{"id":"https://openalex.org/W4408353845","doi":"https://doi.org/10.1109/icassp49660.2025.10890123","title":"IDE: A Multi-Agent-Driven Iterative Framework for Dynamic Evaluation of LLMs","display_name":"IDE: A Multi-Agent-Driven Iterative Framework for Dynamic Evaluation of LLMs","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353845","doi":"https://doi.org/10.1109/icassp49660.2025.10890123"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890123","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100784736","display_name":"Xin Tong","orcid":"https://orcid.org/0000-0001-5969-6389"},"institutions":[{"id":"https://openalex.org/I37448385","display_name":"China People's Public Security University","ror":"https://ror.org/05twya590","country_code":"CN","type":"education","lineage":["https://openalex.org/I37448385"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Tong","raw_affiliation_strings":["People’s Public Security University of China,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"People’s Public Security University of China,Beijing,China","institution_ids":["https://openalex.org/I37448385"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060620859","display_name":"Bo Jin","orcid":"https://orcid.org/0000-0001-5655-4545"},"institutions":[{"id":"https://openalex.org/I1302611135","display_name":"Ministry of Public Security of the People's Republic of China","ror":"https://ror.org/00bt9we26","country_code":"CN","type":"government","lineage":["https://openalex.org/I1302611135"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Jin","raw_affiliation_strings":["The Third Research Institute of the Ministry of Public Security of China,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Third Research Institute of the Ministry of Public Security of China,China","institution_ids":["https://openalex.org/I1302611135"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100639522","display_name":"Jingya Wang","orcid":"https://orcid.org/0000-0003-0441-3665"},"institutions":[{"id":"https://openalex.org/I37448385","display_name":"China People's Public Security University","ror":"https://ror.org/05twya590","country_code":"CN","type":"education","lineage":["https://openalex.org/I37448385"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingya Wang","raw_affiliation_strings":["People’s Public Security University of China,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"People’s Public Security University of China,Beijing,China","institution_ids":["https://openalex.org/I37448385"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043022304","display_name":"Xing Wu","orcid":"https://orcid.org/0000-0002-0514-3292"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenpeng Xing","raw_affiliation_strings":["Zhejiang University,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101603610","display_name":"Tian Xia","orcid":"https://orcid.org/0009-0001-2527-4257"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tian Xia","raw_affiliation_strings":["Renmin University of China,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China,Beijing,China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002157315","display_name":"Meng Han","orcid":"https://orcid.org/0000-0003-2868-6246"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Han","raw_affiliation_strings":["Zhejiang University,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10703","display_name":"Business Process Modeling and Analysis","score":0.911899983882904,"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"}},"topics":[{"id":"https://openalex.org/T10703","display_name":"Business Process Modeling and Analysis","score":0.911899983882904,"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/computer-science","display_name":"Computer science","score":0.6247398853302002}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6247398853302002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890123","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2971107062","https://openalex.org/W4285294723","https://openalex.org/W4384071683","https://openalex.org/W4385572482","https://openalex.org/W4393160461","https://openalex.org/W4401043273","https://openalex.org/W4402670101","https://openalex.org/W4402683839","https://openalex.org/W4404783199","https://openalex.org/W4409348063","https://openalex.org/W4412203333","https://openalex.org/W6762392948","https://openalex.org/W6764401283","https://openalex.org/W6782879696","https://openalex.org/W6803096969","https://openalex.org/W6810738896","https://openalex.org/W6846002521","https://openalex.org/W6852870998","https://openalex.org/W6852911403","https://openalex.org/W6854866820","https://openalex.org/W6856398428","https://openalex.org/W6857010465","https://openalex.org/W6857253204","https://openalex.org/W6857842733","https://openalex.org/W6858023062","https://openalex.org/W6858561328","https://openalex.org/W6861350592","https://openalex.org/W6861803797","https://openalex.org/W6862395929","https://openalex.org/W6862631004","https://openalex.org/W6869164663","https://openalex.org/W6869722496"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"With":[0],"the":[1,71,86,110,127],"widespread":[2],"use":[3],"of":[4,54,68,112,132],"large":[5],"language":[6,11],"models":[7,113],"(LLMs)":[8],"in":[9,57,114],"natural":[10],"processing,":[12],"traditional":[13,119],"evaluation":[14],"methods":[15],"based":[16],"on":[17],"static":[18],"datasets":[19],"have":[20],"become":[21],"inadequate":[22],"to":[23,48,118],"fully":[24],"capture":[25],"their":[26],"performance":[27],"and":[28,61,94,99,130],"generalization":[29],"capabilities.":[30],"To":[31],"address":[32],"this":[33],"challenge,":[34],"we":[35],"propose":[36],"an":[37],"Iterative":[38],"Dynamic":[39],"Evaluation":[40],"(IDE)":[41],"framework,":[42],"which":[43],"utilizes":[44],"a":[45,122],"multi-agent":[46],"system":[47],"systematically":[49],"evaluate":[50],"LLMs.":[51,133],"The":[52],"innovation":[53],"IDE":[55,106],"lies":[56],"its":[58],"iterative":[59,92],"enhancement":[60],"comparative":[62],"selection":[63,83],"mechanisms.":[64],"Through":[65],"successive":[66],"rounds":[67],"data":[69],"augmentation,":[70],"framework":[72],"emulates":[73],"evolutionary":[74],"processes":[75],"by":[76],"progressively":[77],"increasing":[78],"sample":[79],"complexity,":[80],"while":[81],"competitive":[82],"ensures":[84],"only":[85],"optimal":[87],"samples":[88],"are":[89],"retained.":[90],"This":[91],"optimization":[93],"filtering":[95],"produce":[96],"increasingly":[97],"challenging":[98],"diverse":[100],"datasets.":[101],"Experimental":[102],"results":[103],"demonstrate":[104],"that":[105],"more":[107,123],"effectively":[108],"exposes":[109],"limitations":[111],"complex":[115],"tasks":[116],"compared":[117],"methods,":[120],"providing":[121],"comprehensive":[124],"foundation":[125],"for":[126],"evaluation,":[128],"optimization,":[129],"application":[131]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}