{"id":"https://openalex.org/W7155372963","doi":"https://doi.org/10.1145/3777884.3797017","title":"An Evaluation Study of Generative AI Systems: Framework-Aware Performance Under Real-World Constraints","display_name":"An Evaluation Study of Generative AI Systems: Framework-Aware Performance Under Real-World Constraints","publication_year":2026,"publication_date":"2026-04-23","ids":{"openalex":"https://openalex.org/W7155372963","doi":"https://doi.org/10.1145/3777884.3797017"},"language":null,"primary_location":{"id":"doi:10.1145/3777884.3797017","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3777884.3797017","pdf_url":null,"source":null,"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 17th ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3777884.3797017","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5118970099","display_name":"Abed Matinpour","orcid":null},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Abed Matinpour","raw_affiliation_strings":["Electrical Engineering and Computer Science Department, York University, Toronto, Canada"],"raw_orcid":"https://orcid.org/0009-0003-4634-6795","affiliations":[{"raw_affiliation_string":"Electrical Engineering and Computer Science Department, York University, Toronto, Canada","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023376863","display_name":"Farhoud Jafari Kaleibar","orcid":"https://orcid.org/0000-0001-9726-5408"},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Farhoud Jafari Kaleibar","raw_affiliation_strings":["Electrical Engineering and Computer Science Department, York University, Toronto, Canada"],"raw_orcid":"https://orcid.org/0000-0001-9726-5408","affiliations":[{"raw_affiliation_string":"Electrical Engineering and Computer Science Department, York University, Toronto, Canada","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123804045","display_name":"Sara Fehresti","orcid":null},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sara Fehresti","raw_affiliation_strings":["The School of Information Technology, York University, Toronto, Canada"],"raw_orcid":"https://orcid.org/0000-0003-3580-161X","affiliations":[{"raw_affiliation_string":"The School of Information Technology, York University, Toronto, Canada","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134414783","display_name":"Shaylin Ziaei","orcid":"https://orcid.org/0009-0002-2591-213X"},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Shaylin Ziaei","raw_affiliation_strings":["Electrical Engineering and Computer Science Department, York University, Toronto, Canada"],"raw_orcid":"https://orcid.org/0009-0002-2591-213X","affiliations":[{"raw_affiliation_string":"Electrical Engineering and Computer Science Department, York University, Toronto, Canada","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051000791","display_name":"Marin Litoiu","orcid":"https://orcid.org/0000-0003-0383-920X"},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Marin Litoiu","raw_affiliation_strings":["Electrical Engineering and Computer Science Department, York University, Toronto, Canada"],"raw_orcid":"https://orcid.org/0000-0003-0383-920X","affiliations":[{"raw_affiliation_string":"Electrical Engineering and Computer Science Department, York University, Toronto, Canada","institution_ids":["https://openalex.org/I192455969"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5118970099"],"corresponding_institution_ids":["https://openalex.org/I192455969"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93538294,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"406","last_page":"418"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.4749999940395355,"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"}},"topics":[{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.4749999940395355,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.05700000002980232,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.05429999902844429,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/orchestration","display_name":"Orchestration","score":0.6614000201225281},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6384999752044678},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6079999804496765},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5390999913215637},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5177000164985657},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.40450000762939453},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.4043999910354614},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3855000138282776}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7961000204086304},{"id":"https://openalex.org/C199168358","wikidata":"https://www.wikidata.org/wiki/Q3367000","display_name":"Orchestration","level":3,"score":0.6614000201225281},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6384999752044678},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