{"id":"https://openalex.org/W4415797489","doi":"https://doi.org/10.52202/079017-1725","title":"APIGen: Automated PIpeline for Generating Verifiable and Diverse Function-Calling Datasets","display_name":"APIGen: Automated PIpeline for Generating Verifiable and Diverse Function-Calling Datasets","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4415797489","doi":"https://doi.org/10.52202/079017-1725"},"language":"en","primary_location":{"id":"doi:10.52202/079017-1725","doi":"https://doi.org/10.52202/079017-1725","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-1725","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.18518","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037613999","display_name":"Zuxin Liu","orcid":"https://orcid.org/0000-0001-7412-5074","observed_orcids":["https://orcid.org/0000-0001-7412-5074"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zuxin Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114130501","display_name":"Thai Hoang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thai Hoang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jianguo Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianguo Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102947896","display_name":"Ming Hua Zhu","orcid":"https://orcid.org/0000-0003-2812-5406","observed_orcids":["https://orcid.org/0000-0003-2812-5406"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110379714","display_name":"Tian Lan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian Lan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099241656","display_name":"Shirley Kokane","orcid":"https://orcid.org/0009-0004-8655-8191","observed_orcids":["https://orcid.org/0009-0004-8655-8191"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shirley Kokane","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002064919","display_name":"Juntao Tan","orcid":"https://orcid.org/0000-0003-3646-933X","observed_orcids":["https://orcid.org/0000-0003-3646-933X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juntao Tan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Weiran Yao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weiran Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004924286","display_name":"Zhiwei Liu","orcid":"https://orcid.org/0000-0002-1018-0522","observed_orcids":["https://orcid.org/0000-0002-1018-0522"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiwei Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111345651","display_name":"Yihao Feng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yihao Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112976037","display_name":"Rithesh Murthy","orcid":"https://orcid.org/0009-0006-8032-1526","observed_orcids":["https://orcid.org/0009-0006-8032-1526"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rithesh Murthy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100751566","display_name":"Huan Wang","orcid":"https://orcid.org/0000-0002-1403-5314","observed_orcids":["https://orcid.org/0000-0002-1403-5314","https://orcid.org/0000-0002-3504-6522","https://orcid.org/0009-0005-3082-6422"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liangwei Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042646536","display_name":"Silvio Savarese","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Silvio Savarese","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018518655","display_name":"Juan Carlos Niebles","orcid":"https://orcid.org/0000-0001-8225-9793","observed_orcids":["https://orcid.org/0000-0001-8225-9793","https://orcid.org/0000-0002-3953-6297"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juan Niebles","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100751566","display_name":"Huan Wang","orcid":"https://orcid.org/0000-0002-1403-5314","observed_orcids":["https://orcid.org/0000-0002-1403-5314","https://orcid.org/0000-0002-3504-6522","https://orcid.org/0009-0005-3082-6422"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huan Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063103006","display_name":"Shelby Heinecke","orcid":"https://orcid.org/0000-0002-8831-0753","observed_orcids":["https://orcid.org/0000-0002-8831-0753"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shelby Heinecke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032046813","display_name":"Caiming Xiong","orcid":"https://orcid.org/0000-0003-0349-8628","observed_orcids":["https://orcid.org/0000-0003-0349-8628"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Caiming Xiong","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":20.9512,"has_fulltext":true,"cited_by_count":137,"citation_normalized_percentile":{"value":0.99543886,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"54463","last_page":"54482"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.29829999804496765,"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":0.29829999804496765,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.1729000061750412,"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/T13904","display_name":"Artificial Intelligence Applications","score":0.12489999830722809,"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/function-calling","display_name":"function calling","score":0.8500000238418579},{"id":"https://openalex.org/keywords/dataset-construction","display_name":"dataset