{"id":"https://openalex.org/W7166875322","doi":"https://doi.org/10.18653/v1/2026.acl-long.1804","title":"MemCoRL: Alternating Co-Optimization of Memory Retrieval and Utilization via Collaborative Reinforcement Learning","display_name":"MemCoRL: Alternating Co-Optimization of Memory Retrieval and Utilization via Collaborative Reinforcement Learning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166875322","doi":"https://doi.org/10.18653/v1/2026.acl-long.1804"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1804","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1804","pdf_url":"https://aclanthology.org/2026.acl-long.1804.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.1804.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062795564","display_name":"Yuewen Liu","orcid":"https://orcid.org/0000-0002-1996-4999"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuewen Liu","raw_affiliation_strings":["State Key Lab of Networking and Switching Technology Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab of Networking and Switching Technology Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139733712","display_name":"Peng Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Xu","raw_affiliation_strings":["State Key Lab of Networking and Switching Technology Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab of Networking and Switching Technology Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101392976","display_name":"Muxi Diao","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Muxi Diao","raw_affiliation_strings":["State Key Lab of Networking and Switching Technology Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab of Networking and Switching Technology Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139714788","display_name":"Anyi Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Anyi Zhang","raw_affiliation_strings":["State Key Lab of Networking and Switching Technology Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab of Networking and Switching Technology Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139744315","display_name":"Yang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Li","raw_affiliation_strings":["State Key Lab of Networking and Switching Technology Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab of Networking and Switching Technology Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139847651","display_name":"Yutong Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutong Zhang","raw_affiliation_strings":["State Key Lab of Networking and Switching Technology Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab of Networking and Switching Technology Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.88156187,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"38912","last_page":"38924"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1378999948501587,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1378999948501587,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.11320000141859055,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.07150000333786011,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.5029000043869019},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2743000090122223},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.26420000195503235},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2547000050544739},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.25290000438690186}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6833999752998352},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5029000043869019},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4715000092983246},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2939999997615814},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2743000090122223},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25290000438690186},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2476000040769577}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1804","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1804","pdf_url":"https://aclanthology.org/2026.acl-long.1804.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1804","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1804","pdf_url":"https://aclanthology.org/2026.acl-long.1804.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166875322.pdf","grobid_xml":"https://content.openalex.org/works/W7166875322.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"are":[4],"inherently":[5],"constrained":[6],"by":[7],"their":[8],"fixed-length":[9],"context":[10],"windows,":[11],"which":[12,116],"limits":[13],"LLMs'":[14],"ability":[15],"to":[16],"retain":[17],"and":[18,44,56,87,102,134,144],"utilize":[19],"information":[20],"across":[21],"long-term":[22],"interactions.To":[23],"address":[24],"this":[25],"limitation,":[26],"recent":[27],"work":[28,48],"has":[29],"proposed":[30],"external":[31],"memory":[32,36,45,54,63,114,142,145],"modules":[33,37,55],"for":[34],"LLMs.Using":[35],"typically":[38],"involves":[39],"two":[40],"stages:":[41],"evidence":[42,82],"retrieval":[43,58,83,112,120,143],"utilization.While":[46],"prior":[47],"focuses":[49],"on":[50,68,130],"the":[51,57,60,127,139],"architecture":[52],"of":[53],"stage,":[59],"equally":[61],"critical":[62],"utilization":[64,91,96],"stage":[65],"remains":[66],"underexplored.Building":[67],"this,":[69],"we":[70],"propose":[71],"MemCoRL,":[72],"a":[73,107],"two-stage":[74],"alternating":[75],"co-optimization":[76,105,140],"reinforcement":[77],"learning":[78],"method.Stage":[79],"1":[80],"optimizes":[81,95],"using":[84],"citation":[85],"feedback":[86,109],"semantic":[88,100,135],"accuracy":[89],"from":[90],"as":[92],"rewards.Stage":[93],"2":[94],"with":[97],"rewards":[98],"combining":[99],"similarity":[101,136],"lexical":[103,132],"overlap.Iterative":[104],"establishes":[106],"positive":[108],"loop:":[110],"better":[111],"improves":[113],"utilization,":[115],"in":[117,141],"turn":[118],"refines":[119],"rewards.Experimental":[121],"results":[122],"show":[123],"our":[124],"approach":[125],"outperforms":[126],"leading":[128],"baselines":[129],"both":[131],"overlap":[133],"metrics,":[137],"confirming":[138],"utilization.":[146]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}