{"id":"https://openalex.org/W4415068065","doi":"https://doi.org/10.48550/arxiv.2506.11102","title":"Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey","display_name":"Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey","publication_year":2025,"publication_date":"2025-06-06","ids":{"openalex":"https://openalex.org/W4415068065","doi":"https://doi.org/10.48550/arxiv.2506.11102"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2506.11102","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.11102","pdf_url":"https://arxiv.org/pdf/2506.11102","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.11102","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101499969","display_name":"Jiachen Zhu","orcid":"https://orcid.org/0000-0002-7092-4722","observed_orcids":["https://orcid.org/0000-0002-7092-4722"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhu, Jiachen","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034417837","display_name":"Menghui Zhu","orcid":"https://orcid.org/0000-0002-8567-2185","observed_orcids":["https://orcid.org/0000-0002-8567-2185"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhu, Menghui","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043374188","display_name":"Renting Rui","orcid":"https://orcid.org/0009-0000-7031-5786","observed_orcids":["https://orcid.org/0009-0000-7031-5786"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui, Renting","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100963648","display_name":"Rong Shan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan, Rong","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106266875","display_name":"Congmin Zheng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng, Congmin","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100427434","display_name":"Bo Chen","orcid":"https://orcid.org/0000-0003-3750-2533","observed_orcids":["https://orcid.org/0000-0003-3750-2533"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Bo","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013513956","display_name":"Yunjia Xi","orcid":"https://orcid.org/0000-0001-6883-881X","observed_orcids":["https://orcid.org/0000-0001-6883-881X"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi, Yunjia","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036057873","display_name":"Jianghao Lin","orcid":"https://orcid.org/0000-0002-8953-3203","observed_orcids":["https://orcid.org/0000-0002-8953-3203"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin, Jianghao","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101500385","display_name":"Weiwen Liu","orcid":"https://orcid.org/0000-0002-9148-3997","observed_orcids":["https://orcid.org/0000-0002-9148-3997"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Weiwen","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054330014","display_name":"Ruiming Tang","orcid":"https://orcid.org/0000-0002-9224-2431","observed_orcids":["https://orcid.org/0000-0002-9224-2431"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tang, Ruiming","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064534815","display_name":"Yong Yu","orcid":"https://orcid.org/0000-0003-4457-2820","observed_orcids":["https://orcid.org/0000-0003-4457-2820"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu, Yong","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090720315","display_name":"Weinan Zhang","orcid":"https://orcid.org/0000-0002-0127-2425","observed_orcids":["https://orcid.org/0000-0002-0127-2425"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Weinan","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"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/T12031","display_name":"Speech and dialogue systems","score":0.4771000146865845,"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/T12031","display_name":"Speech and dialogue systems","score":0.4771000146865845,"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/T13904","display_name":"Artificial Intelligence Applications","score":0.1818999946117401,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.1145000010728836,"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/large-language-models","display_name":"large language models","score":0.7889999747276306},{"id":"https://openalex.org/keywords/ai-agents","display_name":"AI agents","score":0.9509999752044678},{"id":"https://openalex.org/keywords/llm-chatbots","display_name":"LLM chatbots","score":0.8820000290870667},{"id":"https://openalex.org/keywords/ai-agent-evaluation","display_name":"AI agent evaluation","score":0.8859999775886536},{"id":"https://openalex.org/keywords/evaluation-benchmark","display_name":"evaluation benchmark","score":0.9520000219345093},{"id":"https://openalex.org/keywords/benchmark-selection","display_name":"benchmark selection","score":0.7519999742507935},{"id":"https://openalex.org/keywords/dynamic-feedback","display_name":"dynamic feedback","score":0.902999997138977},{"id":"https://openalex.org/keywords/multisensory-perception","display_name":"multisensory