{"id":"https://openalex.org/W7158098060","doi":"https://doi.org/10.1145/3805621.3807627","title":"Asynchronous Verified Semantic Caching for Tiered LLM Architectures","display_name":"Asynchronous Verified Semantic Caching for Tiered LLM Architectures","publication_year":2026,"publication_date":"2026-04-27","ids":{"openalex":"https://openalex.org/W7158098060","doi":"https://doi.org/10.1145/3805621.3807627"},"language":null,"primary_location":{"id":"doi:10.1145/3805621.3807627","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805621.3807627","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixth European Workshop on Machine Learning and Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805621.3807627","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126169316","display_name":"Asmit Kumar Singh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Asmit Kumar Singh","raw_affiliation_strings":["Apple, Cupertino, California, USA"],"raw_orcid":"https://orcid.org/0000-0003-3313-4518","affiliations":[{"raw_affiliation_string":"Apple, Cupertino, California, USA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126155627","display_name":"Haozhe Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haozhe Wang","raw_affiliation_strings":["Apple, Cupertino, USA"],"raw_orcid":"https://orcid.org/0009-0007-5024-9575","affiliations":[{"raw_affiliation_string":"Apple, Cupertino, USA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126082871","display_name":"Laxmi Naga Santosh Attaluri","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laxmi Naga Santosh Attaluri","raw_affiliation_strings":["Apple, Cupertino, USA"],"raw_orcid":"https://orcid.org/0009-0007-3964-0872","affiliations":[{"raw_affiliation_string":"Apple, Cupertino, USA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126123171","display_name":"Tak Chiam","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tak Chiam","raw_affiliation_strings":["Apple, Cupertino, USA"],"raw_orcid":"https://orcid.org/0009-0004-5921-6954","affiliations":[{"raw_affiliation_string":"Apple, Cupertino, USA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101434706","display_name":"Weihua Zhu","orcid":"https://orcid.org/0000-0001-5959-1608"},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weihua Zhu","raw_affiliation_strings":["Apple, Cupertino, USA"],"raw_orcid":"https://orcid.org/0009-0002-5180-9435","affiliations":[{"raw_affiliation_string":"Apple, Cupertino, USA","institution_ids":["https://openalex.org/I4210153776"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5126169316"],"corresponding_institution_ids":["https://openalex.org/I4210153776"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.96323686,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"192","last_page":"199"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.12800000607967377,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.12800000607967377,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.11410000175237656,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.10530000180006027,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/cache","display_name":"Cache","score":0.7369999885559082},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.6401000022888184},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.5846999883651733},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5796999931335449},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5030999779701233},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.49230000376701355},{"id":"https://openalex.org/keywords/static-analysis","display_name":"Static analysis","score":0.475600004196167}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8741000294685364},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.7369999885559082},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.6401000022888184},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.5846999883651733},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5796999931335449},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5030999779701233},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.49230000376701355},{"id":"https://openalex.org/C97686452","wikidata":"https://www.wikidata.org/wiki/Q7604153","display_name":"Static analysis","level":2,"score":0.475600004196167},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4383000135421753},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.4345000088214874},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3727000057697296},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.3176000118255615},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.28459998965263367},{"id":"https://openalex.org/C2778565505","wikidata":"https://www.wikidata.org/wiki/Q2207566","display_name":"Spec#","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.262800008058548}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805621.3807627","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805621.3807627","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixth European Workshop on Machine Learning and Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805621.3807627","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805621.3807627","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixth European Workshop on Machine Learning and Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2110679325","https://openalex.org/W3000004779","https://openalex.org/W4387321091","https://openalex.org/W4389523830","https://openalex.org/W4400641571","https://openalex.org/W4402026018","https://openalex.org/W4412610379"],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"now":[4],"sit":[5],"in":[6],"the":[7,100,112,117,122,134,140,148,178,214],"critical":[8,101],"path":[9],"of":[10,37,116,180],"search,":[11],"assistance,":[12],"and":[13,24,154,161,173,200],"agentic":[14],"workflows,":[15],"making":[16],"semantic":[17],"caching":[18,89],"essential":[19],"for":[20,139,213],"reducing":[21],"inference":[22],"cost":[23],"latency.":[25],"Production":[26],"deployments":[27],"typically":[28],"use":[29],"a":[30,34,46,59,66,107],"tiered":[31],"static-dynamic":[32],"design:":[33],"static":[35,93,114,123,135,159,163,185,188],"cache":[36,48],"curated,":[38],"offline-vetted":[39],"responses":[40],"mined":[41],"from":[42],"logs,":[43],"backed":[44],"by":[45,58,193],"dynamic":[47,149],"populated":[49],"online.":[50],"In":[51,167],"practice,":[52],"both":[53],"tiers":[54],"are":[55,145],"commonly":[56],"governed":[57],"single":[60],"embedding":[61],"similarity":[62],"threshold,":[63,124],"which":[64],"induces":[65],"hard":[67],"tradeoff:":[68],"conservative":[69],"thresholds":[70,77],"miss":[71],"safe":[72],"reuse":[73,157],"opportunities,":[74],"while":[75],"aggressive":[76],"risk":[78],"serving":[79,97],"semantically":[80],"incorrect":[81],"responses.":[82],"We":[83],"introduce":[84],"Krites,":[85],"an":[86,128],"asynchronous,":[87],"LLM-judged":[88],"policy":[90],"that":[91,216],"expands":[92],"coverage":[94],"without":[95],"changing":[96],"decisions.":[98],"On":[99],"path,":[102],"Krites":[103,125,176],"behaves":[104],"exactly":[105],"like":[106],"standard":[108],"static-threshold":[109],"policy.":[110],"When":[111],"nearest":[113],"neighbor":[115],"prompt":[118],"falls":[119],"just":[120],"below":[121],"asynchronously":[126],"invokes":[127],"LLM":[129],"judge":[130],"to":[131,156,195,206],"verify":[132],"whether":[133],"response":[136],"is":[137],"acceptable":[138],"new":[141],"prompt.":[142],"Approved":[143],"matches":[144],"promoted":[146],"into":[147],"cache,":[150],"allowing":[151],"future":[152],"repeats":[153],"paraphrases":[155],"curated":[158,184],"answers":[160,186],"expanding":[162],"reach":[164],"over":[165],"time.":[166],"oracle-based":[168],"trace-driven":[169],"simulations":[170],"on":[171,197,202],"conversational":[172,198],"search":[174],"workloads,":[175],"increases":[177],"fraction":[179],"requests":[181],"served":[182],"with":[183,209],"(direct":[187],"hits":[189],"plus":[190],"verified":[191],"promotions)":[192],"up":[194],"2.4\u00d7":[196],"traffic":[199],"3.9\u00d7":[201],"search-style":[203],"queries":[204],"relative":[205],"tuned":[207],"baselines,":[208],"unchanged":[210],"critical-path":[211],"latency":[212],"request":[215],"triggered":[217],"verification.":[218]},"counts_by_year":[],"updated_date":"2026-04-30T06:11:10.768123","created_date":"2026-04-30T00:00:00"}