{"id":"https://openalex.org/W7119224602","doi":"https://doi.org/10.34218/ijrcait_09_01_001","title":"A MODULAR BENCHMARKING FRAMEWORK FOR EVALUATING LLM-BASED AGENT APPLICATIONS","display_name":"A MODULAR BENCHMARKING FRAMEWORK FOR EVALUATING LLM-BASED AGENT APPLICATIONS","publication_year":2026,"publication_date":"2026-01-06","ids":{"openalex":"https://openalex.org/W7119224602","doi":"https://doi.org/10.34218/ijrcait_09_01_001"},"language":"en","primary_location":{"id":"doi:10.34218/ijrcait_09_01_001","doi":"https://doi.org/10.34218/ijrcait_09_01_001","is_oa":true,"landing_page_url":"https://doi.org/10.34218/ijrcait_09_01_001","pdf_url":"https://doi.org/10.34218/ijrcait_09_01_001","source":{"id":"https://openalex.org/S5406993224","display_name":"INTERNATIONAL JOURNAL OF RESEARCH IN COMPUTER APPLICATIONS AND INFORMATION TECHNOLOGY","issn_l":"2347-5099","issn":["2347-5099","2348-0009"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERNATIONAL JOURNAL OF RESEARCH IN COMPUTER APPLICATIONS AND INFORMATION TECHNOLOGY","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://doi.org/10.34218/ijrcait_09_01_001","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128783501","display_name":"Karthik Perikala","orcid":"https://orcid.org/0009-0004-2852-3089","observed_orcids":["https://orcid.org/0009-0004-2852-3089"]},"institutions":[{"id":"https://openalex.org/I2799939184","display_name":"Home Depot (United States)","ror":"https://ror.org/031603425","country_code":"US","type":"company","lineage":["https://openalex.org/I2799939184"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Karthik Perikala","raw_affiliation_strings":["Technology Leader , The Home Depot , United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technology Leader , The Home Depot , United States","institution_ids":["https://openalex.org/I2799939184"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5128783501"],"corresponding_institution_ids":["https://openalex.org/I2799939184"],"apc_list":null,"apc_paid":null,"fwci":26.9866,"has_fulltext":true,"cited_by_count":29,"citation_normalized_percentile":{"value":0.99576001,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"9","issue":"1","first_page":"1","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.27250000834465027,"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/T10028","display_name":"Topic Modeling","score":0.27250000834465027,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.18790000677108765,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.11509999632835388,"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":0.8669999837875366},{"id":"https://openalex.org/keywords/agent-evaluation","display_name":"agent evaluation","score":0.7850000262260437},{"id":"https://openalex.org/keywords/benchmarking-framework","display_name":"benchmarking framework","score":0.9490000009536743},{"id":"https://openalex.org/keywords/multi-turn-interaction","display_name":"multi-turn interaction","score":0.6629999876022339},{"id":"https://openalex.org/keywords/tool-invocation","display_name":"tool invocation","score":0.8939999938011169},{"id":"https://openalex.org/keywords/contextual-grounding","display_name":"contextual grounding","score":0.7799999713897705},{"id":"https://openalex.org/keywords/agent-safety","display_name":"agent safety","score":0.7390000224113464},{"id":"https://openalex.org/keywords/synthetic-benchmark","display_name":"synthetic benchmark","score":0.8420000076293945},{"id":"https://openalex.org/keywords/agent-architecture","display_name":"agent architecture","score":0.5740000009536743}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6080999970436096},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.558899998664856},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5497999787330627},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.4124999940395355},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.32429999113082886},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.29339998960494995},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C88482812","wikidata":"https://www.wikidata.org/wiki/Q6453666","display_name":"Modular