://openalex.org/I4576418"]},{"raw_affiliation_string":"Faculty of Information Technology, University of Lahore, Sargodha, 40100, Pakistan","institution_ids":["https://openalex.org/I160968435"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103280329","display_name":"Muhammad Abdullah","orcid":"https://orcid.org/0000-0003-1576-4444"},"institutions":[{"id":"https://openalex.org/I160968435","display_name":"University of Sargodha","ror":"https://ror.org/0086rpr26","country_code":"PK","type":"education","lineage":["https://openalex.org/I160968435"]}],"countries":["PK"],"is_corresponding":true,"raw_author_name":"Muhammad Abdullah","raw_affiliation_strings":["Faculty of Information Technology, University of Lahore, Sargodha, 40100, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, University of Lahore, Sargodha, 40100, Pakistan","institution_ids":["https://openalex.org/I160968435"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134506153","display_name":"Ahmad Sami Al-Shamayleh","orcid":null},"institutions":[{"id":"https://openalex.org/I104941359","display_name":"Al-Ahliyya Amman University","ror":"https://ror.org/00xddhq60","country_code":"JO","type":"education","lineage":["https://openalex.org/I104941359"]}],"countries":["JO"],"is_corresponding":false,"raw_author_name":"Ahmad Sami Al-Shamayleh","raw_affiliation_strings":["Department of Data Science and Artificial Intelligence, Faculty of Information Technology, Al-Ahliyya Amman University, Amman, 19328, Jordan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Data Science and Artificial Intelligence, Faculty of Information Technology, Al-Ahliyya Amman University, Amman, 19328, Jordan","institution_ids":["https://openalex.org/I104941359"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044220134","display_name":"Nikola Ivkovi\u0107","orcid":"https://orcid.org/0000-0003-1730-2518"},"institutions":[{"id":"https://openalex.org/I181343428","display_name":"University of Zagreb","ror":"https://ror.org/00mv6sv71","country_code":"HR","type":"education","lineage":["https://openalex.org/I181343428"]},{"id":"https://openalex.org/I4210105025","display_name":"University North","ror":"https://ror.org/01afbkc02","country_code":"HR","type":"education","lineage":["https://openalex.org/I4210105025"]},{"id":"https://openalex.org/I4210148069","display_name":"Op\u0107a Bolnica Vara\u017edin","ror":"https://ror.org/056bmw021","country_code":"HR","type":"healthcare","lineage":["https://openalex.org/I4210148069"]}],"countries":["HR"],"is_corresponding":false,"raw_author_name":"Nikola Ivkovi\u0107","raw_affiliation_strings":["Faculty of Organization and Informatics, University of Zagreb, Vara\u017edin, 42000, Croatia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Organization and Informatics, University of Zagreb, Vara\u017edin, 42000, Croatia","institution_ids":["https://openalex.org/I181343428","https://openalex.org/I4210105025","https://openalex.org/I4210148069"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076231501","display_name":"Nor Azman Ismail","orcid":"https://orcid.org/0000-0003-1785-008X"},"institutions":[{"id":"https://openalex.org/I4576418","display_name":"University of Technology Malaysia","ror":"https://ror.org/026w31v75","country_code":"MY","type":"education","lineage":["https://openalex.org/I4576418"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Nor Azman Ismail","raw_affiliation_strings":["Faculty of Computing, Universiti Teknologi Malaysia, Johor Bahru, 81310, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computing, Universiti Teknologi Malaysia, Johor Bahru, 81310, Malaysia","institution_ids":["https://openalex.org/I4576418"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073424149","display_name":"Sharifah Sakinah Syed Ahmad","orcid":"https://orcid.org/0000-0002-3803-4578"},"institutions":[{"id":"https://openalex.org/I32589535","display_name":"Technical University of Malaysia Malacca","ror":"https://ror.org/01xb6rs26","country_code":"MY","type":"education","lineage":["https://openalex.org/I32589535"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Sharifah Sakinah Syed Ahmad","raw_affiliation_strings":["Faculty of Artificial Intelligence and Cyber Security, Universiti Teknikal Malaysia Melaka, 76100, Durian Tunggal, Melaka,, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Artificial Intelligence and Cyber Security, Universiti Teknikal Malaysia Melaka, 76100, Durian Tunggal, Melaka,, Malaysia","institution_ids":["https://openalex.org/I32589535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134513340","display_name":"Abdul Rehman","orcid":null},"institutions":[{"id":"https://openalex.org/I160968435","display_name":"University of Sargodha","ror":"https://ror.org/0086rpr26","country_code":"PK","type":"education","lineage":["https://openalex.org/I160968435"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Abdul Rehman","raw_affiliation_strings":["Faculty of Information Technology, University of Lahore, Sargodha, 