{"id":"https://openalex.org/W7165628106","doi":"https://doi.org/10.48550/arxiv.2606.21649","title":"EvoEmbedding: Evolvable Representations for Long-Context Retrieval and Agentic Memory","display_name":"EvoEmbedding: Evolvable Representations for Long-Context Retrieval and Agentic Memory","publication_year":2026,"publication_date":"2026-06-19","ids":{"openalex":"https://openalex.org/W7165628106","doi":"https://doi.org/10.48550/arxiv.2606.21649"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.21649","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.21649","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.2606.21649","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139207897","display_name":"Chang Nie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nie, Chang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014172220","display_name":"Chaoyou Fu","orcid":"https://orcid.org/0000-0002-0079-7668"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Chaoyou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139192355","display_name":"Junlan Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Junlan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139143200","display_name":"Caifeng Shan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shan, Caifeng","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":0.4438000023365021,"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":0.4438000023365021,"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":0.3379000127315521,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.02810000069439411,"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/embedding","display_name":"Embedding","score":0.6251000165939331},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5964000225067139},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.551800012588501},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5080999732017517},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4869999885559082},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.45239999890327454},{"id":"https://openalex.org/keywords/adaptive-memory","display_name":"Adaptive memory","score":0.44020000100135803},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4108000099658966},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.39239999651908875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8424999713897705},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6251000165939331},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5964000225067139},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5525000095367432},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.551800012588501},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5080999732017517},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4869999885559082},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.45239999890327454},{"id":"https://openalex.org/C30390489","wikidata":"https://www.wikidata.org/wiki/Q4680748","display_name":"Adaptive memory","level":3,"score":0.44020000100135803},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4108000099658966},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.39239999651908875},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.37860000133514404},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.375900000333786},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35569998621940613},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35339999198913574},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.3531000018119812},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.3474999964237213},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C110332635","wikidata":"https://www.wikidata.org/wiki/Q629498","display_name":"Genetic programming","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.30160000920295715},{"id":"https://openalex.org/C88576662","wikidata":"https://www.wikidata.org/wiki/Q18646","display_name":"Episodic memory","level":3,"score":0.29589998722076416},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C118702147","wikidata":"https://www.wikidata.org/wiki/Q189396","display_name":"Dynamic random-access memory","level":3,"score":0.25699999928474426},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.21649","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.21649","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.2606.21649","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.21649","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":{"Existing":[0],"embedding":[1,25],"models":[2],"are":[3],"inherently":[4],"static:":[5],"they":[6],"encode":[7],"text":[8],"segments":[9],"in":[10],"isolation,":[11],"ignoring":[12],"their":[13],"surrounding":[14],"context":[15],"and":[16,44,65,121,144,162],"temporal":[17],"order.":[18],"This":[19],"paper":[20],"introduces":[21],"EvoEmbedding,":[22],"a":[23,55,111,126,165,200],"novel":[24],"model":[26,83,104,154,207],"that":[27,139,152],"generates":[28],"evolvable":[29,75],"representations":[30],"for":[31,36,78,114],"retrieval.":[32,122],"It":[33],"is":[34,41,51],"tailored":[35],"long-context":[37,168],"scenarios,":[38],"where":[39],"information":[40],"dynamic,":[42],"sequential,":[43],"requires":[45],"continuous":[46],"state":[47],"tracking.":[48],"Our":[49],"design":[50],"simple:":[52],"EvoEmbedding":[53,189],"maintains":[54],"continuously":[56],"updated":[57],"latent":[58,119],"memory":[59,120,127,211],"as":[60],"it":[61,67],"sequentially":[62],"processes":[63],"inputs,":[64],"uses":[66],"alongside":[68,136],"the":[69,79,93,103,115],"raw":[70],"content":[71],"to":[72,87,129,175,195],"jointly":[73],"generate":[74],"embeddings.":[76],"Consequently,":[77],"same":[80],"query,":[81],"our":[82,153,206],"adapts":[84],"its":[85,185],"representation":[86,131],"retrieve":[88],"distinct":[89],"targets":[90],"based":[91],"on":[92],"evolving":[94],"context,":[95],"going":[96],"beyond":[97],"static":[98],"semantic":[99],"search.":[100],"To":[101],"equip":[102],"with":[105,180,205],"this":[106],"capability,":[107],"we":[108,124],"construct":[109],"EvoTrain-180K,":[110],"diverse":[112],"dataset":[113],"joint":[116],"optimization":[117],"of":[118,167],"Furthermore,":[123],"introduce":[125],"queue":[128],"prevent":[130],"collapse":[132],"during":[133],"recurrent":[134],"encoding,":[135],"segment-batching":[137],"techniques":[138],"tackle":[140],"significant":[141],"length":[142],"variance":[143],"accelerate":[145],"training":[146,186],"by":[147],"3.8$\\times$.":[148],"Extensive":[149],"experiments":[150],"show":[151],"not":[155],"only":[156],"outperforms":[157],"larger-scale":[158],"specialists":[159],"(e.g.,":[160,178],"Qwen3-Embedding-8B":[161],"KaLM-Embedding-Gemma3-12B)":[163],"across":[164],"range":[166],"retrieval":[169],"benchmarks,":[170],"but":[171],"also":[172],"generalizes":[173],"well":[174],"downstream":[176],"tasks":[177],"personalization)":[179],"contexts":[181],"10$\\times$":[182],"longer":[183],"than":[184],"window.":[187],"Notably,":[188],"seamlessly":[190],"integrates":[191],"into":[192],"agentic":[193,210],"workflows":[194],"boost":[196],"performance.":[197],"For":[198],"instance,":[199],"naive":[201],"RAG":[202],"pipeline":[203],"equipped":[204],"surpasses":[208],"dedicated":[209],"systems.":[212],"Project":[213],"Page:":[214],"https://clare-nie.github.io/EvoEmbedding/.":[215]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-24T00:00:00"}