{"id":"https://openalex.org/W4412944602","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1258","title":"Retrieval Models Aren\u2019t Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models","display_name":"Retrieval Models Aren\u2019t Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944602","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1258"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.1258","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1258","pdf_url":"https://aclanthology.org/2025.findings-acl.1258.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.1258.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100551503","display_name":"Zhengliang Shi","orcid":"https://orcid.org/0000-0002-9658-4906"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhengliang Shi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100360655","display_name":"Yuhan Wang","orcid":"https://orcid.org/0000-0002-5560-5213"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuhan Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094087200","display_name":"Lingyong Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lingyong Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046700486","display_name":"Pengjie Ren","orcid":"https://orcid.org/0000-0003-2964-6422"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengjie Ren","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050255638","display_name":"Shuaiqiang Wang","orcid":"https://orcid.org/0000-0002-9212-1947"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuaiqiang Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101771060","display_name":"Dawei Yin","orcid":"https://orcid.org/0000-0002-0684-6205"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dawei Yin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100384130","display_name":"Zhaochun Ren","orcid":"https://orcid.org/0000-0002-9076-6565"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhaochun Ren","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":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"24497","last_page":"24524"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9700000286102295,"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":0.9700000286102295,"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":0.968999981880188,"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/computer-science","display_name":"Computer science","score":0.7879034280776978},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7861056327819824},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5881503224372864},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.542108952999115},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49686339497566223},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4602583348751068},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3889080882072449}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7879034280776978},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7861056327819824},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5881503224372864},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.542108952999115},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49686339497566223},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4602583348751068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3889080882072449},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.1258","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1258","pdf_url":"https://aclanthology.org/2025.findings-acl.1258.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.1258","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1258","pdf_url":"https://aclanthology.org/2025.findings-acl.1258.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6283261777","display_name":null,"funder_award_id":"62472261","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412944602.pdf","grobid_xml":"https://content.openalex.org/works/W4412944602.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W4288267738","https://openalex.org/W2964413124","https://openalex.org/W4388937922","https://openalex.org/W3113264705"],"abstract_inverted_index":{"Tool":[0],"learning":[1],"aims":[2],"to":[3,14,22,35],"augment":[4],"large":[5,40],"language":[6],"models":[7,34,51,113,118],"(LLMs)":[8],"with":[9,119,151],"diverse":[10,96],"tools,":[11,104],"enabling":[12],"them":[13],"act":[15],"as":[16],"agents":[17],"for":[18,74],"solving":[19],"practical":[20],"tasks.Due":[21],"the":[23,47,81,117,135,158],"limited":[24],"context":[25],"length":[26],"of":[27,49,71,102,112,139,162],"tool-using":[28],"LLMs,":[29],"adopting":[30],"information":[31],"retrieval":[32,54,92,97,132,160],"(IR)":[33],"select":[36],"useful":[37],"tools":[38,73],"from":[39,80,106],"toolsets":[41],"is":[42,78],"a":[43,68,89,100,142,147],"critical":[44],"initial":[45],"step.However,":[46],"performance":[48,121,128],"IR":[50,124,163],"in":[52,122],"tool":[53,91,159],"tasks":[55],"remains":[56],"underexplored":[57],"and":[58,99],"unclear.Most":[59],"tooluse":[60],"benchmarks":[61],"simplify":[62],"this":[63,84],"step":[64],"by":[65],"manually":[66],"pre-annotating":[67],"small":[69],"set":[70],"relevant":[72],"each":[75],"task,":[76],"which":[77,155],"far":[79],"real-world":[82],"scenarios.In":[83],"paper,":[85],"we":[86,145],"propose":[87],"TOOLRET,":[88],"heterogeneous":[90],"benchmark":[93,109],"comprising":[94],"7.6k":[95],"tasks,":[98],"corpus":[101],"43k":[103],"collected":[105],"existing":[107],"datasets.We":[108],"six":[110],"types":[111],"on":[114,129],"TOOL-RET.Surprisingly,":[115],"even":[116],"strong":[120],"conventional":[123],"benchmarks,":[125],"exhibit":[126],"poor":[127],"TOOLRET.This":[130],"low":[131],"quality":[133],"degrades":[134],"task":[136],"pass":[137],"rate":[138],"tool-use":[140],"LLMs.As":[141],"further":[143],"step,":[144],"contribute":[146],"large-scale":[148],"training":[149],"dataset":[150],"over":[152],"200k":[153],"instances,":[154],"substantially":[156],"optimizes":[157],"ability":[161],"models.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}