{"id":"https://openalex.org/W4408352582","doi":"https://doi.org/10.1109/icassp49660.2025.10890828","title":"Tool Playgrounds: A Comprehensive and Analyzable Benchmark for LLM Tool Invocation","display_name":"Tool Playgrounds: A Comprehensive and Analyzable Benchmark for LLM Tool Invocation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352582","doi":"https://doi.org/10.1109/icassp49660.2025.10890828"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890828","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890828","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5112518846","display_name":"Zhiwei Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhiwei Dong","raw_affiliation_strings":["University of Science and Technology,Beijing"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology,Beijing","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048414655","display_name":"Ruihao Gong","orcid":"https://orcid.org/0000-0002-6024-7086"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruihao Gong","raw_affiliation_strings":["SenseTime Research"],"affiliations":[{"raw_affiliation_string":"SenseTime Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100717244","display_name":"Yong Yang","orcid":"https://orcid.org/0000-0002-2157-0243"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Yong","raw_affiliation_strings":["SenseTime Research"],"affiliations":[{"raw_affiliation_string":"SenseTime Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085750604","display_name":"Shuo Wu","orcid":"https://orcid.org/0000-0002-2908-6595"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuo Wu","raw_affiliation_strings":["SenseTime Research"],"affiliations":[{"raw_affiliation_string":"SenseTime Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001649888","display_name":"Yongqiang Yao","orcid":"https://orcid.org/0009-0002-1941-9904"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongqiang Yao","raw_affiliation_strings":["SenseTime Research"],"affiliations":[{"raw_affiliation_string":"SenseTime Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006074341","display_name":"Song-Lu Chen","orcid":"https://orcid.org/0000-0002-0780-658X"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song-Lu Chen","raw_affiliation_strings":["University of Science and Technology,Beijing"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology,Beijing","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074514262","display_name":"Xu-Cheng Yin","orcid":"https://orcid.org/0000-0003-0023-0220"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu-Cheng Yin","raw_affiliation_strings":["University of Science and Technology,Beijing"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology,Beijing","institution_ids":["https://openalex.org/I92403157"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5112518846"],"corresponding_institution_ids":["https://openalex.org/I92403157"],"apc_list":null,"apc_paid":null,"fwci":1.5069,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83892401,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11675","display_name":"Open Source Software Innovations","score":0.9793999791145325,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11675","display_name":"Open Source Software Innovations","score":0.9793999791145325,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T13999","display_name":"Digital Rights Management and Security","score":0.9671000242233276,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/invocation","display_name":"Invocation","score":0.9212427139282227},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8554620146751404},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8098034262657166},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.32958197593688965},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.052568644285202026}],"concepts":[{"id":"https://openalex.org/C2776527387","wikidata":"https://www.wikidata.org/wiki/Q1671839","display_name":"Invocation","level":2,"score":0.9212427139282227},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8554620146751404},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8098034262657166},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.32958197593688965},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.052568644285202026},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890828","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890828","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W4385245566","https://openalex.org/W4389518608","https://openalex.org/W4393147146","https://openalex.org/W4402670146","https://openalex.org/W4402670152","https://openalex.org/W4403998643","https://openalex.org/W4411113053","https://openalex.org/W6755207826","https://openalex.org/W6763701032","https://openalex.org/W6769627184","https://openalex.org/W6778883912","https://openalex.org/W6852792400","https://openalex.org/W6853966477","https://openalex.org/W6855330075","https://openalex.org/W6856490892","https://openalex.org/W6857892373","https://openalex.org/W6859407334","https://openalex.org/W6860485421","https://openalex.org/W6860501820","https://openalex.org/W6861272002"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4255072433","https://openalex.org/W2527536206","https://openalex.org/W4233258402","https://openalex.org/W2460921780","https://openalex.org/W2489188378","https://openalex.org/W2586198568","https://openalex.org/W2231659815"],"abstract_inverted_index":{"The":[0],"rapid":[1],"advancement":[2],"of":[3,27],"large":[4],"language":[5],"models":[6,101],"(LLMs)":[7],"has":[8,22],"paved":[9],"the":[10,25,64,97],"way":[11],"for":[12],"their":[13],"use":[14],"in":[15,20,110],"solving":[16],"real-world":[17],"problems,":[18],"which":[19],"turn":[21],"significantly":[23],"driven":[24],"development":[26],"tool-assisted":[28],"LLMs.":[29],"This":[30,74],"progress":[31],"necessitates":[32],"thorough":[33],"evaluation":[34],"methods.":[35],"However,":[36],"existing":[37],"benchmarks":[38],"typically":[39],"only":[40],"provide":[41],"end-to-end":[42],"scores":[43],"but":[44],"lack":[45],"in-depth":[46],"analysis":[47],"and":[48,71,88,107,119,127],"often":[49],"suffer":[50],"from":[51],"issues":[52],"such":[53,79],"as":[54,80],"instability.":[55],"To":[56,115],"address":[57],"this":[58],"gap,":[59],"we":[60,121],"have":[61,122],"meticulously":[62],"designed":[63],"Tool":[65],"Playgrounds":[66],"framework,":[67],"a":[68],"comprehensive,":[69],"analyzable,":[70],"extensible":[72],"benchmark.":[73],"framework":[75],"evaluates":[76],"boundary":[77],"dimensions":[78],"parameter":[81,84],"missing":[82],"interaction,":[83],"correction,":[85],"tool":[86,113],"failover,":[87],"leveraging":[89],"internal":[90],"knowledge.":[91],"Our":[92],"findings":[93],"indicate":[94],"that":[95],"even":[96],"most":[98],"advanced":[99],"commercial":[100],"frequently":[102],"overlook":[103],"these":[104],"essential":[105],"aspects":[106],"face":[108],"challenges":[109],"managing":[111],"complex":[112],"usage.":[114],"foster":[116],"further":[117],"research":[118],"development,":[120],"made":[123],"our":[124],"code,":[125],"dataset,":[126],"leaderboard":[128],"publicly":[129],"available":[130],"on":[131],"https://github.com/zhiwei-dong/ToolPlaygrounds.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}