{"id":"https://openalex.org/W7162792993","doi":"https://doi.org/10.48550/arxiv.2605.29055","title":"Hallucination Mitigation with Agentic AI, Nested Learning, and AI Sustainability via Semantic Caching","display_name":"Hallucination Mitigation with Agentic AI, Nested Learning, and AI Sustainability via Semantic Caching","publication_year":2026,"publication_date":"2026-05-27","ids":{"openalex":"https://openalex.org/W7162792993","doi":"https://doi.org/10.48550/arxiv.2605.29055"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.29055","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29055","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.2605.29055","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137310534","display_name":"Diego Gosmar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gosmar, Diego","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5022751300","display_name":"Deborah A. Dahl","orcid":"https://orcid.org/0000-0002-3389-2784"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dahl, Deborah A.","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/T11424","display_name":"Security and Verification in Computing","score":0.11490000039339066,"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/T11424","display_name":"Security and Verification in Computing","score":0.11490000039339066,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.08720000088214874,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.0851999968290329,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/pipeline","display_name":"Pipeline (software)","score":0.5544000267982483},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5170999765396118},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.43950000405311584},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.3921999931335449},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.3547999858856201},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.336899995803833},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.3352999985218048},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.3343999981880188}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7063999772071838},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5544000267982483},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5170999765396118},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4564000070095062},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.43950000405311584},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.3921999931335449},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3547999858856201},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35339999198913574},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3418000042438507},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.3352999985218048},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.3343999981880188},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.33090001344680786},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.32659998536109924},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C122770356","wikidata":"https://www.wikidata.org/wiki/Q1656753","display_name":"Identifiability","level":2,"score":0.3215999901294708},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C108154423","wikidata":"https://www.wikidata.org/wiki/Q1469792","display_name":"Salience (neuroscience)","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C46355384","wikidata":"https://www.wikidata.org/wiki/Q726686","display_name":"Compromise","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.29055","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29055","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.2605.29055","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29055","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":0.45256590843200684,"id":"https://metadata.un.org/sdg/12","display_name":"Responsible consumption and production"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Hallucination":[0,98],"remains":[1],"a":[2,25,40,120,132,140],"major":[3],"reliability":[4],"barrier":[5],"for":[6],"production":[7,199],"LLM":[8,182],"systems,":[9],"particularly":[10],"in":[11],"multi-agent":[12,223],"pipelines":[13,195],"where":[14],"unsupported":[15],"claims":[16],"can":[17,225],"propagate":[18],"unchecked":[19],"across":[20,100,164],"stages.":[21],"This":[22,153],"paper":[23],"adapts":[24],"HOPE-inspired":[26],"Nested":[27],"Learning":[28],"architecture":[29],"with":[30,68],"Continuum":[31],"Memory":[32],"Systems":[33],"(CMS)":[34],"and":[35,50,88,111,147,188,191,232],"semantic":[36],"similarity":[37],"caching":[38,169],"to":[39,104,138,162,184],"hybrid":[41],"benchmark":[42],"of":[43,160],"310":[44],"prompts":[45,49],"combining":[46],"217":[47],"epistemic-uncertainty":[48],"93":[51],"fabrication-induction":[52],"stress-test":[53],"prompts.":[54],"A":[55],"three-stage":[56],"agentic":[57],"pipeline":[58],"orchestrated":[59],"via":[60],"the":[61,145,203],"Open":[62],"Floor":[63],"Protocol":[64],"(OFP)":[65],"is":[66,129],"evaluated":[67],"five":[69,101,165],"KPIs":[70],"--":[71,93],"FCD":[72],"(Factual":[73,77],"Claim":[74],"Density),":[75],"FGR":[76,112],"Grounding":[78],"References),":[79],"FDF":[80],"(Fictional":[81],"Disclaimer":[82],"Frequency),":[83],"ECS":[84],"(Explicit":[85],"Contextualization":[86],"Score),":[87],"OSR":[89],"(Observability":[90],"Score":[91],"Ratio)":[92],"aggregated":[94],"into":[95],"THS":[96,123,158,207],"(Total":[97],"Score)":[99],"weighting":[102,166],"configurations":[103,212],"study":[105],"mitigation-observability":[106],"trade-offs.":[107],"FDF,":[108],"ECS,":[109],"OSR,":[110],"are":[113],"subtracted":[114],"as":[115,131,150],"mitigation":[116],"signals,":[117],"so":[118],"that":[119,210,221],"more":[121],"negative":[122,205],"indicates":[124],"stronger":[125],"mitigation.":[126,217],"The":[127],"FrontEndAgent":[128],"configured":[130],"high-stochasticity":[133],"generator":[134],"(temperature":[135],"=":[136],"1.0)":[137],"produce":[139],"realistic":[141],"hallucination":[142],"baseline,":[143],"while":[144],"SecondLevelReviewer":[146],"ThirdLevelReviewer":[148],"operate":[149],"progressive":[151],"correctors.":[152],"asymmetric":[154],"design":[155],"yields":[156],"end-to-end":[157],"reductions":[159],"-31.3%":[161],"-35.9%":[163],"configurations.":[167],"Semantic":[168],"achieves":[170],"440":[171],"cache":[172],"hits":[173],"over":[174],"930":[175],"potential":[176],"calls":[177],"(47.3%":[178],"hit":[179],"rate),":[180],"reducing":[181],"invocations":[183],"490,":[185],"lowering":[186],"energy":[187],"CO2e":[189],"footprint,":[190],"making":[192],"multi-stage":[193],"review":[194],"operationally":[196],"viable":[197],"at":[198],"scale.":[200],"ExtremeObservability":[201],"attains":[202],"most":[204],"final":[206],"(-0.0709),":[208],"confirming":[209],"observability-heavy":[211],"reinforce":[213],"rather":[214],"than":[215],"compromise":[216],"These":[218],"findings":[219],"suggest":[220],"memory-augmented":[222],"designs":[224],"jointly":[226],"improve":[227],"factual":[228],"reliability,":[229],"operational":[230],"efficiency,":[231],"auditability":[233],"without":[234],"model":[235],"retraining.":[236]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-30T00:00:00"}