{"id":"https://openalex.org/W7165665211","doi":"https://doi.org/10.48550/arxiv.2606.22030","title":"When Does Belief-Based Agent Memory Help? Reliability-Conditional Updating and Provenance-Capped Poisoning Defense","display_name":"When Does Belief-Based Agent Memory Help? Reliability-Conditional Updating and Provenance-Capped Poisoning Defense","publication_year":2026,"publication_date":"2026-06-20","ids":{"openalex":"https://openalex.org/W7165665211","doi":"https://doi.org/10.48550/arxiv.2606.22030"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.22030","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22030","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,"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.2606.22030","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133692291","display_name":"Pranav Singh","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Singh, Pranav","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5133692291"],"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":0.4374000132083893,"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":0.4374000132083893,"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":0.15760000050067902,"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":0.07240000367164612,"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/forgetting","display_name":"Forgetting","score":0.6647999882698059},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.546500027179718},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.460999995470047},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4092000126838684},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.3400999903678894},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.3138999938964844},{"id":"https://openalex.org/keywords/surprise","display_name":"Surprise","score":0.29829999804496765},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.29350000619888306}],"concepts":[{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.6647999882698059},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6067000031471252},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.546500027179718},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5382000207901001},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.460999995470047},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.421999990940094},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4092000126838684},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.3400999903678894},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.3138999938964844},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.30090001225471497},{"id":"https://openalex.org/C2780343955","wikidata":"https://www.wikidata.org/wiki/Q333173","display_name":"Surprise","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28600001335144043},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C2778023277","wikidata":"https://www.wikidata.org/wiki/Q321703","display_name":"Premise","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.2590000033378601},{"id":"https://openalex.org/C82687282","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Auxiliary memory","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C2778924833","wikidata":"https://www.wikidata.org/wiki/Q7064603","display_name":"Novelty detection","level":3,"score":0.25119999051094055},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.22030","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22030","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,"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.2606.22030","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22030","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,"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,75],"investigate":[1],"when":[2,102],"belief-based":[3,181],"memory":[4,18,66,174,182],"actually":[5],"improves":[6],"large":[7],"language":[8],"model":[9],"(LLM)":[10],"agents.":[11],"Our":[12,176],"vehicle":[13],"is":[14,110,123,183],"Nous,":[15],"a":[16,26,89,156],"long-term":[17,173],"architecture":[19],"that":[20,52,93,179],"represents":[21],"each":[22],"entity-attribute":[23],"pair":[24],"as":[25],"categorical":[27],"probability":[28],"distribution":[29],"updated":[30],"through":[31],"closed-form":[32],"Bayesian":[33,53],"inference,":[34],"with":[35],"information-theoretic":[36],"surprise":[37],"driving":[38],"belief":[39,54,94,119],"revision":[40],"and":[41,86,99,147,162,192],"entropy-based":[42],"forgetting.":[43],"A":[44],"controlled":[45,90,133],"ablation":[46],"on":[47,88,165],"the":[48,144],"LoCoMo":[49],"benchmark":[50,92],"shows":[51],"updating":[55,95],"alone":[56],"provides":[57],"little":[58],"benefit":[59],"over":[60,190],"naive":[61],"last-write-wins":[62,98],"because":[63],"existing":[64],"conversational":[65,199],"benchmarks":[67],"rarely":[68],"contain":[69],"contradictory":[70],"or":[71],"differently":[72,193],"reliable":[73],"evidence.":[74],"then":[76],"introduce":[77],"reliability-conditioned":[78],"updating,":[79,120],"estimating":[80],"per-observation":[81],"reliability":[82,109],"from":[83],"epistemic":[84],"language,":[85],"show":[87],"contradiction":[91],"substantially":[96],"outperforms":[97],"raw-memory":[100],"retrieval":[101],"observations":[103],"differ":[104],"in":[105,186],"trustworthiness.":[106],"Because":[107],"content-derived":[108],"itself":[111],"vulnerable":[112],"to":[113],"manipulation,":[114],"we":[115,154],"further":[116],"propose":[117],"provenance-capped":[118],"where":[121],"trust":[122],"bounded":[124],"by":[125],"source":[126],"provenance":[127],"rather":[128,196],"than":[129,197],"textual":[130],"confidence.":[131],"Under":[132],"memory-poisoning":[134],"experiments,":[135],"this":[136],"approach":[137],"resists":[138],"volumetric":[139],"poisoning":[140],"attacks":[141],"while":[142],"revealing":[143],"utility":[145],"costs":[146],"implementation":[148],"requirements":[149],"of":[150],"provenance-aware":[151],"memory.":[152],"Finally,":[153],"quantify":[155],"27.5-point":[157],"discrepancy":[158],"between":[159],"strict":[160],"token-F1":[161],"LLM-as-judge":[163],"evaluation":[164],"identical":[166],"outputs,":[167],"highlighting":[168],"important":[169],"reproducibility":[170],"concerns":[171],"for":[172],"benchmarks.":[175],"results":[177],"suggest":[178],"probabilistic":[180],"most":[184],"beneficial":[185],"environments":[187],"requiring":[188],"reasoning":[189],"conflicting":[191],"trustworthy":[194],"evidence,":[195],"conventional":[198],"recall":[200],"alone.":[201]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-24T00:00:00"}