{"id":"https://openalex.org/W7126117765","doi":"https://doi.org/10.1109/bibm66473.2025.11356640","title":"A Comprehensive Benchmark of Tool-Augmented Large Language Models for Biomedical Knowledge Retrieval and Integration","display_name":"A Comprehensive Benchmark of Tool-Augmented Large Language Models for Biomedical Knowledge Retrieval and Integration","publication_year":2025,"publication_date":"2025-12-15","ids":{"openalex":"https://openalex.org/W7126117765","doi":"https://doi.org/10.1109/bibm66473.2025.11356640"},"language":null,"primary_location":{"id":"doi:10.1109/bibm66473.2025.11356640","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","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/A5047872287","display_name":"Van Truong","orcid":"https://orcid.org/0000-0002-5485-1818"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Van Q. Truong","raw_affiliation_strings":["University of Pennsylvania,Genomics & Computational Biology PhD Program,USA"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania,Genomics & Computational Biology PhD Program,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124169575","display_name":"Shu Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210163477","display_name":"Institute for Medical Informatics and Biostatistics","ror":"https://ror.org/04e79zk25","country_code":"CH","type":"facility","lineage":["https://openalex.org/I4210163477"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Shu Yang","raw_affiliation_strings":["University of Pennsylvania,Department of Biostatistics, Epidemiology & Informatics,USA"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania,Department of Biostatistics, Epidemiology & Informatics,USA","institution_ids":["https://openalex.org/I4210163477"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080198746","display_name":"Li Shen","orcid":"https://orcid.org/0000-0001-6520-1418"},"institutions":[{"id":"https://openalex.org/I4210163477","display_name":"Institute for Medical Informatics and Biostatistics","ror":"https://ror.org/04e79zk25","country_code":"CH","type":"facility","lineage":["https://openalex.org/I4210163477"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Li Shen","raw_affiliation_strings":["University of Pennsylvania,Department of Biostatistics, Epidemiology & Informatics,USA"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania,Department of Biostatistics, Epidemiology & Informatics,USA","institution_ids":["https://openalex.org/I4210163477"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124239881","display_name":"Marylyn D. Ritchie","orcid":null},"institutions":[{"id":"https://openalex.org/I153297377","display_name":"Medical University of South Carolina","ror":"https://ror.org/012jban78","country_code":"US","type":"education","lineage":["https://openalex.org/I153297377"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marylyn D. Ritchie","raw_affiliation_strings":["Medical University of South Carolina,Division of Biomedical Informatics & AI,USA"],"affiliations":[{"raw_affiliation_string":"Medical University of South Carolina,Division of Biomedical Informatics & AI,USA","institution_ids":["https://openalex.org/I153297377"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5047872287"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.65733952,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6599","last_page":"6606"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.310699999332428,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.310699999332428,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11642","display_name":"Genomics and Rare Diseases","score":0.15600000321865082,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.10029999911785126,"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/benchmark","display_name":"Benchmark (surveying)","score":0.5493999719619751},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.5335999727249146},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5299999713897705},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.36649999022483826},{"id":"https://openalex.org/keywords/controlled-vocabulary","display_name":"Controlled vocabulary","score":0.32190001010894775},{"id":"https://openalex.org/keywords/data-curation","display_name":"Data curation","score":0.2928999960422516}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7494999766349792},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5493999719619751},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.5335999727249146},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5299999713897705},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.46950000524520874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42570000886917114},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38199999928474426},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.36649999022483826},{"id":"https://openalex.org/C110615152","wikidata":"https://www.wikidata.org/wiki/Q1469824","display_name":"Controlled vocabulary","level":2,"score":0.32190001010894775},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.27469998598098755},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26350000500679016}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm66473.2025.11356640","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2254417325","display_name":null,"funder_award_id":"U01AG066833,P30AG073105,U01AG066833,UL1TR001878,P30AG073105","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2916749909","https://openalex.org/W2988303005","https://openalex.org/W3095580221","https://openalex.org/W3134303686","https://openalex.org/W4223591189","https://openalex.org/W4247001379","https://openalex.org/W4366563389","https://openalex.org/W4381587418","https://openalex.org/W4388851821","https://openalex.org/W4389991792","https://openalex.org/W4400353742","https://openalex.org/W4404282917","https://openalex.org/W4404622579","https://openalex.org/W4406152279","https://openalex.org/W4406421570","https://openalex.org/W4407174849","https://openalex.org/W4408093912","https://openalex.org/W4409190866","https://openalex.org/W4411119577","https://openalex.org/W4412889963"],"related_works":[],"abstract_inverted_index":{"General-purpose":[0],"large":[1],"language":[2],"models":[3,98],"(LLMs)":[4],"often":[5],"struggle":[6],"in":[7,33,108],"specialized":[8],"biomedical":[9,86,124,138],"applications":[10],"due":[11],"to":[12,16,81],"their":[13],"limited":[14],"access":[15,103],"up-to-date,":[17],"structured":[18,101],"knowledge":[19],"and":[20,63,112,126,132],"domainspecific":[21],"tools.":[22],"Although":[23],"recent":[24],"studies":[25,39],"show":[26,96],"proof":[27],"of":[28,51,119],"life":[29],"for":[30,122,130],"AI":[31],"agents":[32,135],"increasingly":[34],"complex":[35],"scientific":[36],"tasks,":[37],"few":[38],"offer":[40],"insights":[41,129],"at":[42],"an":[43],"atomic-level.":[44],"We":[45],"present":[46],"the":[47,117],"first":[48],"large-scale":[49],"evaluation":[50],"LLM":[52],"tool-calling":[53,79],"capabilities,":[54],"focused":[55],"on":[56],"genomics":[57],"annotation":[58],"tasks":[59],"such":[60],"as":[61],"variant-to-position":[62],"variant-to-gene":[64],"mapping.":[65],"Our":[66,93],"study":[67],"benchmarks":[68],"over":[69],"one":[70],"hundred":[71],"LLMs,":[72],"via":[73],"OpenRouter's":[74],"metagateway,":[75],"using":[76],"a":[77],"standardized":[78],"protocol":[80],"retrieve":[82],"information":[83],"directly":[84],"from":[85],"APIs":[87],"(e.g.,":[88],"NCBI":[89],"dbSNP,":[90],"Entrez":[91],"Gene).":[92],"experimental":[94],"results":[95],"that":[97],"equipped":[99],"with":[100],"tool":[102,120],"significantly":[104],"outperform":[105],"prompt-only":[106],"baselines":[107],"accuracy,":[109],"factual":[110],"consistency,":[111],"verifiability.":[113],"These":[114],"findings":[115],"demonstrate":[116],"necessity":[118],"augmentation":[121],"reliable":[123],"reasoning":[125],"provide":[127],"practical":[128],"building":[131],"testing":[133],"LLM-based":[134],"across":[136],"diverse":[137],"workflows.":[139]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-30T00:00:00"}