{"id":"https://openalex.org/W7161039234","doi":"https://doi.org/10.1145/3745756.3809195","title":"Agent-X: Full Pipeline Acceleration of On-device AI Agents","display_name":"Agent-X: Full Pipeline Acceleration of On-device AI Agents","publication_year":2026,"publication_date":"2026-05-29","ids":{"openalex":"https://openalex.org/W7161039234","doi":"https://doi.org/10.1145/3745756.3809195"},"language":null,"primary_location":{"id":"doi:10.1145/3745756.3809195","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3745756.3809195","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 24th Annual International Conference on Mobile Systems, Applications and Services","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3745756.3809195","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135930425","display_name":"Jinha Chung","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jinha Chung","raw_affiliation_strings":["KAIST, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-5652-604X","affiliations":[{"raw_affiliation_string":"KAIST, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135958522","display_name":"Byeongjun Shin","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byeongjun Shin","raw_affiliation_strings":["KAIST, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0005-6443-4398","affiliations":[{"raw_affiliation_string":"KAIST, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135979325","display_name":"Jiin Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jiin Kim","raw_affiliation_strings":["KAIST, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0003-1297-1509","affiliations":[{"raw_affiliation_string":"KAIST, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091648103","display_name":"Minsoo Rhu","orcid":"https://orcid.org/0000-0003-3303-8681"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minsoo Rhu","raw_affiliation_strings":["KAIST, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-3303-8681","affiliations":[{"raw_affiliation_string":"KAIST, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":0.75675676,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"144","last_page":"157"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.12229999899864197,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.12229999899864197,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.09520000219345093,"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"}},{"id":"https://openalex.org/T11424","display_name":"Security and Verification in Computing","score":0.07819999754428864,"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/security-token","display_name":"Security token","score":0.7422999739646912},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6295999884605408},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.60589998960495},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5893999934196472},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5720000267028809},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4837999939918518},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4699999988079071},{"id":"https://openalex.org/keywords/prefix","display_name":"Prefix","score":0.4268999993801117}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8184999823570251},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7422999739646912},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6295999884605408},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.60589998960495},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5893999934196472},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5720000267028809},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4837999939918518},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4699999988079071},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4537999927997589},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.4268999993801117},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.42489999532699585},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.3968999981880188},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.3698999881744385},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.35280001163482666},{"id":"https://openalex.org/C147297375","wikidata":"https://www.wikidata.org/wiki/Q6674930","display_name":"Look-ahead","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.33219999074935913},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.30649998784065247},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.2890999913215637},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2712000012397766},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2671000063419342},{"id":"https://openalex.org/C3913047","wikidata":"https://www.wikidata.org/wiki/Q1956265","display_name":"sync","level":3,"score":0.26420000195503235},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3745756.3809195","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3745756.3809195","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 24th Annual International Conference on Mobile Systems, Applications and Services","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2605.10380","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.10380","pdf_url":"https://arxiv.org/pdf/2605.10380","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3745756.3809195","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3745756.3809195","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 24th Annual International Conference on Mobile Systems, Applications and Services","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3525134573","display_name":null,"funder_award_id":"RS-2024-00457882","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G450777280","display_name":null,"funder_award_id":"RS-2025-02214652","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G5704809196","display_name":null,"funder_award_id":"RS-2024-00457882","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G6281998519","display_name":null,"funder_award_id":"RS-2024-00395134","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G6647357998","display_name":null,"funder_award_id":"RS-2025-02214652","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G7822388480","display_name":null,"funder_award_id":"RS-2024-00395134","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"LLM-based":[0],"agents":[1],"deliver":[2],"state-of-the-art":[3],"performance":[4],"across":[5],"tasks":[6],"but":[7],"incur":[8],"high":[9],"end-to-end":[10,69],"latency":[11,103],"on":[12],"edge":[13],"devices.":[14],"We":[15],"introduce":[16],"Agent-X,":[17],"a":[18,67],"software-only,":[19],"accuracy-preserving":[20],"framework":[21],"that":[22],"accelerates":[23],"both":[24],"the":[25,89,96],"prefill":[26],"and":[27,49,78,101],"decode":[28],"stages":[29],"of":[30,91],"on-device":[31,85,106],"agent":[32],"workloads.":[33],"Agent-X's":[34],"two":[35],"key":[36],"components":[37],"rewrite":[38],"prompts":[39],"to":[40,45,98],"leverage":[41],"prefix":[42],"caching":[43],"tailored":[44],"agent-specific":[46],"input-token":[47],"patterns":[48],"enable":[50],"LLM-free":[51],"speculative":[52],"decoding":[53],"for":[54],"fast":[55],"token":[56],"generation":[57],"with":[58,74],"minimal":[59],"overhead.":[60],"On":[61],"representative":[62],"agentic":[63],"workloads,":[64],"Agent-X":[65],"achieves":[66],"1.61\u00d7":[68],"speedup":[70],"in":[71,105],"real":[72],"systems":[73],"no":[75],"accuracy":[76],"loss":[77],"can":[79],"be":[80],"seamlessly":[81],"integrated":[82],"into":[83],"existing":[84],"AI":[86],"agents.":[87,107],"To":[88],"best":[90],"our":[92],"knowledge,":[93],"ours":[94],"is":[95],"first":[97],"systematically":[99],"characterize":[100],"eliminate":[102],"bottlenecks":[104]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-14T00:00:00"}
