{"id":"https://openalex.org/W4416749229","doi":"https://doi.org/10.1109/iros60139.2025.11247595","title":"ContextCache: Task-Aware Lifecycle Management for Memory-Efficient LLM Agent Deployment","display_name":"ContextCache: Task-Aware Lifecycle Management for Memory-Efficient LLM Agent Deployment","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749229","doi":"https://doi.org/10.1109/iros60139.2025.11247595"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247595","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247595","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","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/A5028842878","display_name":"Tao Liu","orcid":"https://orcid.org/0000-0002-3568-4882"},"institutions":[{"id":"https://openalex.org/I2970213756","display_name":"Alltech (United States)","ror":"https://ror.org/01gh6ja41","country_code":"US","type":"company","lineage":["https://openalex.org/I2970213756"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tao Liu","raw_affiliation_strings":["InchiTech,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"InchiTech,Nanjing,China","institution_ids":["https://openalex.org/I2970213756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066240938","display_name":"Ping Guo","orcid":"https://orcid.org/0000-0002-5239-8896"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ping Guo","raw_affiliation_strings":["Intel Labs China,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Intel Labs China,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dong Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I2970213756","display_name":"Alltech (United States)","ror":"https://ror.org/01gh6ja41","country_code":"US","type":"company","lineage":["https://openalex.org/I2970213756"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Feng","raw_affiliation_strings":["InchiTech,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"InchiTech,Nanjing,China","institution_ids":["https://openalex.org/I2970213756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108049097","display_name":"Peng Wang","orcid":"https://orcid.org/0000-0002-5223-7515"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng Wang","raw_affiliation_strings":["Intel Labs China,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Intel Labs China,Beijing,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5028842878"],"corresponding_institution_ids":["https://openalex.org/I2970213756"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.48866965,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11271","last_page":"11276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14347","display_name":"Big Data and Digital Economy","score":0.065700002014637,"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/T14347","display_name":"Big Data and Digital Economy","score":0.065700002014637,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.06319999694824219,"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.051899999380111694,"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":0.6646000146865845},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.6391000151634216},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5604000091552734},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5375999808311462},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4925999939441681},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45500001311302185},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.40639999508857727},{"id":"https://openalex.org/keywords/context-management","display_name":"Context management","score":0.3962000012397766},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.3659999966621399}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8001999855041504},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6646000146865845},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.6391000151634216},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5604000091552734},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5375999808311462},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4925999939441681},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4790000021457672},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45500001311302185},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4278999865055084},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.40639999508857727},{"id":"https://openalex.org/C2776285913","wikidata":"https://www.wikidata.org/wiki/Q5165183","display_name":"Context management","level":3,"score":0.3962000012397766},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3747999966144562},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3659999966621399},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3538999855518341},{"id":"https://openalex.org/C30452754","wikidata":"https://www.wikidata.org/wiki/Q621590","display_name":"Application lifecycle management","level":3,"score":0.34929999709129333},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3246000111103058},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C9616225","wikidata":"https://www.wikidata.org/wiki/Q3929429","display_name":"Semantic reasoner","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C53833338","wikidata":"https://www.wikidata.org/wiki/Q1061424","display_name":"Context switch","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C35280785","wikidata":"https://www.wikidata.org/wiki/Q559486","display_name":"System lifecycle","level":4,"score":0.2939000129699707},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.2854999899864197},{"id":"https://openalex.org/C7465953","wikidata":"https://www.wikidata.org/wiki/Q1572577","display_name":"Product life-cycle management","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.28029999136924744},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.2671000063419342},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C46743427","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference engine","level":3,"score":0.2583000063896179},{"id":"https://openalex.org/C82687282","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Auxiliary memory","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.25459998846054077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247595","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247595","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":12,"referenced_works":["https://openalex.org/W3112116031","https://openalex.org/W4232896595","https://openalex.org/W4385562710","https://openalex.org/W4387321091","https://openalex.org/W4387567460","https://openalex.org/W4396918564","https://openalex.org/W4398217369","https://openalex.org/W4402671542","https://openalex.org/W4405787555","https://openalex.org/W4406800520","https://openalex.org/W4406892690","https://openalex.org/W4408848702"],"related_works":[],"abstract_inverted_index":{"LLM-based":[0],"agents":[1,23],"have":[2],"demonstrated":[3],"remarkable":[4],"capabilities":[5],"in":[6,55,128,139,149],"multi-step":[7,86],"reasoning":[8],"and":[9,17,97,100,119],"task":[10],"execution":[11],"across":[12,66],"domains":[13],"such":[14],"as":[15],"robotics":[16],"autonomous":[18],"systems.":[19],"However,":[20],"deploying":[21],"these":[22],"on":[24,109],"resource-constrained":[25,150],"platforms":[26],"presents":[27],"a":[28,75,110,125],"fundamental":[29],"challenge:":[30],"minimizing":[31],"latency":[32],"while":[33],"optimizing":[34],"memory":[35,61,103,129],"usage.":[36],"Existing":[37],"caching":[38,84,134],"techniques":[39],"(KVCache,":[40],"PrefixCache,":[41],"PromptCache)":[42],"improve":[43],"inference":[44,140],"speed":[45],"by":[46],"reusing":[47],"cached":[48],"context":[49,82,95],"but":[50],"overlook":[51],"LLM":[52,67,87],"dependency":[53],"relationships":[54],"agent":[56],"workflows,":[57],"leading":[58],"to":[59,132],"excessive":[60],"usage":[62,130],"or":[63],"redundant":[64],"recomputation":[65],"calls.":[68],"To":[69],"address":[70],"this,":[71],"we":[72],"propose":[73],"ContextCache,":[74],"task-aware":[76],"lifecycle":[77],"management":[78],"framework":[79],"that":[80],"optimizes":[81],"fragment":[83,96],"for":[85,146],"agents.":[88],"ContextCache":[89],"predicts":[90],"the":[91],"lifespan":[92],"of":[93],"each":[94],"dynamically":[98],"allocates":[99],"releases":[101],"GPU":[102],"accordingly.":[104],"We":[105],"evaluate":[106],"our":[107,143],"approach":[108,144],"newly":[111],"constructed":[112],"dataset,":[113],"covering":[114],"logistics":[115],"coordination,":[116],"assembly":[117],"tasks,":[118],"health":[120],"management.":[121],"Experimental":[122],"results":[123],"demonstrate":[124],"15%":[126],"reduction":[127],"compared":[131],"state-of-the-art":[133],"strategies,":[135],"with":[136],"no":[137],"loss":[138],"efficiency,":[141],"making":[142],"well-suited":[145],"real-world":[147],"deployment":[148],"environments.":[151]},"counts_by_year":[],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-11-28T00:00:00"}