{"id":"https://openalex.org/W7160937981","doi":"https://doi.org/10.48550/arxiv.2605.10268","title":"MemReread: Enhancing Agentic Long-Context Reasoning via Memory-Guided Rereading","display_name":"MemReread: Enhancing Agentic Long-Context Reasoning via Memory-Guided Rereading","publication_year":2026,"publication_date":"2026-05-11","ids":{"openalex":"https://openalex.org/W7160937981","doi":"https://doi.org/10.48550/arxiv.2605.10268"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.10268","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10268","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":"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.10268","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123457001","display_name":"Baibei Ji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji, Baibei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126599810","display_name":"Xiaoyang Weng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weng, Xiaoyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135963135","display_name":"Juntao Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Juntao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135988268","display_name":"Zecheng Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Zecheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063901345","display_name":"Yihang Lou","orcid":"https://orcid.org/0000-0002-8143-389X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lou, Yihang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135991992","display_name":"Min Zhang","orcid":"https://orcid.org/0000-0002-6771-007X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Min","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3723999857902527,"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":0.3723999857902527,"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":0.219200000166893,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.06970000267028809,"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/recall","display_name":"Recall","score":0.6686000227928162},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5875999927520752},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5727999806404114},{"id":"https://openalex.org/keywords/context-dependent-memory","display_name":"Context-dependent memory","score":0.4316999912261963},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.38769999146461487},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.3824999928474426},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.34950000047683716},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.34150001406669617}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7452999949455261},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.6686000227928162},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5875999927520752},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5727999806404114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5228000283241272},{"id":"https://openalex.org/C76679254","wikidata":"https://www.wikidata.org/wiki/Q5165163","display_name":"Context-dependent memory","level":4,"score":0.4316999912261963},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.38769999146461487},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3824999928474426},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3560999929904938},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.34950000047683716},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.34150001406669617},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3188999891281128},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.3179999887943268},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.3125},{"id":"https://openalex.org/C43971567","wikidata":"https://www.wikidata.org/wiki/Q3142865","display_name":"Logical reasoning","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C21963081","wikidata":"https://www.wikidata.org/wiki/Q11337567","display_name":"Working memory","level":3,"score":0.2635999917984009},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.258899986743927},{"id":"https://openalex.org/C88576662","wikidata":"https://www.wikidata.org/wiki/Q18646","display_name":"Episodic memory","level":3,"score":0.2581999897956848},{"id":"https://openalex.org/C82687282","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Auxiliary memory","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C30390489","wikidata":"https://www.wikidata.org/wiki/Q4680748","display_name":"Adaptive memory","level":3,"score":0.2513999938964844},{"id":"https://openalex.org/C27853696","wikidata":"https://www.wikidata.org/wiki/Q3480151","display_name":"Interference theory","level":4,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.10268","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10268","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.10268","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10268","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":"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"},"sustainable_development_goals":[{"score":0.7094102501869202,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"To":[0,32,78,129],"tackle":[1],"long-context":[2,171],"reasoning":[3,119,172],"tasks":[4],"without":[5],"the":[6,34,100,106,122,147],"quadratic":[7],"complexity":[8,178],"of":[9,37,108,126,149],"standard":[10],"attention":[11],"mechanisms,":[12],"approaches":[13],"based":[14,152],"on":[15,153,170],"agent":[16],"memory":[17,26,59,70,102],"have":[18,46],"emerged,":[19],"which":[20],"typically":[21],"maintain":[22],"a":[23,135],"dynamically":[24,145],"updated":[25],"when":[27,99],"linearly":[28],"processing":[29],"document":[30,127],"chunks.":[31],"mitigate":[33],"potential":[35],"loss":[36,68],"latent":[38],"evidence":[39,67],"in":[40],"this":[41],"memorize-while-reading":[42],"paradigm,":[43],"recent":[44],"works":[45],"integrated":[47],"retrieval":[48],"modules":[49],"that":[50,111,139,164],"allow":[51],"agents":[52],"to":[53,181],"recall":[54,63],"information":[55],"previously":[56],"discarded":[57],"during":[58,69],"overwriting.":[60],"However,":[61],"retrieval-based":[62],"suffers":[64],"from":[65],"both":[66],"formation":[71],"and":[72,97],"interference":[73],"induced":[74],"by":[75],"invalid":[76],"queries.":[77],"overcome":[79],"these":[80],"limitations,":[81],"we":[82,133],"propose":[83],"MemReread.":[84],"Built":[85],"upon":[86],"streaming":[87],"reading,":[88],"MemReread":[89,165],"circumvents":[90],"intermediate":[91],"retrieval.":[92],"It":[93],"triggers":[94],"question":[95],"decomposition":[96],"rereading":[98,150],"final":[101],"is":[103],"insufficient,":[104],"enabling":[105],"recovery":[107],"indirect":[109],"facts":[110],"were":[112],"prematurely":[113],"discarded.":[114],"This":[115],"design":[116],"supports":[117],"non-linear":[118],"while":[120,144,174],"preserving":[121],"inherent":[123],"logical":[124],"flow":[125],"comprehension.":[128],"further":[130],"enhance":[131],"practicality,":[132],"introduce":[134],"reinforcement":[136],"learning":[137],"framework":[138],"enhances":[140],"length":[141],"extrapolation":[142],"capability":[143],"determining":[146],"number":[148],"passes":[151],"task":[154],"complexity,":[155],"thereby":[156],"flexibly":[157],"controlling":[158],"computational":[159],"overhead.":[160],"Extensive":[161],"experiments":[162],"demonstrate":[163],"consistently":[166],"outperforms":[167],"baseline":[168],"frameworks":[169],"tasks,":[173],"maintaining":[175],"linear":[176],"time":[177],"with":[179],"respect":[180],"context":[182],"length.":[183]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-13T00:00:00"}