{"id":"https://openalex.org/W7163868305","doi":"https://doi.org/10.48550/arxiv.2606.06566","title":"NTILC: Neural Tool Invocation via Learned Compression","display_name":"NTILC: Neural Tool Invocation via Learned Compression","publication_year":2026,"publication_date":"2026-06-04","ids":{"openalex":"https://openalex.org/W7163868305","doi":"https://doi.org/10.48550/arxiv.2606.06566"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.06566","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.06566","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":"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.06566","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138176981","display_name":"Andrew Krikorian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Krikorian, Andrew","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138180930","display_name":"Yayuan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yayuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5079301873","display_name":"Jason J. Corso","orcid":"https://orcid.org/0000-0001-6454-9594"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Corso, Jason J.","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":false,"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/T10028","display_name":"Topic Modeling","score":0.7469000220298767,"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":0.7469000220298767,"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":0.08299999684095383,"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/T12031","display_name":"Speech and dialogue systems","score":0.02419999986886978,"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/latency","display_name":"Latency (audio)","score":0.6245999932289124},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5527999997138977},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5447999835014343},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.48669999837875366},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.47200000286102295},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4442000091075897},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4117000102996826},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.3418000042438507}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8302000164985657},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6245999932289124},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5527999997138977},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5447999835014343},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.48669999837875366},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.47200000286102295},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4442000091075897},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4117000102996826},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3935000002384186},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3837999999523163},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3418000042438507},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3165000081062317},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2930000126361847},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C98184364","wikidata":"https://www.wikidata.org/wiki/Q1780131","display_name":"Argument (complex analysis)","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.2711000144481659}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.06566","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.06566","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.06566","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.06566","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":"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Agentic":[0],"tool-calling":[1],"language":[2,108],"models":[3],"depend":[4],"on":[5,113,179],"large":[6],"registries":[7],"of":[8,32],"callable":[9],"APIs,":[10],"functions,":[11],"and":[12,50,72,89,148,182,185,192,207],"local":[13],"actions.":[14],"Placing":[15],"full":[16],"tool":[17,34,70,90,98,116,141],"specifications":[18,91],"directly":[19],"in":[20],"the":[21,30,33,38,42,114,160],"prompt":[22],"incurs":[23],"a":[24,68,93,129,156],"cost":[25],"that":[26,75,166],"scales":[27],"linearly":[28],"with":[29,80,137,155],"size":[31],"registry,":[35],"rapidly":[36],"consuming":[37],"context":[39,187,201],"budget.":[40],"As":[41],"registry":[43,78],"grows,":[44],"this":[45],"leads":[46],"to":[47,56,125,212,215],"higher":[48],"latency":[49,194,209],"degrades":[51],"selection":[52,71,99,193],"accuracy,":[53,191],"particularly":[54],"due":[55],"interference":[57],"from":[58,140],"irrelevant":[59],"tools.":[60],"We":[61,176],"overcome":[62],"these":[63,197],"limitations":[64],"by":[65,204,210],"introducing":[66],"NTILC,":[67],"neural":[69],"invocation":[73],"framework":[74],"replaces":[76],"in-context":[77,105],"look-up":[79],"learned":[81],"latent":[82],"retrieval.":[83],"NTILC":[84,178,199],"maps":[85],"both":[86],"user":[87],"intent":[88],"into":[92],"shared":[94],"embedding":[95],"space,":[96],"enabling":[97],"via":[100],"external":[101],"retrieval":[102,190],"rather":[103],"than":[104],"lookup.":[106],"The":[107],"model":[109,161],"is":[110,128],"conditioned":[111],"only":[112],"selected":[115],"schema,":[117,145],"allowing":[118],"for":[119],"precise,":[120],"constrained":[121],"argument":[122,144],"generation.":[123],"Central":[124],"our":[126],"approach":[127],"signature-aware":[130],"composite":[131],"objective,":[132],"which":[133],"augments":[134],"semantic":[135],"similarity":[136],"constraints":[138],"derived":[139],"signatures":[142],"(e.g.,":[143],"type":[146],"compatibility,":[147],"return":[149],"types).":[150],"By":[151],"combining":[152],"Circle":[153],"Loss":[154],"Functional":[157],"Margin":[158],"Loss,":[159],"enforces":[162],"separation":[163],"between":[164],"tools":[165],"are":[167],"semantically":[168],"similar":[169],"but":[170],"incompatible":[171],"under":[172],"their":[173],"execution":[174],"signatures.":[175],"evaluate":[177],"public":[180],"tool-selection":[181],"function-calling":[183],"datasets":[184],"report":[186],"token":[188],"usage,":[189],"metrics.":[195],"Across":[196],"settings,":[198],"reduces":[200],"window":[202],"consumption":[203],"over":[205],"95%":[206],"inference":[208],"up":[211],"74%":[213],"compared":[214],"long-context":[216],"ICT":[217],"baselines.":[218]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-09T00:00:00"}