{"id":"https://openalex.org/W7134913827","doi":"https://doi.org/10.48550/arxiv.2603.09297","title":"TA-Mem: Tool-Augmented Autonomous Memory Retrieval for LLM in Long-Term Conversational QA","display_name":"TA-Mem: Tool-Augmented Autonomous Memory Retrieval for LLM in Long-Term Conversational QA","publication_year":2026,"publication_date":"2026-03-10","ids":{"openalex":"https://openalex.org/W7134913827","doi":"https://doi.org/10.48550/arxiv.2603.09297"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.09297","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.09297","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.09297","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127910971","display_name":"Mengwei Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yuan, Mengwei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128700696","display_name":"Jianan Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Jianan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128730066","display_name":"Jing Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Jing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034388453","display_name":"Xianyou Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xianyou","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102381470","display_name":"Weiran Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Weiran","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128797687","display_name":"Yichao Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Yichao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128702778","display_name":"Penghao Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Penghao","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5127910971"],"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":0.7706999778747559,"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":0.7706999778747559,"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/T13629","display_name":"Text Readability and Simplification","score":0.04360000044107437,"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":0.02539999969303608,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/semantic-memory","display_name":"Semantic memory","score":0.5235999822616577},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.47519999742507935},{"id":"https://openalex.org/keywords/episodic-memory","display_name":"Episodic memory","score":0.4700999855995178},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.46869999170303345},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.451200008392334},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.40849998593330383},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.3928000032901764},{"id":"https://openalex.org/keywords/memory-model","display_name":"Memory model","score":0.3571000099182129}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8564000129699707},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.5235999822616577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4918000102043152},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.47519999742507935},{"id":"https://openalex.org/C88576662","wikidata":"https://www.wikidata.org/wiki/Q18646","display_name":"Episodic memory","level":3,"score":0.4700999855995178},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.46869999170303345},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.451200008392334},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.40849998593330383},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3984000086784363},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39719998836517334},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.3928000032901764},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.3571000099182129},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3111000061035156},{"id":"https://openalex.org/C82687282","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Auxiliary memory","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28200000524520874},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27559998631477356},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.2678000032901764},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C551230270","wikidata":"https://www.wikidata.org/wiki/Q4368942","display_name":"Data retrieval","level":2,"score":0.263700008392334}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.09297","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.09297","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.09297","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.09297","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"score":0.47203949093818665,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Model":[2],"(LLM)":[3],"has":[4],"exhibited":[5],"strong":[6],"reasoning":[7,165],"ability":[8],"in":[9],"text-based":[10],"contexts":[11],"across":[12,193],"various":[13],"domains,":[14],"yet":[15],"the":[16,24,135,144,148,157,162,167,175,199,202],"limitation":[17],"of":[18,50,117,190,201],"context":[19],"window":[20],"poses":[21],"challenges":[22],"for":[23,114],"model":[25],"on":[26,57,99,147,166,174],"long-range":[27],"inference":[28],"tasks":[29],"and":[30,47,102,124,151],"necessitates":[31],"a":[32,72,83,109,128],"memory":[33,76,84,111,130,136],"storage":[34,39],"system.":[35],"While":[36],"many":[37],"current":[38],"approaches":[40],"have":[41],"been":[42],"proposed":[43,203],"with":[44],"episodic":[45],"notes":[46],"graph":[48],"representations":[49],"memory,":[51],"retrieval":[52,77,131],"methods":[53,119],"still":[54],"primarily":[55],"rely":[56],"predefined":[58],"workflows":[59],"or":[60,160],"static":[61],"similarity":[62],"top-k":[63],"over":[64,182],"embeddings.":[65],"To":[66],"address":[67],"this":[68],"inflexibility,":[69],"we":[70],"introduced":[71],"novel":[73],"tool-augmented":[74,129],"autonomous":[75],"framework":[78],"(TA-Mem),":[79],"which":[80,88,133],"contains:":[81],"(1)":[82],"extraction":[85],"LLM":[86],"agent":[87,132],"is":[89,172],"prompted":[90],"to":[91,154,156],"adaptively":[92],"chuck":[93],"an":[94,188],"input":[95],"into":[96,105],"sub-context":[97],"based":[98,146],"semantic":[100],"correlation,":[101],"extract":[103],"information":[104],"structured":[106],"notes,":[107],"(2)":[108],"multi-indexed":[110],"database":[112,145],"designed":[113],"different":[115,194],"types":[116,196],"query":[118],"including":[120],"both":[121],"key-based":[122],"lookup":[123],"similarity-based":[125],"retrieval,":[126],"(3)":[127],"explores":[134],"autonomously":[137],"by":[138,143],"selecting":[139],"appropriate":[140],"tools":[141],"provided":[142],"user":[149],"input,":[150],"decides":[152],"whether":[153],"proceed":[155],"next":[158],"iteration":[159],"finalizing":[161],"response":[163],"after":[164],"fetched":[168],"memories.":[169],"The":[170],"TA-Mem":[171],"evaluated":[173],"LoCoMo":[176],"dataset,":[177],"achieving":[178],"significant":[179],"performance":[180],"improvements":[181],"existing":[183],"baseline":[184],"approaches.":[185],"In":[186],"addition,":[187],"analysis":[189],"tool":[191],"use":[192],"question":[195],"also":[197],"demonstrates":[198],"adaptivity":[200],"method.":[204]},"counts_by_year":[],"updated_date":"2026-03-12T06:18:43.230356","created_date":"2026-03-12T00:00:00"}