{"id":"https://openalex.org/W4416035896","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.30","title":"Toolscaler: Scalable Generative Tool Calling via Structure-Aware Semantic Tokenization","display_name":"Toolscaler: Scalable Generative Tool Calling via Structure-Aware Semantic Tokenization","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035896","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.30"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.30","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.30","pdf_url":"https://aclanthology.org/2025.findings-emnlp.30.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: EMNLP 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.30.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111037332","display_name":"Yunyue Su","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunyue Su","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120308932","display_name":"Zhang Jinshuai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang Jinshuai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Bowen Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bowen Fang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101800290","display_name":"Ye Wen","orcid":"https://orcid.org/0000-0001-6764-7544"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen Ye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101576666","display_name":"Jinghao Zhang","orcid":"https://orcid.org/0000-0003-3671-3005"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinghao Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089573343","display_name":"Bowen Song","orcid":"https://orcid.org/0000-0003-1553-0496"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bowen Song","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080477405","display_name":"Weiqiang Wang","orcid":"https://orcid.org/0000-0002-6159-619X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weiqiang Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Qiang Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiang Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100456470","display_name":"Liang Wang","orcid":"https://orcid.org/0000-0001-5444-748X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1584746,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"556","last_page":"578"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.1582999974489212,"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.1582999974489212,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.07890000194311142,"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/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.07509999722242355,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/generative-grammar","display_name":"Generative grammar","score":0.40610000491142273},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.3903999924659729},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3874000012874603},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.3718000054359436},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3456000089645386}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7824000120162964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5568000078201294},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44350001215934753},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.40610000491142273},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3903999924659729},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3874000012874603},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.3718000054359436},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.33559998869895935},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.23899999260902405}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.30","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.30","pdf_url":"https://aclanthology.org/2025.findings-emnlp.30.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: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.30","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.30","pdf_url":"https://aclanthology.org/2025.findings-emnlp.30.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: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4127089600","display_name":null,"funder_award_id":"62141608","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5156147101","display_name":null,"funder_award_id":"62236010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320318398","display_name":"Ant Group","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035896.pdf","grobid_xml":"https://content.openalex.org/works/W4416035896.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Enhancing":[0],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"with":[5,38],"external":[6],"tools":[7,21,72,78,101,109],"has":[8],"become":[9],"a":[10,39,89,127,134,173],"promising":[11],"approach":[12,53],"for":[13,122],"solving":[14],"complex":[15],"tasks.As":[16],"the":[17,47,115,145,153,162],"number":[18],"of":[19,114,148,164],"available":[20],"grows,":[22],"context-based":[23],"prompting":[24],"methods":[25],"increasingly":[26],"rely":[27],"on":[28,133,152],"retrieval":[29],"mechanisms.A":[30],"common":[31],"solution":[32],"is":[33],"to":[34,45,62,68,99],"represent":[35],"each":[36],"tool":[37,91,149,182],"unique":[40],"token":[41,49,120],"and":[42,73,118,175],"train":[43],"LLMs":[44],"generate":[46],"corresponding":[48],"during":[50],"inference.However,":[51],"this":[52,82],"suffers":[54],"from":[55,141],"linear":[56],"growth":[57],"in":[58,79,180],"representation":[59,116],"space,":[60],"leading":[61],"scalability":[63],"challenges.It":[64],"also":[65],"limits":[66],"generalization":[67],"novel":[69],"or":[70],"rare":[71],"underutilizes":[74],"collaborative":[75,139],"signals":[76,140],"among":[77],"downstream":[80,142],"tasks.In":[81],"paper,":[83],"we":[84],"propose":[85],"Toolscaler":[86,165],"1":[87],",":[88],"generative":[90,177],"invocation":[92],"framework":[93],"that":[94],"introduces":[95],"structure-aware":[96],"semantic":[97],"tokenization":[98],"encode":[100],"as":[102,172],"discrete":[103],"code":[104],"sequences.This":[105],"method":[106],"ensures":[107],"similar":[108],"share":[110],"subtokens,":[111],"enabling":[112],"compression":[113],"space":[117],"facilitating":[119],"sharing":[121],"new":[123],"tools.We":[124],"further":[125],"introduce":[126],"postguided,":[128],"multistage":[129],"iterative":[130],"training":[131],"strategy":[132],"shared":[135],"backbone":[136],"model,":[137],"where":[138],"tasks":[143],"guide":[144],"dynamic":[146],"refinement":[147],"representations.Extensive":[150],"experiments":[151],"ToolBench":[154],"dataset,":[155],"which":[156],"includes":[157],"over":[158],"47,000":[159],"APIs,":[160],"demonstrate":[161],"effectiveness":[163],"across":[166],"various":[167],"tasks,":[168],"showcasing":[169],"its":[170],"potential":[171],"scalable":[174],"generalizable":[176],"tool-using":[178],"paradigm":[179],"large-scale":[181],"usage":[183],"scenarios.":[184]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-08T00:00:00"}