{"id":"https://openalex.org/W7160899042","doi":"https://doi.org/10.48550/arxiv.2605.08538","title":"Human-Inspired Memory Architecture for LLM Agents","display_name":"Human-Inspired Memory Architecture for LLM Agents","publication_year":2026,"publication_date":"2026-05-08","ids":{"openalex":"https://openalex.org/W7160899042","doi":"https://doi.org/10.48550/arxiv.2605.08538"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.08538","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.08538","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.08538","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017560288","display_name":"Doga Kerestecioglu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kerestecioglu, Doga","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093331232","display_name":"Alexei Robsky","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Robsky, Alexei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135948527","display_name":"Clemens Vasters","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vasters, Clemens","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135958039","display_name":"Anshul Sharma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sharma, Anshul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135983972","display_name":"Yitzhak Kesselman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kesselman, Yitzhak","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.22499999403953552,"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/T10028","display_name":"Topic Modeling","score":0.22499999403953552,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1680999994277954,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.06920000165700912,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.582099974155426},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5759000182151794},{"id":"https://openalex.org/keywords/memory-consolidation","display_name":"Memory consolidation","score":0.5759000182151794},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4530999958515167},{"id":"https://openalex.org/keywords/consolidation","display_name":"Consolidation (business)","score":0.39649999141693115},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.2994999885559082}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7599999904632568},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.582099974155426},{"id":"https://openalex.org/C48455012","wikidata":"https://www.wikidata.org/wiki/Q2892593","display_name":"Memory consolidation","level":3,"score":0.5759000182151794},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5759000182151794},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48669999837875366},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4530999958515167},{"id":"https://openalex.org/C2776014549","wikidata":"https://www.wikidata.org/wiki/Q3050847","display_name":"Consolidation (business)","level":2,"score":0.39649999141693115},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3763999938964844},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3450999855995178},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C82687282","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Auxiliary memory","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C2779602883","wikidata":"https://www.wikidata.org/wiki/Q15544750","display_name":"Memory architecture","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.257999986410141}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.08538","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.08538","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.08538","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.08538","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Current":[0],"LLM":[1],"agents":[2],"lack":[3],"principled":[4],"mechanisms":[5],"for":[6],"managing":[7],"persistent":[8],"memory":[9,18,55],"across":[10],"long":[11],"interaction":[12],"horizons.":[13],"We":[14,57,79],"present":[15],"a":[16,49,59,73,85,127,145,158],"biologically-grounded":[17],"architecture":[19],"comprising":[20],"six":[21],"cognitive":[22],"mechanisms:":[23],"(1)":[24],"sleep-phase":[25],"consolidation,":[26],"(2)":[27],"interference-based":[28],"forgetting,":[29],"(3)":[30],"engram":[31],"maturation,":[32],"(4)":[33],"reconsolidation":[34],"upon":[35],"retrieval,":[36],"(5)":[37],"entity":[38],"knowledge":[39],"graphs,":[40],"and":[41],"(6)":[42],"hybrid":[43],"multi-cue":[44],"retrieval.":[45],"Each":[46],"mechanism":[47],"addresses":[48],"specific":[50],"failure":[51],"mode":[52],"of":[53,76],"naive":[54],"accumulation.":[56],"introduce":[58],"synthetic":[60],"calibration":[61],"methodology":[62],"that":[63],"derives":[64],"all":[65],"pipeline":[66,132],"thresholds":[67],"without":[68],"benchmark":[69,112],"data":[70],"exposure,":[71],"eliminating":[72],"common":[74],"source":[75],"evaluation":[77,120],"leakage.":[78],"evaluate":[80],"on":[81],"two":[82],"benchmarks.":[83],"First,":[84],"VSCode":[86],"issue-tracking":[87],"dataset":[88],"(13K":[89],"issues,":[90],"120K":[91],"events)":[92],"where":[93,113],"deduplication-based":[94],"consolidation":[95,156],"achieves":[96],"97.2%":[97],"retention":[98],"precision":[99],"with":[100],"58%":[101],"store":[102],"reduction":[103],"(+21.8":[104],"pp":[105,160],"over":[106],"baseline).":[107],"Second,":[108],"the":[109,116],"LongMemEval":[110],"personal-chat":[111],"we":[114],"conduct":[115],"first":[117],"streaming":[118],"M-tier":[119],"(475":[121],"sessions,":[122],"~540K":[123],"unique":[124],"turns).":[125],"At":[126,150],"200K-token":[128],"context":[129],"budget,":[130],"our":[131],"matches":[133],"raw":[134],"retrieval":[135],"accuracy":[136],"(70.1%":[137],"vs.":[138],"71.2%,":[139],"overlapping":[140],"95%":[141],"CI)":[142],"while":[143],"exposing":[144],"tunable":[146],"accuracy/store-size":[147],"operating":[148],"curve.":[149],"S-tier":[151],"scale":[152],"(50":[153],"sessions),":[154],"dedup-based":[155],"yields":[157],"+13.3":[159],"improvement":[161],"in":[162],"preference":[163],"recall.":[164]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-13T00:00:00"}