{"id":"https://openalex.org/W7160904158","doi":"https://doi.org/10.48550/arxiv.2605.09942","title":"HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution","display_name":"HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution","publication_year":2026,"publication_date":"2026-05-11","ids":{"openalex":"https://openalex.org/W7160904158","doi":"https://doi.org/10.48550/arxiv.2605.09942"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.09942","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.09942","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.09942","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121536196","display_name":"Dongming Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Dongming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135963773","display_name":"Yi Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025726299","display_name":"Guanpeng Li","orcid":"https://orcid.org/0000-0001-7773-7826"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Guanpeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135970389","display_name":"Qiannan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Qiannan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5048972267","display_name":"Bingzhe Li","orcid":"https://orcid.org/0000-0002-5815-9706"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Bingzhe","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/T11273","display_name":"Advanced Graph Neural Networks","score":0.34299999475479126,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.34299999475479126,"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":0.32899999618530273,"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/T10028","display_name":"Topic Modeling","score":0.2054000049829483,"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/tree-traversal","display_name":"Tree traversal","score":0.8001000285148621},{"id":"https://openalex.org/keywords/binary-relation","display_name":"Binary relation","score":0.5748999714851379},{"id":"https://openalex.org/keywords/statistical-relational-learning","display_name":"Statistical relational learning","score":0.47440001368522644},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.40799999237060547},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.40400001406669617},{"id":"https://openalex.org/keywords/graph-traversal","display_name":"Graph traversal","score":0.3822000026702881},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.36500000953674316},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.3569999933242798},{"id":"https://openalex.org/keywords/memory-map","display_name":"Memory map","score":0.34150001406669617}],"concepts":[{"id":"https://openalex.org/C140745168","wikidata":"https://www.wikidata.org/wiki/Q1210082","display_name":"Tree traversal","level":2,"score":0.8001000285148621},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7069000005722046},{"id":"https://openalex.org/C65180967","wikidata":"https://www.wikidata.org/wiki/Q130901","display_name":"Binary relation","level":2,"score":0.5748999714851379},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5651999711990356},{"id":"https://openalex.org/C177877439","wikidata":"https://www.wikidata.org/wiki/Q7604413","display_name":"Statistical relational learning","level":3,"score":0.47440001368522644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45739999413490295},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.40799999237060547},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.40400001406669617},{"id":"https://openalex.org/C96333769","wikidata":"https://www.wikidata.org/wiki/Q907955","display_name":"Graph traversal","level":3,"score":0.3822000026702881},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.36500000953674316},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3569999933242798},{"id":"https://openalex.org/C74426580","wikidata":"https://www.wikidata.org/wiki/Q719484","display_name":"Memory map","level":3,"score":0.34150001406669617},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.31790000200271606},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.311599999666214},{"id":"https://openalex.org/C163561899","wikidata":"https://www.wikidata.org/wiki/Q1994977","display_name":"Logical matrix","level":3,"score":0.311599999666214},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.29159998893737793},{"id":"https://openalex.org/C40207289","wikidata":"https://www.wikidata.org/wiki/Q755662","display_name":"Relational model","level":3,"score":0.2906999886035919},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2833000123500824},{"id":"https://openalex.org/C61114434","wikidata":"https://www.wikidata.org/wiki/Q7144649","display_name":"Path expression","level":3,"score":0.28279998898506165},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27079999446868896},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C30390489","wikidata":"https://www.wikidata.org/wiki/Q4680748","display_name":"Adaptive memory","level":3,"score":0.2680000066757202},{"id":"https://openalex.org/C99436015","wikidata":"https://www.wikidata.org/wiki/Q1722436","display_name":"Relational calculus","level":4,"score":0.26190000772476196},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.09942","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.09942","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.09942","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.09942","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":"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":{"Memory":[0,68],"retrieval":[1,57],"in":[2],"agentic":[3,188],"large":[4],"language":[5],"model":[6],"(LLM)":[7],"systems":[8],"is":[9,69,82,193],"often":[10],"treated":[11],"as":[12,58,71],"a":[13,50,63,85,95,105,122,156,181],"static":[14],"lookup":[15],"problem,":[16],"relying":[17],"on":[18],"flat":[19],"vector":[20,89],"search":[21],"or":[22,146],"fixed":[23,28],"binary":[24],"relational":[25,65,92,102,140],"graphs.":[26],"However,":[27],"graph":[29,73],"structures":[30],"cannot":[31],"capture":[32],"the":[33,101,110,114],"varying":[34],"strength,":[35],"confidence,":[36],"and":[37,104,128,166,180],"query-dependent":[38],"relevance":[39],"of":[40,113,125],"relationships":[41],"between":[42],"events.":[43],"In":[44],"this":[45],"paper,":[46],"we":[47],"propose":[48],"HAGE,":[49],"weighted":[51],"multi-relational":[52],"memory":[53,66,77,135,189],"framework":[54,160],"that":[55,161],"reconceptualizes":[56],"sequential,":[59],"query-conditioned":[60,130],"traversal":[61,136],"over":[62,75],"unified":[64],"graph.":[67],"organized":[70],"relation-specific":[72],"views":[74],"shared":[76],"nodes,":[78],"where":[79],"each":[80],"edge":[81,115,131,167],"associated":[83],"with":[84],"trainable":[86],"relation":[87],"feature":[88],"encoding":[90],"multiple":[91],"signals.":[93],"Given":[94],"query,":[96],"an":[97],"LLM-based":[98],"classifier":[99],"identifies":[100],"intent,":[103],"routing":[106,164],"network":[107],"dynamically":[108],"modulates":[109],"corresponding":[111],"dimensions":[112],"embedding.":[116],"Traversal":[117],"scores":[118],"are":[119],"computed":[120],"via":[121],"learned":[123],"combination":[124],"semantic":[126],"similarity":[127],"these":[129],"representations.":[132],"This":[133],"allows":[134],"to":[137,186],"prioritize":[138],"high-utility":[139],"paths":[141],"while":[142],"softly":[143],"suppressing":[144],"noisy":[145],"weakly":[147],"relevant":[148],"connections.":[149],"Beyond":[150],"adaptive":[151],"traversal,":[152],"HAGE":[153],"further":[154],"introduces":[155],"reinforcement":[157],"learning-based":[158],"training":[159],"jointly":[162],"optimizes":[163],"behavior":[165],"representations":[168],"using":[169],"downstream":[170],"tasks.":[171],"Finally,":[172],"empirical":[173],"results":[174],"demonstrate":[175],"improved":[176],"long-horizon":[177],"reasoning":[178],"accuracy":[179],"favorable":[182],"accuracy-efficiency":[183],"trade-off":[184],"compared":[185],"state-of-the-art":[187],"systems.":[190],"Our":[191],"code":[192],"available":[194],"at":[195],"https://github.com/FredJiang0324/HAGE_MVPReview.":[196]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-13T00:00:00"}