construction","score":0.6990000009536743},{"id":"https://openalex.org/keywords/semantic-verification","display_name":"semantic verification","score":0.828000009059906},{"id":"https://openalex.org/keywords/data-curation","display_name":"data curation","score":0.5180000066757202},{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.5199999809265137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6690999865531921},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6312000155448914},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.48170000314712524},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3659999966621399},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29809999465942383},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.26809999346733093},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2515999972820282},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.24889999628067017}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/079017-1725","doi":"https://doi.org/10.52202/079017-1725","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-1725","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2406.18518","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.18518","pdf_url":"https://arxiv.org/pdf/2406.18518","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2406.18518","doi":"https://doi.org/10.48550/arxiv.2406.18518","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.18518","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2406.18518","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.18518","pdf_url":"https://arxiv.org/pdf/2406.18518","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415797489.pdf","grobid_xml":"https://content.openalex.org/works/W4415797489.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W3126325318","https://openalex.org/W4322718191","https://openalex.org/W4327810158","https://openalex.org/W4378505261","https://openalex.org/W4380136738","https://openalex.org/W4380994509","https://openalex.org/W4385327683","https://openalex.org/W4385682136","https://openalex.org/W4385825419","https://openalex.org/W4385963839","https://openalex.org/W4386908092","https://openalex.org/W4387427530","https://openalex.org/W4387560526","https://openalex.org/W4387560542","https://openalex.org/W4387561532","https://openalex.org/W4387891177","https://openalex.org/W4390723197","https://openalex.org/W4391272793","https://openalex.org/W4392182703","https://openalex.org/W4392223321","https://openalex.org/W4392679398","https://openalex.org/W4396600560","https://openalex.org/W4402670718","https://openalex.org/W4402671629","https://openalex.org/W4402672016","https://openalex.org/W4415795271","https://openalex.org/W4415797149"],"related_works":["https://openalex.org/W7162751695","https://openalex.org/W4402954204","https://openalex.org/W4415200961","https://openalex.org/W4391912470","https://openalex.org/W7125799440","https://openalex.org/W7172315588","https://openalex.org/W4405714925","https://openalex.org/W4416251035","https://openalex.org/W7134269006","https://openalex.org/W4400267079"],"abstract_inverted_index":{"The":[0,133],"advancement":[1],"of":[2,129],"function-calling":[3,28,45,130],"agent":[4,131],"models":[5,80],"requires":[6],"diverse,":[7],"reliable,":[8],"and":[9,33,50,69,75,113,140],"high-quality":[10,25,122],"datasets.":[11],"This":[12],"paper":[13],"presents":[14],"APIGen,":[15],"an":[16],"automated":[17],"data":[18,54],"generation":[19],"pipeline":[20],"designed":[21],"to":[22,42,125],"synthesize":[23],"verifiable":[24],"datasets":[26,46],"for":[27],"applications.":[29],"We":[30,77,116],"leverage":[31],"APIGen":[32],"collect":[34],"3,673":[35],"executable":[36],"APIs":[37],"across":[38],"21":[39],"different":[40],"categories":[41],"generate":[43],"diverse":[44],"in":[47,55],"a":[48,118],"scalable":[49],"structured":[51],"manner.":[52],"Each":[53],"our":[56,83,105],"dataset":[57,119,134],"is":[58,135],"verified":[59],"through":[60],"three":[61],"hierarchical":[62],"stages:":[63],"format":[64],"checking,":[65],"actual":[66],"function":[67],"executions,":[68],"semantic":[70],"verification,":[71],"ensuring":[72],"its":[73],"reliability":[74],"correctness.":[76],"demonstrate":[78],"that":[79],"trained":[81],"with":[82,87],"curated":[84],"datasets,":[85],"even":[86],"only":[88],"7B":[89],"parameters,":[90],"can":[91],"achieve":[92],"state-of-the-art":[93],"performance":[94],"on":[95,137],"the":[96,127,141],"Berkeley":[97],"Function-Calling":[98],"Benchmark,":[99],"outperforming":[100],"multiple":[101],"GPT-4":[102],"models.":[103],"Moreover,":[104],"1B":[106],"model":[107],"achieves":[108],"exceptional":[109],"performance,":[110],"surpassing":[111],"GPT-3.5-Turbo":[112],"Claude-3":[114],"Haiku.":[115],"release":[117],"containing":[120],"60,000":[121],"entries,":[123],"aiming":[124],"advance":[126],"field":[128],"domains.":[132],"available":[136],"Huggingface:":[138],"https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k":[139],"project":[142],"homepage:":[143],"https://apigen-pipeline.github.io/":[144]},"counts_by_year":[{"year":2026,"cited_by_count":72},{"year":2025,"cited_by_count":51},{"year":2024,"cited_by_count":14}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2025-11-03T00:00:00"}
