{"id":"https://openalex.org/W4416298066","doi":"https://doi.org/10.1007/s11227-025-08034-8","title":"A data-augmented model routing framework for efficient LLM deployment in edge\u2013cloud environments","display_name":"A data-augmented model routing framework for efficient LLM deployment in edge\u2013cloud environments","publication_year":2025,"publication_date":"2025-11-17","ids":{"openalex":"https://openalex.org/W4416298066","doi":"https://doi.org/10.1007/s11227-025-08034-8"},"language":"en","primary_location":{"id":"doi:10.1007/s11227-025-08034-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-025-08034-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11227-025-08034-8.pdf","source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11227-025-08034-8.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023268855","display_name":"Muhammad Syafiq Mohd Pozi","orcid":"https://orcid.org/0000-0001-9379-7351"},"institutions":[{"id":"https://openalex.org/I94625822","display_name":"Northern University of Malaysia","ror":"https://ror.org/01ss10648","country_code":"MY","type":"education","lineage":["https://openalex.org/I94625822"]}],"countries":["MY"],"is_corresponding":true,"raw_author_name":"Muhammad Syafiq Mohd Pozi","raw_affiliation_strings":["School of Computing, Universiti Utara Malaysia, UUM Sintok, 06010, Bukit Kayu Hitam, Kedah, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, Universiti Utara Malaysia, UUM Sintok, 06010, Bukit Kayu Hitam, Kedah, Malaysia","institution_ids":["https://openalex.org/I94625822"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038208057","display_name":"Yukinori Sato","orcid":null},"institutions":[{"id":"https://openalex.org/I136259955","display_name":"Toyohashi University of Technology","ror":"https://ror.org/04ezg6d83","country_code":"JP","type":"education","lineage":["https://openalex.org/I136259955"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yukinori Sato","raw_affiliation_strings":["Department of Computer Science and Engineering, Toyohashi University of Technology, Toyohashi, Aichi, 441-8580, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Toyohashi University of Technology, Toyohashi, Aichi, 441-8580, Japan","institution_ids":["https://openalex.org/I136259955"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5023268855","https://openalex.org/A5038208057"],"corresponding_institution_ids":["https://openalex.org/I136259955","https://openalex.org/I94625822"],"apc_list":{"value":3290,"currency":"USD","value_usd":3290},"apc_paid":{"value":3290,"currency":"USD","value_usd":3290},"fwci":3.2837,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.92793766,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"81","issue":"17","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.25540000200271606,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.25540000200271606,"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/T14347","display_name":"Big Data and Digital Economy","score":0.19269999861717224,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.05480000004172325,"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/software-deployment","display_name":"Software deployment","score":0.824999988079071},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7174000144004822},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.5429999828338623},{"id":"https://openalex.org/keywords/inference-engine","display_name":"Inference engine","score":0.30250000953674316},{"id":"https://openalex.org/keywords/execution-time","display_name":"Execution time","score":0.2856000065803528},{"id":"https://openalex.org/keywords/routing-algorithm","display_name":"Routing algorithm","score":0.27549999952316284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9125999808311462},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.824999988079071},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7174000144004822},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5529000163078308},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.5429999828338623},{"id":"https://openalex.org/C46743427","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference engine","level":3,"score":0.30250000953674316},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C2984173633","wikidata":"https://www.wikidata.org/wiki/Q22725","display_name":"Routing algorithm","level":4,"score":0.27549999952316284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27070000767707825},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.26669999957084656},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C104954878","wikidata":"https://www.wikidata.org/wiki/Q1648707","display_name":"Routing protocol","level":3,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11227-025-08034-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-025-08034-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11227-025-08034-8.pdf","source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11227-025-08034-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-025-08034-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11227-025-08034-8.pdf","source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6342574221","display_name":null,"funder_award_id":"JPNP20017","funder_id":"https://openalex.org/F4320321680","funder_display_name":"New Energy and Industrial Technology Development Organization"}],"funders":[{"id":"https://openalex.org/F4320309591","display_name":"Universiti Utara Malaysia","ror":"https://ror.org/01ss10648"},{"id":"https://openalex.org/F4320321680","display_name":"New Energy and Industrial Technology Development Organization","ror":"https://ror.org/0055k7a87"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416298066.pdf","grobid_xml":"https://content.openalex.org/works/W4416298066.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W3176923149","https://openalex.org/W3198685994","https://openalex.org/W4284676027","https://openalex.org/W4385825586","https://openalex.org/W4389519587","https://openalex.org/W4389520201","https://openalex.org/W4389524484","https://openalex.org/W4392266005","https://openalex.org/W4400680805","https://openalex.org/W4401943776"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Large":[1],"language":[2],"model":[3,37],"(LLM)-based":[4],"program":[5],"generation":[6],"tasks":[7],"are":[8],"hindered":[9],"by":[10],"high":[11,18],"computational":[12,90],"demands.":[13],"These":[14],"challenges,":[15],"along":[16],"with":[17],"deployment":[19],"costs,":[20],"often":[21],"pose":[22],"a":[23,33,51,56],"barrier":[24],"to":[25,63,69],"practical":[26],"applications.":[27],"To":[28],"address":[29],"these,":[30],"we":[31],"propose":[32],"novel":[34],"data-augmented":[35],"multi-LLM":[36],"routing":[38],"approach":[39],"that":[40],"classifies":[41],"prompts":[42,85],"based":[43],"on":[44,50],"whether":[45],"they":[46],"should":[47],"be":[48],"processed":[49],"weak":[52],"LLM":[53],"engine":[54],"or":[55],"strong":[57],"LLM.":[58],"Experimental":[59],"results":[60],"show":[61],"up":[62],"16":[64],"times":[65],"better":[66],"efficiency":[67],"compared":[68],"the":[70,76,80],"existing":[71],"cascaded":[72],"approaches,":[73],"while":[74,92],"preserving":[75],"inference":[77,94],"accuracy.":[78,95],"Thus,":[79],"proposed":[81],"method":[82],"optimally":[83],"allocates":[84],"across":[86],"multiple":[87],"LLMs,":[88],"reducing":[89],"costs":[91],"maintaining":[93]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-08-25T07:29:55.448023","created_date":"2025-11-17T00:00:00"}