{"id":"https://openalex.org/W7155506625","doi":"https://doi.org/10.1145/3767295.3803622","title":"AIMS: Cost-Efficient LLM-Based Agent Deployment in Hybrid Cloud-Edge Environments","display_name":"AIMS: Cost-Efficient LLM-Based Agent Deployment in Hybrid Cloud-Edge Environments","publication_year":2026,"publication_date":"2026-04-24","ids":{"openalex":"https://openalex.org/W7155506625","doi":"https://doi.org/10.1145/3767295.3803622"},"language":null,"primary_location":{"id":"doi:10.1145/3767295.3803622","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767295.3803622","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 21st European Conference on Computer Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3767295.3803622","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100736544","display_name":"Shiyi Liu","orcid":"https://orcid.org/0000-0002-0990-5303"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiyi Liu","raw_affiliation_strings":["University of Virginia, Charlottesville, VA, USA"],"raw_orcid":"https://orcid.org/0000-0001-7611-319X","affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050569064","display_name":"Haiying Shen","orcid":"https://orcid.org/0000-0002-7548-6223"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haiying Shen","raw_affiliation_strings":["University of Virginia, Charlottesville, VA, USA"],"raw_orcid":"https://orcid.org/0000-0002-7548-6223","affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018356320","display_name":"Shuai Che","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuai Che","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3192-3057","affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087254129","display_name":"Mahdi Ghandi","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahdi Ghandi","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0009-0003-7600-0488","affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103208235","display_name":"Mingqin Li","orcid":"https://orcid.org/0009-0002-0270-9489"},"institutions":[{"id":"https://openalex.org/I174135032","display_name":"Bellevue College","ror":"https://ror.org/05gr4yv49","country_code":"US","type":"education","lineage":["https://openalex.org/I174135032"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mingqin Li","raw_affiliation_strings":["Shopify, Bellevue, WA, USA"],"raw_orcid":"https://orcid.org/0000-0001-8103-3581","affiliations":[{"raw_affiliation_string":"Shopify, Bellevue, WA, USA","institution_ids":["https://openalex.org/I174135032"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.52969747,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1862","last_page":"1878"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.23880000412464142,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.23880000412464142,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.09749999642372131,"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/T12203","display_name":"Mobile Agent-Based Network Management","score":0.06939999759197235,"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/software-deployment","display_name":"Software deployment","score":0.41179999709129333},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.32269999384880066},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.3181000053882599},{"id":"https://openalex.org/keywords/troubleshooting","display_name":"Troubleshooting","score":0.2791999876499176},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.2623000144958496},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.25679999589920044}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5662999749183655},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.41179999709129333},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C147494362","wikidata":"https://www.wikidata.org/wiki/Q2078905","display_name":"Troubleshooting","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.267300009727478},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3767295.3803622","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767295.3803622","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 21st European Conference on Computer Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3767295.3803622","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767295.3803622","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 21st European Conference on Computer Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W4388626886"],"related_works":[],"abstract_inverted_index":{"In":[0,91],"the":[1,13,21,36,68,101,112,136,143,159,206],"realm":[2],"of":[3,15,38,55,103,192],"AI,":[4],"large":[5],"language":[6,30],"models":[7,31],"(LLMs)":[8],"like":[9],"GPT-5,":[10],"central":[11],"to":[12,48,71,99,121,150,170,179,187,194],"operation":[14],"AI":[16,45,80,104,125],"agents,":[17],"predominantly":[18],"operate":[19],"in":[20,148,175,183],"cloud,":[22],"incurring":[23],"high":[24],"operational":[25],"costs.":[26],"With":[27],"local-based":[28,129],"small":[29],"(SLMs)":[32],"becoming":[33],"more":[34],"accurate,":[35],"necessity":[37],"cloud-exclusive":[39],"processing":[40],"is":[41,77],"being":[42],"reconsidered.":[43],"An":[44],"agent's":[46,126],"response":[47],"a":[49,53,118,171,195],"user's":[50],"request":[51,70],"comprises":[52],"series":[54],"subtasks":[56,127,193],"or":[57,65],"iterations.":[58],"Existing":[59],"approaches":[60],"choose":[61],"either":[62],"an":[63,124],"LLM":[64,208],"SLM":[66,130,152,184,197],"for":[67,79,145],"entire":[69],"ensure":[72],"similar":[73,200],"outputs,":[74],"but":[75],"this":[76,92],"ineffective":[78],"agents":[81],"as":[82,153,155],"SLMs":[83],"may":[84],"generate":[85],"differing":[86],"subtasks,":[87],"compromising":[88],"final":[89],"accuracy.":[90],"paper,":[93],"we":[94,110],"first":[95],"conduct":[96],"experimental":[97,163],"analysis":[98],"understand":[100],"features":[102,139],"agent":[105],"operations.":[106],"Leveraging":[107],"our":[108],"findings,":[109],"propose":[111],"Adaptive":[113],"Iteration-level":[114],"Model":[115],"Selector":[116],"(AIMS),":[117],"lightweight":[119],"scheduler":[120],"automatically":[122],"partition":[123],"between":[128],"and":[131,140,177],"cloud-based":[132],"LLM.":[133],"AIMS":[134,167],"considers":[135],"varying":[137],"subtask":[138,147],"strategically":[141],"decides":[142],"location":[144],"each":[146],"order":[149],"use":[151],"much":[154],"possible":[156],"while":[157,198],"maintaining":[158],"accuracy":[160,176,201],"level.":[161],"Our":[162],"results":[164],"demonstrate":[165],"that":[166],"achieves":[168],"up":[169,178],"27.5%":[172],"relative":[173,181],"improvement":[174],"31.4%":[180],"increase":[182],"usage":[185],"compared":[186,204],"HybridLLM.":[188],"It":[189],"offloads":[190],"83.4%":[191],"local":[196],"attaining":[199],"on":[202],"average":[203],"with":[205],"cloud-only":[207],"approach.":[209]},"counts_by_year":[],"updated_date":"2026-04-26T06:01:38.667478","created_date":"2026-04-25T00:00:00"}