6079999804496765},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5390999913215637},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.52920001745224},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5177000164985657},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.40450000762939453},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4043999910354614},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3855000138282776},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.3659000098705292},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36039999127388},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.3596999943256378},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.35359999537467957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33809998631477356},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3328000009059906},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.26820001006126404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3777884.3797017","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3777884.3797017","pdf_url":null,"source":null,"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 17th ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3777884.3797017","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3777884.3797017","pdf_url":null,"source":null,"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 17th ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5671790242195129,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W4387701050","https://openalex.org/W4412378850","https://openalex.org/W7133209743"],"related_works":[],"abstract_inverted_index":{"The":[0],"widespread":[1],"adoption":[2],"of":[3,19,113,213],"Large":[4],"Language":[5],"Models":[6],"(LLMs)":[7],"in":[8,216,229],"enterprise":[9],"applications":[10],"has":[11],"created":[12],"a":[13],"critical":[14],"need":[15],"for":[16,168,223],"systematic":[17],"evaluation":[18,39],"Generative":[20],"AI":[21],"Systems":[22],"(GenAIS)":[23],"that":[24,105],"integrate":[25],"orchestration":[26,49,214],"frameworks,":[27],"foundation":[28,53,67],"models,":[29,54],"and":[30,55,75,84,95,138,155,161,180,203,219,227],"deployment":[31,56],"optimizations.":[32],"This":[33],"paper":[34],"presents":[35],"the":[36,45,210],"first":[37],"comprehensive":[38],"study":[40,63],"specifically":[41],"designed":[42],"to":[43],"evaluate":[44],"performance":[46,111,218],"trade-offs":[47,118],"between":[48],"frameworks":[50],"(LangChain,":[51],"LlamaIndex),":[52],"constraints":[57],"across":[58,69,120,151],"multiple":[59],"application":[60],"domains.":[61],"Our":[62],"systematically":[64],"evaluates":[65],"eight":[66],"models":[68,154],"question-answering":[70],"with":[71,116],"Retrieval-Augmented":[72],"Generation":[73],"(RAG)":[74],"mathematical":[76,145],"reasoning":[77],"tasks,":[78,146],"measuring":[79],"latency,":[80,131],"accuracy,":[81,226],"resource":[82,163],"utilization,":[83],"power":[85],"consumption":[86],"under":[87],"various":[88],"optimization":[89],"strategies":[90],"including":[91],"adaptive":[92],"context":[93,173],"windowing":[94,174],"concurrent":[96],"request":[97],"processing.":[98],"Through":[99],"extensive":[100],"empirical":[101,221],"analysis,":[102],"we":[103],"demonstrate":[104],"framework":[106],"selection":[107],"significantly":[108],"impacts":[109],"system":[110],"independent":[112],"model":[114],"choice,":[115],"task-specific":[117],"emerging":[119],"workload":[121],"types.":[122],"For":[123,143],"retrieval-heavy":[124],"RAG":[125],"workloads,":[126],"LlamaIndex":[127],"delivers":[128],"3-15%":[129],"lower":[130,134],"around":[132],"60%":[133],"peak":[135],"memory":[136],"usage,":[137],"2-4%":[139],"more":[140,157],"energy":[141],"consumption.":[142],"reasoning-intensive":[144],"Langchain":[147],"achieves":[148],"higher":[149],"accuracy":[150],"all":[152],"tested":[153],"provides":[156],"predictable":[158],"latency":[159,202],"profiles":[160],"reasonable":[162],"consumption,":[164],"making":[165],"it":[166],"preferable":[167],"strict":[169],"SLA":[170,205],"environments.":[171],"Adaptive":[172],"does":[175],"not":[176],"yield":[177],"uniform":[178],"gains":[179],"offers":[181],"only":[182],"modest,":[183],"model-dependent":[184],"improvements":[185],"over":[186],"fixed":[187],"policies,":[188],"whereas":[189],"increasing":[190],"concurrency":[191],"improves":[192],"aggregate":[193],"throughput":[194],"but,":[195],"beyond":[196],"moderate":[197],"loads,":[198],"consistently":[199],"inflates":[200],"tail":[201],"degrades":[204],"predictability.":[206],"These":[207],"findings":[208],"underscore":[209],"decisive":[211],"role":[212],"design":[215],"GenAIS":[217],"provide":[220],"guidance":[222],"balancing":[224],"efficiency,":[225],"scalability":[228],"real-world":[230],"deployments.":[231]},"counts_by_year":[],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2026-04-24T00:00:00"}