40100, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, University of Lahore, Sargodha, 40100, Pakistan","institution_ids":["https://openalex.org/I160968435"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035884247","display_name":"Adnan Akhunzada","orcid":"https://orcid.org/0000-0001-8370-9290"},"institutions":[{"id":"https://openalex.org/I60342839","display_name":"Qatar University","ror":"https://ror.org/00yhnba62","country_code":"QA","type":"education","lineage":["https://openalex.org/I60342839"]}],"countries":["QA"],"is_corresponding":true,"raw_author_name":"Adnan Akhunzada","raw_affiliation_strings":["College of Computing & IT, Department of Data and Cybersecurity, University of Doha for Science and Technology, Doha, 24449, Qatar"],"raw_orcid":"https://orcid.org/0000-0001-8370-9290","affiliations":[{"raw_affiliation_string":"College of Computing & IT, Department of Data and Cybersecurity, University of Doha for Science and Technology, Doha, 24449, Qatar","institution_ids":["https://openalex.org/I60342839"]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5035884247","https://openalex.org/A5103280329"],"corresponding_institution_ids":["https://openalex.org/I160968435","https://openalex.org/I60342839"],"apc_list":{"value":3090,"currency":"USD","value_usd":3090},"apc_paid":{"value":3090,"currency":"USD","value_usd":3090},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.47766475,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"59","issue":"8","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.15449999272823334,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.15449999272823334,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.0763000026345253,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.06780000030994415,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6118999719619751},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.5569000244140625},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4810999929904938},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4629000127315521},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.3962000012397766},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.37700000405311584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7871999740600586},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6118999719619751},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5569000244140625},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4810999929904938},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.4666999876499176},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4629000127315521},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.3962000012397766},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.39489999413490295},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.37700000405311584},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3303000032901764},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.32679998874664307},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.32350000739097595},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3174000084400177},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2915000021457672},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26919999718666077},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.25940001010894775},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25679999589920044}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10462-026-11571-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-026-11571-0","pdf_url":null,"source":{"id":"https://openalex.org/S122814990","display_name":"Artificial Intelligence Review","issn_l":"0269-2821","issn":["0269-2821","1573-7462"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence Review","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10462-026-11571-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-026-11571-0","pdf_url":null,"source":{"id":"https://openalex.org/S122814990","display_name":"Artificial Intelligence Review","issn_l":"0269-2821","issn":["0269-2821","1573-7462"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence Review","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.4099358320236206,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W2889787757","https://openalex.org/W2908261578","https://openalex.org/W3034758614","https://openalex.org/W3106649810","https://openalex.org/W3123221944","https://openalex.org/W3166816823","https://openalex.org/W3167898434","https://openalex.org/W3168463823","https://openalex.org/W3183977027","https://openalex.org/W3197578004","https://openalex.org/W3205483668","https://openalex.org/W3216656735","https://openalex.org/W4220891756","https://openalex.org/W4287958635","https://openalex.org/W4294771618","https://openalex.org/W4300862292","https://openalex.org/W4308885736","https://openalex.org/W4312068198","https://openalex.org/W4312638675","https://openalex.org/W4319084034","https://openalex.org/W4365141796","https://openalex.org/W4375859932","