{"id":"https://openalex.org/W4413755610","doi":"https://doi.org/10.1109/isvlsi65124.2025.11130343","title":"InsectAgent: Improving Insect Recognition through Dynamic Information Augmentation with Multimodal Large Language Models","display_name":"InsectAgent: Improving Insect Recognition through Dynamic Information Augmentation with Multimodal Large Language Models","publication_year":2025,"publication_date":"2025-07-06","ids":{"openalex":"https://openalex.org/W4413755610","doi":"https://doi.org/10.1109/isvlsi65124.2025.11130343"},"language":"en","primary_location":{"id":"doi:10.1109/isvlsi65124.2025.11130343","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isvlsi65124.2025.11130343","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)","raw_type":"proceedings-article"},"type":"article","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/A5011586053","display_name":"Shu Zhao","orcid":"https://orcid.org/0000-0003-4377-1086"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shu Zhao","raw_affiliation_strings":["The Pennsylvania State University,University Park,PA,USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University,University Park,PA,USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019520458","display_name":"Ajay Narayanan Sridhar","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ajay Narayanan Sridhar","raw_affiliation_strings":["The Pennsylvania State University,University Park,PA,USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University,University Park,PA,USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046541457","display_name":"Harland M. Patch","orcid":"https://orcid.org/0000-0002-8777-9090"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harland Patch","raw_affiliation_strings":["The Pennsylvania State University,University Park,PA,USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University,University Park,PA,USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101919131","display_name":"Vijaykrishnan Narayanan","orcid":"https://orcid.org/0000-0001-6266-6068"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijaykrishnan Narayanan","raw_affiliation_strings":["The Pennsylvania State University,University Park,PA,USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University,University Park,PA,USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5011586053"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13741954,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10895","display_name":"Species Distribution and Climate Change","score":0.9262999892234802,"subfield":{"id":"https://openalex.org/subfields/2302","display_name":"Ecological Modeling"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10895","display_name":"Species Distribution and Climate Change","score":0.9262999892234802,"subfield":{"id":"https://openalex.org/subfields/2302","display_name":"Ecological Modeling"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7653315663337708},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.44281062483787537},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4333896040916443},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4290022850036621},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4199331998825073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7653315663337708},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.44281062483787537},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4333896040916443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4290022850036621},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4199331998825073}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isvlsi65124.2025.11130343","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isvlsi65124.2025.11130343","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2117793557","https://openalex.org/W2564288310","https://openalex.org/W2907268124","https://openalex.org/W2970476707","https://openalex.org/W3128905120","https://openalex.org/W3203376123","https://openalex.org/W3212167230","https://openalex.org/W4294325784","https://openalex.org/W4303183997","https://openalex.org/W4313591142","https://openalex.org/W4385555651","https://openalex.org/W4391094120","https://openalex.org/W4392172801","https://openalex.org/W4402716330","https://openalex.org/W4403792205"],"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/W3204019825"],"abstract_inverted_index":{"Insect":[0],"recognition":[1,81],"remains":[2],"a":[3,74,96,110],"critical":[4],"challenge":[5],"for":[6,129,146,153,189],"biodiversity":[7],"monitoring,":[8],"conservation":[9],"efforts,":[10],"and":[11,125],"agricultural":[12],"sustainability.":[13],"Current":[14],"computer":[15],"vision":[16,33,68,97,178],"approaches":[17],"struggle":[18],"with":[19,103,163],"accurate":[20],"species":[21,41,51,101],"identification":[22,191],"due":[23],"to":[24,37,64],"subtle":[25],"morphological":[26],"differences.":[27],"Our":[28],"analysis":[29],"reveals":[30],"that":[31,58,78,173],"while":[32,149],"classifiers":[34,69],"frequently":[35],"fail":[36],"predict":[38],"the":[39,49,93,112],"correct":[40],"as":[42],"their":[43],"top":[44,53],"choice,":[45],"they":[46],"consistently":[47],"include":[48],"true":[50],"within":[52],"candidate":[54,100],"predictions.":[55],"This":[56,132],"indicates":[57],"expert":[59,122,167],"entomological":[60],"knowledge":[61,119,123],"is":[62],"required":[63],"resolve":[65],"ambiguities":[66],"when":[67],"fail.":[70],"We":[71],"present":[72],"InsectAgent,":[73],"novel":[75],"two-stage":[76],"framework":[77],"enhances":[79],"insect":[80,190],"through":[82],"dynamic":[83],"information":[84],"augmentation":[85],"using":[86],"Multimodal":[87],"Large":[88],"Language":[89],"Models":[90],"(MLLMs).":[91],"In":[92],"first":[94],"stage,":[95],"classifier":[98],"generates":[99],"predictions":[102,148],"confidence":[104,107],"scores.":[105],"When":[106],"falls":[108],"below":[109],"threshold,":[111],"second":[113],"stage":[114],"activates,":[115],"retrieving":[116],"relevant":[117],"taxonomic":[118],"from":[120],"an":[121,127,181],"base":[124],"invoking":[126],"MLLM":[128,134],"further":[130],"analysis.":[131],"conditional":[133],"invocation":[135],"strategy":[136],"significantly":[137,175],"reduces":[138],"computational":[139],"costs":[140],"by":[141],"avoiding":[142],"expensive":[143],"model":[144],"calls":[145],"high-confidence":[147],"ensuring":[150],"expertlevel":[151],"reasoning":[152,158],"ambiguous":[154],"cases.":[155],"The":[156],"information-augmented":[157],"process":[159],"combines":[160],"visual":[161],"cues":[162],"domain":[164],"expertise,":[165],"mirroring":[166],"entomologists\u2019":[168],"workflow.":[169],"Experimental":[170],"results":[171],"demonstrate":[172],"InsectAgent":[174],"outperforms":[176],"standalone":[177],"classifiers,":[179],"achieving":[180],"average":[182],"relative":[183],"improvement":[184],"of":[185],"14.24%":[186],"in":[187],"accuracy":[188],"tasks.":[192]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
