{"id":"https://openalex.org/W7127083622","doi":"https://doi.org/10.48550/arxiv.2601.23014","title":"Mem-T: Densifying Rewards for Long-Horizon Memory Agents","display_name":"Mem-T: Densifying Rewards for Long-Horizon Memory Agents","publication_year":2026,"publication_date":"2026-01-30","ids":{"openalex":"https://openalex.org/W7127083622","doi":"https://doi.org/10.48550/arxiv.2601.23014"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2601.23014","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.23014","pdf_url":"https://arxiv.org/pdf/2601.23014","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2601.23014","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037828026","display_name":"Yanwei Yue","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue, Yanwei","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057316227","display_name":"Boci Peng","orcid":"https://orcid.org/0000-0002-0984-8740","observed_orcids":["https://orcid.org/0000-0002-0984-8740"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng, Boci","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101263563","display_name":"Xuanbo Fan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan, Xuanbo","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128720955","display_name":"Jiaxin Guo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guo, Jiaxin","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128797194","display_name":"Qiankun Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Li, Qiankun","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5128788719","display_name":"Yan Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Yan","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":20,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.31200000643730164,"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"}},"topics":[{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.31200000643730164,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.12439999729394913,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.08789999783039093,"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/memory-agents","display_name":"memory agents","score":0.972000002861023},{"id":"https://openalex.org/keywords/inference-efficiency","display_name":"inference efficiency","score":0.5479999780654907}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7703999876976013},{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.5913000106811523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5335000157356262},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5220999717712402},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.5149000287055969},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.49079999327659607},{"id":"https://openalex.org/C30390489","wikidata":"https://www.wikidata.org/wiki/Q4680748","display_name":"Adaptive memory","level":3,"score":0.47929999232292175},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.373199999332428},{"id":"https://openalex.org/C118702147","wikidata":"https://www.wikidata.org/wiki/Q189396","display_name":"Dynamic random-access memory","level":3,"score":0.3675000071525574},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.3668000102043152},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.3407000005245209},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.335999995470047},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.31049999594688416},{"id":"https://openalex.org/C74426580","wikidata":"https://www.wikidata.org/wiki/Q719484","display_name":"Memory map","level":3,"score":0.31040000915527344},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C171675096","wikidata":"https://www.wikidata.org/wiki/Q1143380","display_name":"Extended memory","level":4,"score":0.2879999876022339},{"id":"https://openalex.org/C88576662","wikidata":"https://www.wikidata.org/wiki/Q18646","display_name":"Episodic memory","level":3,"score":0.2759999930858612},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2646999955177307},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C157170001","wikidata":"https://www.wikidata.org/wiki/Q4781507","display_name":"Applications of artificial intelligence","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2601.23014","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.23014","pdf_url":"https://arxiv.org/pdf/2601.23014","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2601.23014","doi":"https://doi.org/10.48550/arxiv.2601.23014","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.23014","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2601.23014","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.23014","pdf_url":"https://arxiv.org/pdf/2601.23014","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7127083622.pdf","grobid_xml":"https://content.openalex.org/works/W7127083622.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W2779681640","https://openalex.org/W2952862139","https://openalex.org/W4385965642","https://openalex.org/W4387636003","https://openalex.org/W4389363365","https://openalex.org/W4391631327","https://openalex.org/W4393160747","https://openalex.org/W4393942918","https://openalex.org/W4402670856","https://openalex.org/W4402684150","https://openalex.org/W4407759090","https://openalex.org/W4414939355","https://openalex.org/W4415112028","https://openalex.org/W4415276218","https://openalex.org/W4415963275","https://openalex.org/W4416047871","https://openalex.org/W4416057654","https://openalex.org/W4416895257","https://openalex.org/W4417095241","https://openalex.org/W4417459816","https://openalex.org/W6891839109","https://openalex.org/W6947947872","https://openalex.org/W6967397561","https://openalex.org/W7083493645","https://openalex.org/W7084138381","https://openalex.org/W7102411227","https://openalex.org/W7105002322","https://openalex.org/W7111299929","https://openalex.org/W7117140353","https://openalex.org/W7118792955","https://openalex.org/W7119809923","https://openalex.org/W7125965167","https://openalex.org/W7166848218","https://openalex.org/W7166853358"],"related_works":["https://openalex.org/W7124151273","https://openalex.org/W7124152780","https://openalex.org/W7223208726","https://openalex.org/W7133364044","https://openalex.org/W4417095241","https://openalex.org/W7214794237","https://openalex.org/W7119233124","https://openalex.org/W7162070983","https://openalex.org/W7084138381","https://openalex.org/W7163908280"],"abstract_inverted_index":{"Memory":[0],"agents,":[1],"which":[2,47],"depart":[3],"from":[4],"predefined":[5],"memory-processing":[6],"pipelines":[7],"by":[8,144,164],"endogenously":[9],"managing":[10],"the":[11,121],"processing,":[12],"storage,":[13],"and":[14,25,44,79,115,127,142,148,158],"retrieval":[15,81],"of":[16,38,52,124],"memories,":[17],"have":[18],"garnered":[19],"increasing":[20],"attention":[21],"for":[22],"their":[23],"autonomy":[24],"adaptability.":[26],"However,":[27],"existing":[28],"training":[29],"paradigms":[30],"remain":[31],"constrained:":[32],"agents":[33],"often":[34],"traverse":[35],"long-horizon":[36,88],"sequences":[37],"memory":[39,53,65,73,89,111,125],"operations":[40],"before":[41],"receiving":[42],"sparse":[43,103],"delayed":[45],"rewards,":[46],"hinders":[48],"truly":[49],"end-to-end":[50],"optimization":[51,123],"management":[54,90],"policies.":[55],"To":[56,85],"address":[57],"this":[58],"limitation,":[59],"we":[60,92],"introduce":[61],"Mem-T,":[62],"an":[63],"autonomous":[64],"agent":[66],"that":[67,101,132],"interfaces":[68],"with":[69],"a":[70,96,153],"lightweight":[71],"hierarchical":[72],"database":[74],"to":[75,146,167],"perform":[76],"dynamic":[77],"updates":[78],"multi-turn":[80],"over":[82],"streaming":[83],"inputs.":[84],"effectively":[86],"train":[87],"capabilities,":[91],"further":[93],"propose":[94],"MoT-GRPO,":[95],"tree-guided":[97],"reinforcement":[98],"learning":[99],"framework":[100],"transforms":[102],"terminal":[104],"feedback":[105],"into":[106],"dense,":[107],"step-wise":[108],"supervision":[109],"via":[110],"operation":[112],"tree":[113],"backpropagation":[114],"hindsight":[116],"credit":[117],"assignment,":[118],"thereby":[119],"enabling":[120],"joint":[122],"construction":[126],"retrieval.":[128],"Extensive":[129],"experiments":[130],"demonstrate":[131],"Mem-T":[133],"is":[134],"(1)":[135],"high-performing,":[136],"surpassing":[137],"frameworks":[138],"such":[139],"as":[140],"A-Mem":[141],"Mem0":[143],"up":[145],"$14.92\\%$,":[147],"(2)":[149],"economical,":[150],"operating":[151],"on":[152],"favorable":[154],"accuracy-efficiency":[155],"Pareto":[156],"frontier":[157],"reducing":[159],"inference":[160],"tokens":[161],"per":[162],"query":[163],"$\\sim24.45\\%$":[165],"relative":[166],"GAM":[168],"without":[169],"sacrificing":[170],"performance.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":20}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-02-03T00:00:00"}