perception","score":0.9679999947547913},{"id":"https://openalex.org/keywords/complex-environments","display_name":"complex environments","score":0.703000009059906},{"id":"https://openalex.org/keywords/evaluation-indicators","display_name":"evaluation metrics","score":0.6769999861717224},{"id":"https://openalex.org/keywords/evolutionary-perspective","display_name":"evolutionary perspective","score":0.5450000166893005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6046000123023987},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.6025999784469604},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.48170000314712524},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.4659999907016754},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4578000009059906},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.4242999851703644},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4081000089645386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3919999897480011},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3790000081062317},{"id":"https://openalex.org/C55587333","wikidata":"https://www.wikidata.org/wiki/Q1133029","display_name":"Engineering ethics","level":1,"score":0.2840999960899353},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.27230000495910645}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2506.11102","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.11102","pdf_url":"https://arxiv.org/pdf/2506.11102","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.11102","doi":"https://doi.org/10.48550/arxiv.2506.11102","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.11102","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.11102","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.11102","pdf_url":"https://arxiv.org/pdf/2506.11102","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415068065.pdf","grobid_xml":"https://content.openalex.org/works/W4415068065.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415289348","https://openalex.org/W7128518302","https://openalex.org/W7131893979","https://openalex.org/W4415995818","https://openalex.org/W7161065936","https://openalex.org/W4412877164","https://openalex.org/W4415797149","https://openalex.org/W7212315247","https://openalex.org/W4416982487","https://openalex.org/W4414815214"],"abstract_inverted_index":{"The":[0,29],"advent":[1],"of":[2,25,78,179],"large":[3],"language":[4,17],"models":[5],"(LLMs),":[6],"such":[7],"as":[8],"GPT,":[9],"Gemini,":[10],"and":[11,57,113,128,152,164,177],"DeepSeek,":[12],"has":[13],"significantly":[14],"advanced":[15,38,114,130],"natural":[16],"processing,":[18],"giving":[19],"rise":[20],"to":[21,36,61],"sophisticated":[22],"chatbots":[23,35,56,100],"capable":[24],"diverse":[26],"language-related":[27],"tasks.":[28],"transition":[30],"from":[31,98],"these":[32],"traditional":[33],"LLM":[34,55,99],"more":[37],"AI":[39,58,96,182],"agents":[40,97],"represents":[41],"a":[42,75,89],"pivotal":[43],"evolutionary":[44,85],"step.":[45],"However,":[46],"existing":[47,119],"evaluation":[48,80,120,139,155],"frameworks":[49],"often":[50],"blur":[51],"the":[52,174],"distinctions":[53],"between":[54],"agents,":[59],"leading":[60],"confusion":[62],"among":[63],"researchers":[64],"selecting":[65],"appropriate":[66],"benchmarks.":[67],"To":[68],"bridge":[69],"this":[70,72,190],"gap,":[71],"paper":[73],"introduces":[74],"systematic":[76],"analysis":[77],"current":[79,150],"approaches,":[81],"grounded":[82],"in":[83,143,181,189],"an":[84],"perspective.":[86],"We":[87],"provide":[88],"detailed":[90],"analytical":[91],"framework":[92],"that":[93],"clearly":[94],"differentiates":[95],"along":[101],"five":[102],"key":[103],"aspects:":[104],"complex":[105],"environment,":[106,161],"multi-source":[107],"instructor,":[108],"dynamic":[109],"feedback,":[110],"multi-modal":[111],"perception,":[112],"capability.":[115],"Further,":[116],"we":[117,136,148],"categorize":[118],"benchmarks":[121,180],"based":[122],"on":[123],"external":[124],"environments":[125],"driving":[126],"forces,":[127],"resulting":[129],"internal":[131],"capabilities.":[132],"For":[133],"each":[134],"category,":[135],"delineate":[137],"relevant":[138],"attributes,":[140],"presented":[141],"comprehensively":[142],"practical":[144],"reference":[145],"tables.":[146],"Finally,":[147],"synthesize":[149],"trends":[151],"outline":[153],"future":[154],"methodologies":[156],"through":[157],"four":[158],"critical":[159],"lenses:":[160],"agent,":[162],"evaluator,":[163],"metrics.":[165],"Our":[166],"findings":[167],"offer":[168],"actionable":[169],"guidance":[170],"for":[171],"researchers,":[172],"facilitating":[173],"informed":[175],"selection":[176],"application":[178],"agent":[183],"evaluation,":[184],"thus":[185],"fostering":[186],"continued":[187],"advancement":[188],"rapidly":[191],"evolving":[192],"research":[193],"domain.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":5}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2025-10-11T00:00:00"}
