{"id":"https://openalex.org/W7156967220","doi":"https://doi.org/10.48550/arxiv.2604.22755","title":"RADIANT-LLM: an Agentic Retrieval Augmented Generation Framework for Reliable Decision Support in Safety-Critical Nuclear Engineering","display_name":"RADIANT-LLM: an Agentic Retrieval Augmented Generation Framework for Reliable Decision Support in Safety-Critical Nuclear Engineering","publication_year":2026,"publication_date":"2026-03-04","ids":{"openalex":"https://openalex.org/W7156967220","doi":"https://doi.org/10.48550/arxiv.2604.22755"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.22755","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.22755","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":null,"license_id":null,"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.2604.22755","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115946994","display_name":"Zavier Ndum Ndum","orcid":"https://orcid.org/0009-0002-9608-8678"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ndum, Zavier Ndum","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134803780","display_name":"Jian Tao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao, Jian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134802541","display_name":"John Ford","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ford, John","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123833670","display_name":"Mansung Yim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yim, Mansung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134808484","display_name":"Yang Liu","orcid":"https://orcid.org/0009-0005-1420-1828"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yang","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/T10028","display_name":"Topic Modeling","score":0.17640000581741333,"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":0.17640000581741333,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.10220000147819519,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.060499999672174454,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6717000007629395},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6226000189781189},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5752000212669373},{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.4952000081539154},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.4034000039100647},{"id":"https://openalex.org/keywords/expert-elicitation","display_name":"Expert elicitation","score":0.35040000081062317}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6717000007629395},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6226000189781189},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6194000244140625},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5752000212669373},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.4952000081539154},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.4034000039100647},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.353300005197525},{"id":"https://openalex.org/C72161134","wikidata":"https://www.wikidata.org/wiki/Q5421219","display_name":"Expert elicitation","level":2,"score":0.35040000081062317},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.3206999897956848},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C6604083","wikidata":"https://www.wikidata.org/wiki/Q376937","display_name":"Requirements engineering","level":3,"score":0.28600001335144043},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2831999957561493},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.27900001406669617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2786000072956085},{"id":"https://openalex.org/C107327155","wikidata":"https://www.wikidata.org/wiki/Q330268","display_name":"Decision support system","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27079999446868896},{"id":"https://openalex.org/C170579384","wikidata":"https://www.wikidata.org/wiki/Q2070459","display_name":"Sparging","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.25839999318122864}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.22755","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.22755","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.22755","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.22755","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6476727724075317,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reliable":[0],"decision":[1],"support":[2],"in":[3,31,172],"nuclear":[4,33,59,222],"engineering":[5,223],"requires":[6],"traceable,":[7],"domain-grounded":[8],"knowledge":[9,83,152],"retrieval,":[10],"yet":[11],"safety":[12],"and":[13,22,62,87,105,120,134,156,163,190,208,219],"risk":[14],"analysis":[15],"workflows":[16,224],"remain":[17,158],"hampered":[18],"by":[19],"fragmented":[20],"documentation":[21],"hallucination":[23,111,164],"when":[24],"use":[25],"pre-trained":[26],"large":[27],"language":[28],"model":[29],"(LLM)":[30],"specialized":[32],"domains.":[34],"To":[35,113],"address":[36],"these":[37],"challenges,":[38],"this":[39,116],"paper":[40],"presents":[41],"RADIANT-LLM":[42],"(Retrival-Augumented,":[43],"Domain-Intelligent":[44],"Agent":[45],"for":[46,58],"Nuclear":[47,144],"Technologies":[48],"using":[49],"LLM),":[50],"a":[51,68,74,80,122,199],"multi-modal":[52,75,202],"retrieval-augmented":[53],"generation":[54],"(RAG)":[55],"framework":[56,66,204],"designed":[57],"safety,":[60],"security,":[61],"safeguards":[63],"applications.":[64],"The":[65],"uses":[67],"local-first,":[69],"model-agnostic":[70],"architecture":[71],"that":[72,198,221],"pairs":[73],"document":[76],"ingestion":[77],"pipeline":[78],"with":[79,102,205],"structured,":[81],"metadata-rich":[82],"base,":[84],"supporting":[85],"page-":[86],"figure-level":[88],"retrieval":[89,207],"from":[90,142],"technical":[91],"documents.":[92],"An":[93],"agentic":[94],"layer":[95],"coordinates":[96],"domain-specific":[97,206],"tools,":[98],"enforces":[99],"citation-backed":[100],"responses":[101],"provenance":[103,209],"tracking,":[104],"supports":[106],"human-in-the-loop":[107],"validation":[108],"to":[109,138,181,213],"reduce":[110],"risks.":[112],"rigorously":[114],"evaluate":[115],"framework,":[117],"we":[118],"develop":[119],"apply":[121],"suite":[123],"of":[124],"domain-aware":[125],"metrics,":[126],"including":[127],"Context":[128],"Precision":[129],"(CoP),":[130],"Hallucination":[131],"Rate":[132],"(HR),":[133],"Visual":[135],"Recall":[136],"(ViR),":[137],"expert-curated":[139],"benchmarks":[140],"derived":[141],"Used":[143],"Fuel":[145],"Storage":[146],"Facility":[147],"design":[148],"guidance.":[149],"Across":[150],"varying":[151],"base":[153],"sizes,":[154],"CoP":[155],"ViR":[157],"within":[159],"an":[160],"85--98\\%":[161],"band,":[162],"rates":[165],"are":[166,179],"substantially":[167],"lower":[168],"than":[169],"those":[170],"observed":[171],"general-purpose":[173],"deployments.":[174],"When":[175],"the":[176,186,215],"same":[177],"queries":[178],"posed":[180],"commercial":[182],"LLM":[183],"platforms":[184],"without":[185],"RAG":[187,203],"layer,":[188],"hallucinations":[189],"citation":[191],"errors":[192],"increase":[193],"markedly.":[194],"These":[195],"results":[196],"indicate":[197],"locally":[200],"controlled,":[201],"enforcement":[210],"is":[211],"necessary":[212],"achieve":[214],"factual":[216],"accuracy,":[217],"transparency,":[218],"auditability":[220],"demand.":[225]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-29T00:00:00"}