{"id":"https://openalex.org/W7106310943","doi":"https://doi.org/10.1145/3767695.3769488","title":"Beyond GeneGPT: A Multi-Agent Architecture with Open-Source LLMs for Enhanced Genomic Question Answering","display_name":"Beyond GeneGPT: A Multi-Agent Architecture with Open-Source LLMs for Enhanced Genomic Question Answering","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W7106310943","doi":"https://doi.org/10.1145/3767695.3769488"},"language":null,"primary_location":{"id":"doi:10.1145/3767695.3769488","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767695.3769488","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3767695.3769488","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Haodong Chen","orcid":"https://orcid.org/0009-0001-8647-0331"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Haodong Chen","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia"],"raw_orcid":"https://orcid.org/0009-0001-8647-0331","affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Guido Zuccon","orcid":"https://orcid.org/0000-0003-0271-5563"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Guido Zuccon","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia"],"raw_orcid":"https://orcid.org/0000-0003-0271-5563","affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"last","author":{"id":null,"display_name":"Teerapong Leelanupab","orcid":"https://orcid.org/0000-0002-8117-0612"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Teerapong Leelanupab","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia"],"raw_orcid":"https://orcid.org/0000-0002-8117-0612","affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165143802"],"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":"143","last_page":"152"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6840000152587891,"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":0.6840000152587891,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.09780000150203705,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.04309999942779541,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7390000224113464},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.7050999999046326},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6620000004768372},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46050000190734863},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.43950000405311584},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.40630000829696655},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.38029998540878296},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.34139999747276306}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7390000224113464},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7177000045776367},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.7050999999046326},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6620000004768372},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46050000190734863},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.45179998874664307},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.43950000405311584},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.40630000829696655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38370001316070557},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.38029998540878296},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.34139999747276306},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C20901353","wikidata":"https://www.wikidata.org/wiki/Q4117139","display_name":"Biological database","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30480000376701355},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.29440000653266907},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.26989999413490295},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2676999866962433}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3767695.3769488","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767695.3769488","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.15061","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.15061","pdf_url":"https://arxiv.org/pdf/2511.15061","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"}],"best_oa_location":{"id":"doi:10.1145/3767695.3769488","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767695.3769488","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Genomic":[0],"question":[1,194],"answering":[2],"often":[3],"requires":[4],"complex":[5],"reasoning":[6,122],"and":[7,47,53,60,75,116,123,146,197],"integration":[8],"across":[9,169],"diverse":[10],"biomedical":[11],"sources.":[12],"GeneGPT":[13,62,106,131],"addressed":[14],"this":[15,56,82,90,94],"challenge":[16],"by":[17,107,167],"combining":[18],"domain-specific":[19],"APIs":[20],"with":[21,32],"OpenAI's":[22],"code-davinci-002":[23],"large":[24],"language":[25,30],"model":[26,41,177],"to":[27,85],"enable":[28],"natural":[29],"interaction":[31],"genomic":[33,193],"databases.":[34],"However,":[35],"its":[36],"reliance":[37],"on":[38,93,132,144,148],"a":[39,64,79,100],"proprietary":[40],"limits":[42],"scalability,":[43],"increases":[44],"operational":[45],"costs,":[46],"raises":[48],"concerns":[49],"about":[50],"data":[51],"privacy":[52],"generalization.":[54],"In":[55],"work,":[57],"we":[58,96],"revisit":[59],"reproduce":[61],"in":[63],"pilot":[65],"study":[66],"using":[67,151],"open":[68],"source":[69],"models,":[70],"including":[71],"Llama":[72],"3.1,":[73],"Qwen2.5,":[74],"Qwen2.5":[76],"Coder,":[77],"within":[78],"monolithic":[80],"architecture;":[81],"allows":[83],"us":[84],"identify":[86],"the":[87,136,186],"limitations":[88],"of":[89,135,142,181,188],"approach.":[91],"Building":[92],"foundation,":[95],"then":[97],"develop":[98],"OpenBioLLM,":[99],"modular":[101,162],"multi-agent":[102,163,190],"framework":[103],"that":[104],"extends":[105],"introducing":[108],"agent":[109],"specialization":[110],"for":[111,192],"tool":[112],"routing,":[113],"query":[114],"generation,":[115],"response":[117],"validation.":[118],"This":[119],"enables":[120],"coordinated":[121],"role-based":[124],"task":[125],"execution.":[126],"OpenBioLLM":[127],"matches":[128],"or":[129,158],"outperforms":[130],"over":[133],"90%":[134],"benchmark":[137,170],"tasks,":[138,171],"achieving":[139],"average":[140],"scores":[141],"0.849":[143],"GeneTuring":[145],"0.830":[147],"GeneHop,":[149],"while":[150],"smaller":[152],"open-source":[153,189],"models":[154],"without":[155,175],"additional":[156],"fine-tuning":[157],"tool-specific":[159],"pretraining.":[160],"OpenBioLLM's":[161],"design":[164],"reduces":[165],"latency":[166],"40\u201350%":[168],"significantly":[172],"improving":[173],"efficiency":[174],"compromising":[176],"capability.":[178],"The":[179],"results":[180],"our":[182],"comprehensive":[183],"evaluation":[184],"highlight":[185],"potential":[187],"systems":[191],"answering.":[195],"Code":[196],"resources":[198],"are":[199],"available":[200],"at":[201],"https://github.com/ielab/OpenBioLLM.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-23T00:00:00"}