{"id":"https://openalex.org/W7163530043","doi":"https://doi.org/10.23919/date69613.2026.11539693","title":"ACES: A Chiplet Architecture with Resource Partition and Dynamic Scheduling for Agentic LLMs","display_name":"ACES: A Chiplet Architecture with Resource Partition and Dynamic Scheduling for Agentic LLMs","publication_year":2026,"publication_date":"2026-04-20","ids":{"openalex":"https://openalex.org/W7163530043","doi":"https://doi.org/10.23919/date69613.2026.11539693"},"language":null,"primary_location":{"id":"doi:10.23919/date69613.2026.11539693","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date69613.2026.11539693","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 Design, Automation &amp;amp; Test in Europe Conference (DATE)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127929751","display_name":"Hongou Li","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongou Li","raw_affiliation_strings":["Peking University,School of Integrated Circuits,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,School of Integrated Circuits,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134953472","display_name":"Mingxuan Li","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingxuan Li","raw_affiliation_strings":["Peking University,School of Integrated Circuits,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,School of Integrated Circuits,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107701748","display_name":"Zhantong Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhantong Zhu","raw_affiliation_strings":["Peking University,School of Integrated Circuits,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,School of Integrated Circuits,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110334813","display_name":"Tianyu Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyu Jia","raw_affiliation_strings":["Peking University,School of Integrated Circuits,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,School of Integrated Circuits,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"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":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.14010000228881836,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.14010000228881836,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.1266999989748001,"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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.06069999933242798,"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/scheduling","display_name":"Scheduling (production processes)","score":0.5819000005722046},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5059999823570251},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.46779999136924744},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.3246999979019165},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2782999873161316}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6219000220298767},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5819000005722046},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5059999823570251},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.46779999136924744},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3246999979019165},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.3010999858379364},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.2953000068664551},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.29019999504089355},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2838999927043915},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.275299996137619},{"id":"https://openalex.org/C107568181","wikidata":"https://www.wikidata.org/wiki/Q5319000","display_name":"Dynamic priority scheduling","level":3,"score":0.2639999985694885},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2621999979019165},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/date69613.2026.11539693","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date69613.2026.11539693","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 Design, Automation &amp;amp; Test in Europe Conference (DATE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W3190062760","https://openalex.org/W4296209134","https://openalex.org/W4381886086","https://openalex.org/W4387321091","https://openalex.org/W4392746141","https://openalex.org/W4401211704","https://openalex.org/W4402475847","https://openalex.org/W4402671542","https://openalex.org/W4404739475","https://openalex.org/W4409248344","https://openalex.org/W4411486513","https://openalex.org/W4412931388","https://openalex.org/W4412987431","https://openalex.org/W4413411859","https://openalex.org/W4415799217","https://openalex.org/W4416963676"],"related_works":[],"abstract_inverted_index":{"Agentic":[0],"LLM":[1,23],"is":[2,62,83],"an":[3,127],"emerging":[4],"working":[5],"paradigm":[6],"leveraging":[7,44],"large":[8],"language":[9],"models":[10,110],"(LLMs)":[11],"as":[12],"assistant":[13],"agents":[14,24],"for":[15,53],"complex,":[16],"multi-step":[17],"tasks.":[18,114],"However,":[19],"the":[20,59],"operations":[21],"of":[22],"also":[25],"create":[26],"unique":[27],"workload":[28,51],"characteristics":[29],"with":[30,49,69],"highly":[31],"dynamic":[32,50,80],"resource":[33,93,101],"demands.":[34],"In":[35],"this":[36],"work,":[37],"we":[38],"propose":[39],"ACES,":[40],"a":[41,66,78],"co-designed":[42],"solution":[43],"scalable":[45],"chiplet":[46,60,137],"architecture":[47,61,106],"together":[48],"scheduling":[52,81],"agentic":[54],"LLMs.":[55],"At":[56],"hardware":[57],"level,":[58,77],"designed":[63],"to":[64,95,97,134],"support":[65],"zoned":[67],"fabric":[68],"flexible":[70],"Swing":[71],"Zones.":[72],"Upon":[73],"this,":[74],"at":[75],"software":[76],"conversation-centric":[79],"approach":[82],"adopted,":[84],"which":[85],"includes":[86],"topology-aware":[87],"homing,":[88],"proactive":[89],"caching,":[90],"and":[91,100,126,142],"adaptive":[92],"conversion":[94],"accommodate":[96],"data":[98],"locality":[99],"balance.":[102],"We":[103],"evaluate":[104],"our":[105,120],"using":[107],"Llama-3":[108],"8B":[109],"on":[111],"representative":[112],"agentic-RAG-derived":[113],"The":[115],"system":[116],"evaluations":[117],"demonstrate":[118],"that":[119],"design":[121],"achieves":[122],"2.33\u00d7":[123],"throughput":[124],"improvement":[125],"average":[128],"58%":[129],"conversation":[130],"latency":[131],"reduction":[132],"compared":[133],"state-of-the-art":[135],"DistServe-like":[136],"baselines,":[138],"showcasing":[139],"superior":[140],"performance":[141],"scalability.":[143]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-06-05T00:00:00"}
