{"id":"https://openalex.org/W7154309840","doi":"https://doi.org/10.48550/arxiv.2604.11610","title":"Self-Evolving LLM Memory Extraction Across Heterogeneous Tasks","display_name":"Self-Evolving LLM Memory Extraction Across Heterogeneous Tasks","publication_year":2026,"publication_date":"2026-04-13","ids":{"openalex":"https://openalex.org/W7154309840","doi":"https://doi.org/10.48550/arxiv.2604.11610"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.11610","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.11610","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.11610","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133623765","display_name":"Yuqing Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yuqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133593340","display_name":"Tengxiao Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Tengxiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112120097","display_name":"Wang Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Wang Bill","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133564817","display_name":"Taiwei Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Taiwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133610820","display_name":"Linxin Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Linxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133596091","display_name":"Robin Jia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia, Robin","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":0.6269000172615051,"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":0.6269000172615051,"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/T12128","display_name":"AI in Service Interactions","score":0.06769999861717224,"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":0.029100000858306885,"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/task","display_name":"Task (project management)","score":0.746999979019165},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6916999816894531},{"id":"https://openalex.org/keywords/homogeneous","display_name":"Homogeneous","score":0.6542999744415283},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5916000008583069},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5788999795913696},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.3856000006198883},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.37959998846054077},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.37689998745918274}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7741000056266785},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.746999979019165},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6916999816894531},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.6542999744415283},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5916000008583069},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5788999795913696},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5293999910354614},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4578000009059906},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40209999680519104},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3856000006198883},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.37959998846054077},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.37689998745918274},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.3553999960422516},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.33410000801086426},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.298799991607666},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27649998664855957},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2583000063896179}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.11610","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.11610","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.11610","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.11610","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"LLM-based":[1],"assistants":[2],"become":[3],"persistent":[4],"and":[5,10,37,50,76,117],"personalized,":[6],"they":[7],"must":[8],"extract":[9],"retain":[11],"useful":[12],"information":[13,23],"from":[14],"past":[15],"conversations":[16],"as":[17],"memory.":[18],"However,":[19],"the":[20,32,123],"types":[21],"of":[22],"worth":[24],"remembering":[25],"vary":[26],"considerably":[27],"across":[28,72,134],"tasks.":[29],"We":[30],"formalize":[31],"\\textit{heterogeneous":[33],"memory":[34],"extraction}":[35],"task":[36,74],"introduce":[38],"\\textbf{BEHEMOTH},":[39],"a":[40,54,100],"benchmark":[41],"that":[42,65,77,104,130],"repurposes":[43],"18":[44],"existing":[45,78],"datasets":[46],"spanning":[47],"personalization,":[48],"problem-solving,":[49],"agentic":[51],"tasks,":[52],"using":[53],"downstream":[55],"utility-driven":[56],"metric":[57],"for":[58,85],"systematic":[59],"evaluation.":[60],"Our":[61],"empirical":[62],"analysis":[63],"confirms":[64],"no":[66],"single":[67],"static":[68],"extraction":[69,111,124],"prompt":[70,80],"dominates":[71],"all":[73],"categories,":[75],"self-evolving":[79,102,143],"optimization":[81],"frameworks,":[82],"originally":[83],"designed":[84],"homogeneous":[86],"distributions,":[87],"degrade":[88],"when":[89],"training":[90,106],"tasks":[91,136],"are":[92],"heterogeneous.":[93],"To":[94],"address":[95],"this,":[96],"we":[97],"propose":[98],"\\textbf{CluE},":[99],"cluster-based":[101],"strategy":[103],"groups":[105],"examples":[107],"into":[108],"clusters":[109],"by":[110],"scenarios,":[112],"analyzes":[113],"each":[114],"cluster":[115],"independently,":[116],"synthesizes":[118],"cross-cluster":[119],"insights":[120],"to":[121],"update":[122],"prompt.":[125],"Experiments":[126],"on":[127],"BEHEMOTH":[128],"show":[129],"CluE":[131],"generalizes":[132],"effectively":[133],"heterogeneous":[135],"($+$9.04\\%":[137],"relative":[138],"gain),":[139],"consistently":[140],"outperforming":[141],"prior":[142],"frameworks.":[144]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-15T00:00:00"}