programming","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.34218/ijrcait_09_01_001","doi":"https://doi.org/10.34218/ijrcait_09_01_001","is_oa":true,"landing_page_url":"https://doi.org/10.34218/ijrcait_09_01_001","pdf_url":"https://doi.org/10.34218/ijrcait_09_01_001","source":{"id":"https://openalex.org/S5406993224","display_name":"INTERNATIONAL JOURNAL OF RESEARCH IN COMPUTER APPLICATIONS AND INFORMATION TECHNOLOGY","issn_l":"2347-5099","issn":["2347-5099","2348-0009"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERNATIONAL JOURNAL OF RESEARCH IN COMPUTER APPLICATIONS AND INFORMATION TECHNOLOGY","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.34218/ijrcait_09_01_001","doi":"https://doi.org/10.34218/ijrcait_09_01_001","is_oa":true,"landing_page_url":"https://doi.org/10.34218/ijrcait_09_01_001","pdf_url":"https://doi.org/10.34218/ijrcait_09_01_001","source":{"id":"https://openalex.org/S5406993224","display_name":"INTERNATIONAL JOURNAL OF RESEARCH IN COMPUTER APPLICATIONS AND INFORMATION TECHNOLOGY","issn_l":"2347-5099","issn":["2347-5099","2348-0009"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERNATIONAL JOURNAL OF RESEARCH IN COMPUTER APPLICATIONS AND INFORMATION TECHNOLOGY","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7119224602.pdf","grobid_xml":"https://content.openalex.org/works/W7119224602.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W3153833878","https://openalex.org/W7133214447","https://openalex.org/W7133239970"],"related_works":["https://openalex.org/W7159956031","https://openalex.org/W7164744345","https://openalex.org/W4412877164","https://openalex.org/W7119474322","https://openalex.org/W4385682136","https://openalex.org/W7130534570","https://openalex.org/W4415289348","https://openalex.org/W7131893979","https://openalex.org/W4394710846","https://openalex.org/W7215082812"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Model":[2],"(LLM)":[3],"based":[4],"agent":[5,69,73,115,123,128],"applications":[6,70],"integrate":[7],"reasoning,":[8],"retrieval,":[9],"tool":[10,55],"invocation,":[11],"and":[12,57,75,83,87,102,104],"multi-turn":[13],"interaction":[14],"to":[15,45,110],"solve":[16],"complex":[17],"tasks.While":[18],"recent":[19],"advances":[20],"have":[21,32],"enabled":[22],"rapid":[23],"adoption":[24],"of":[25,114],"agentic":[26],"systems":[27],"in":[28],"production,":[29],"evaluation":[30],"methodologies":[31],"largely":[33],"remained":[34],"model-centric,":[35],"focusing":[36],"on":[37],"single-turn":[38],"accuracy":[39],"or":[40],"preference-based":[41],"scoring.These":[42],"approaches":[43],"fail":[44],"capture":[46],"agent-level":[47],"behavior":[48],"such":[49],"as":[50],"contextual":[51,98],"grounding,":[52,99],"conversational":[53,100],"fidelity,":[54],"effectiveness,":[56],"safety":[58],"characteristics.This":[59],"paper":[60],"introduces":[61],"a":[62,91],"modular":[63],"benchmarking":[64],"framework":[65,78],"for":[66],"evaluating":[67],"LLMbased":[68],"across":[71],"models,":[72,82],"architectures,":[74],"execution":[76,109],"strategies.The":[77],"decouples":[79],"datasets,":[80],"agents,":[81],"metrics,":[84],"enabling":[85],"systematic":[86],"reproducible":[88],"evaluation.We":[89],"define":[90],"multi-dimensional":[92],"metric":[93],"taxonomy":[94],"spanning":[95],"output":[96],"quality,":[97],"relevance,":[101],"safety,":[103],"combine":[105],"it":[106],"with":[107],"trace-aware":[108],"support":[111],"fine-grained":[112],"analysis":[113],"behavior.Using":[116],"representative":[117],"synthetic":[118],"benchmarks":[119],"derived":[120],"from":[121],"real-world":[122],"workloads,":[124],"we":[125],"demonstrate":[126],"that":[127],"design":[129],"choices-particularly":[130],"retrieval":[131],"Karthik":[132],"Perikala":[133]},"counts_by_year":[{"year":2026,"cited_by_count":19},{"year":2025,"cited_by_count":10}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-01-08T00:00:00"}
