{"id":"https://openalex.org/W4415247744","doi":"https://doi.org/10.48550/arxiv.2505.03275","title":"RAG-MCP: Mitigating Prompt Bloat in LLM Tool Selection via Retrieval-Augmented Generation","display_name":"RAG-MCP: Mitigating Prompt Bloat in LLM Tool Selection via Retrieval-Augmented Generation","publication_year":2025,"publication_date":"2025-05-06","ids":{"openalex":"https://openalex.org/W4415247744","doi":"https://doi.org/10.48550/arxiv.2505.03275"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.03275","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.03275","pdf_url":"https://arxiv.org/pdf/2505.03275","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.03275","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Gan, Tiantian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gan, Tiantian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5069955912","display_name":"Qiong Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Qiyao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9857000112533569,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9857000112533569,"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/T10028","display_name":"Topic Modeling","score":0.9277999997138977,"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/selection","display_name":"Selection (genetic algorithm)","score":0.7705000042915344},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6665999889373779},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6589999794960022},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.652400016784668},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.48339998722076416},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.3224000036716461}],"concepts":[{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.7705000042915344},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7623999714851379},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6665999889373779},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6589999794960022},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.652400016784668},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.48339998722076416},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4284999966621399},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42820000648498535},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40779998898506165},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C2775973920","wikidata":"https://www.wikidata.org/wiki/Q3252726","display_name":"Selection algorithm","level":3,"score":0.27480000257492065},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.27230000495910645}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.03275","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.03275","pdf_url":"https://arxiv.org/pdf/2505.03275","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.03275","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.03275","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.03275","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.03275","pdf_url":"https://arxiv.org/pdf/2505.03275","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415247744.pdf","grobid_xml":"https://content.openalex.org/works/W4415247744.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"struggle":[4],"to":[5,25,50,75],"effectively":[6],"utilize":[7],"a":[8,34,57],"growing":[9],"number":[10],"of":[11],"external":[12,62],"tools,":[13],"such":[14],"as":[15],"those":[16],"defined":[17],"by":[18,42,98],"the":[19,52,66,69,76],"Model":[20],"Context":[21],"Protocol":[22],"(MCP)\\cite{IntroducingMCP},":[23],"due":[24],"prompt":[26,80,95],"bloat":[27],"and":[28,82,101,118],"selection":[29,106],"complexity.":[30],"We":[31],"introduce":[32],"RAG-MCP,":[33],"Retrieval-Augmented":[35],"Generation":[36],"framework":[37],"that":[38],"overcomes":[39],"this":[40],"challenge":[41],"offloading":[43],"tool":[44,71,105,120],"discovery.":[45],"RAG-MCP":[46,92,115],"uses":[47],"semantic":[48],"retrieval":[49],"identify":[51],"most":[53],"relevant":[54],"MCP(s)":[55],"for":[56,122],"given":[58],"query":[59],"from":[60],"an":[61,87],"index":[63],"before":[64],"engaging":[65],"LLM.":[67],"Only":[68],"selected":[70],"descriptions":[72],"are":[73],"passed":[74],"model,":[77],"drastically":[78],"reducing":[79],"size":[81],"simplifying":[83],"decision-making.":[84],"Experiments,":[85],"including":[86],"MCP":[88],"stress":[89],"test,":[90],"demonstrate":[91],"significantly":[93],"cuts":[94],"tokens":[96],"(e.g.,":[97],"over":[99],"50%)":[100],"more":[102],"than":[103],"triples":[104],"accuracy":[107],"(43.13%":[108],"vs":[109],"13.62%":[110],"baseline)":[111],"on":[112],"benchmark":[113],"tasks.":[114],"enables":[116],"scalable":[117],"accurate":[119],"integration":[121],"LLMs.":[123]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-16T00:00:00"}