https://openalex.org/W4382119054","https://openalex.org/W4385417895","https://openalex.org/W4385576721","https://openalex.org/W4389104713","https://openalex.org/W4389518608","https://openalex.org/W4389747832","https://openalex.org/W4391136507","https://openalex.org/W4391841626","https://openalex.org/W4391974543","https://openalex.org/W4392077089","https://openalex.org/W4392481868","https://openalex.org/W4393065402","https://openalex.org/W4394015350","https://openalex.org/W4394946189","https://openalex.org/W4395007752","https://openalex.org/W4399364148","https://openalex.org/W4399557965","https://openalex.org/W4399770676","https://openalex.org/W4400647264","https://openalex.org/W4401174036","https://openalex.org/W4402516191","https://openalex.org/W4402665833","https://openalex.org/W4403579163","https://openalex.org/W4404789754","https://openalex.org/W4406296273","https://openalex.org/W4406325768","https://openalex.org/W4406728221","https://openalex.org/W4406798194","https://openalex.org/W4408491642","https://openalex.org/W4411856464","https://openalex.org/W4412670936","https://openalex.org/W4412877164","https://openalex.org/W4412888351","https://openalex.org/W4414023998","https://openalex.org/W4414218637","https://openalex.org/W4416178266","https://openalex.org/W4416578578","https://openalex.org/W7133534962","https://openalex.org/W7162022812"],"related_works":[],"abstract_inverted_index":{"This":[0,170],"review":[1,171],"systematically":[2,141],"examines":[3],"evaluation":[4,26,122,177,181,205,226,238,259],"methodologies":[5,58],"for":[6],"agentic":[7,10,253],"AI":[8,11,254],"systems,":[9],"systems":[12],"capable":[13],"of":[14,190,195,203],"multi-step":[15],"planning,":[16],"tool":[17],"usage,":[18],"and":[19,35,74,99,106,147,159,197,201,228],"environmental":[20],"interaction":[21],"across":[22],"diverse":[23],"domains.":[24],"Current":[25],"practices":[27],"exhibit":[28],"a":[29,173],"critical":[30,65],"disconnect":[31],"between":[32],"benchmark":[33],"performance":[34],"deployment":[36,64],"viability,":[37],"where":[38],"agents":[39],"achieving":[40],"high":[41],"scores":[42],"on":[43,232,257],"standardized":[44],"benchmarks":[45,83,163,212],"frequently":[46],"fail":[47],"in":[48,56,223],"real":[49],"world":[50],"applications":[51],"due":[52],"to":[53,247],"fundamental":[54],"inadequacies":[55],"assessment":[57,267],"that":[59,121,237,269],"prioritize":[60],"task":[61],"completion":[62],"over":[63],"dimensions":[66],"such":[67],"as":[68,113],"cost":[69,184,198],"efficiency,":[70,158],"safety":[71,160,167,214],"compliance,":[72],"maintainability,":[73],"workflow":[75],"integration.":[76],"We":[77,135],"critically":[78],"analyze":[79],"15":[80],"major":[81],"agent":[82,133],"including":[84,193],"AgentBench,":[85],"WebArena,":[86],"SWE-bench,":[87],"PaperBench,":[88],"MLGym,":[89],"BrowserGym,":[90],"HumanEval,":[91],"MBPP,":[92],"GAIA,":[93],"ToolBench,":[94],"Terminal-Bench,":[95],"Mind2Web,":[96],"ALFWorld,":[97],"BabyAI,":[98],"HotPotQA,":[100],"examining":[101],"their":[102,224],"methodologies,":[103],"metrics,":[104],"datasets,":[105],"application":[107],"domains":[108],"with":[109,207],"software":[110],"development":[111],"serving":[112],"our":[114],"primary":[115,129,225,245],"case":[116],"study.":[117],"Our":[118],"analysis":[119],"reveals":[120],"methodology":[123],"not":[124,240],"model":[125,241],"capability":[126],"constitutes":[127],"the":[128,244],"bottleneck":[130,246],"limiting":[131],"reliable":[132,248],"deployment.":[134,249],"demonstrate":[136],"how":[137],"test":[138],"passing":[139],"metrics":[140,153,222,263],"ignore":[142],"code":[143],"quality,":[144],"security":[145,165,216],"vulnerabilities,":[146],"integration":[148],"complexity":[149],"while":[150],"binary":[151,233,262],"success":[152,234],"obscure":[154],"planning":[155],"coherence,":[156],"resource":[157],"violations":[161],"(0/15":[162],"integrate":[164,213],"or":[166,215],"into":[168,217],"scoring.":[169],"provides":[172],"cross-domain":[174],"taxonomy":[175],"exposing":[176],"inadequacies,":[178],"trajectory":[179],"level":[180],"frameworks":[182,268],"addressing":[183],"reproducibility":[185],"validity":[186],"trade-offs,":[187],"systematic":[188],"identification":[189],"metric":[191],"insufficiencies":[192],"absence":[194],"safety-aware":[196],"aware":[199],"scoring,":[200,218],"synthesis":[202],"emerging":[204],"paradigms":[206],"adoption":[208],"barriers.":[209],"Quantitatively,":[210],"0/15":[211,219],"include":[220],"cost-efficiency":[221],"protocol,":[227],"13/15":[229],"rely":[230],"exclusively":[231],"measures":[235],"confirming":[236],"methodology,":[239],"capability,":[242],"is":[243],"Progress":[250],"toward":[251,264],"trustworthy":[252],"fundamentally":[255],"depends":[256],"evolving":[258],"infrastructure":[260],"beyond":[261],"comprehensive,":[265],"multidimensional":[266],"capture":[270],"these":[271],"deployment-essential":[272],"dimensions.":[273]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2026-04-25T00:00:00"}
