{"id":"https://openalex.org/W7160602250","doi":"https://doi.org/10.48550/arxiv.2605.05725","title":"Detecting Time Series Anomalies Like an Expert: A Multi-Agent LLM Framework with Specialized Analyzers","display_name":"Detecting Time Series Anomalies Like an Expert: A Multi-Agent LLM Framework with Specialized Analyzers","publication_year":2026,"publication_date":"2026-05-07","ids":{"openalex":"https://openalex.org/W7160602250","doi":"https://doi.org/10.48550/arxiv.2605.05725"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.05725","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.05725","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.2605.05725","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055913311","display_name":"Hyeongwon Kang","orcid":"https://orcid.org/0000-0002-8710-8844"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kang, Hyeongwon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135720197","display_name":"Jeongseob Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Jeongseob","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135713740","display_name":"Jinwoo Park","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Park, Jinwoo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135688533","display_name":"Pilsung Kang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kang, Pilsung","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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.951200008392334,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.951200008392334,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.01810000091791153,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12127","display_name":"Software System Performance and Reliability","score":0.0044999998062849045,"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/anomaly-detection","display_name":"Anomaly detection","score":0.8076000213623047},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.7070000171661377},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.6220999956130981},{"id":"https://openalex.org/keywords/univariate","display_name":"Univariate","score":0.5098999738693237},{"id":"https://openalex.org/keywords/series","display_name":"Series (stratigraphy)","score":0.398499995470047},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.39570000767707825},{"id":"https://openalex.org/keywords/supervisor","display_name":"Supervisor","score":0.3944999873638153}],"concepts":[{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.8076000213623047},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.7070000171661377},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6765999794006348},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.6220999956130981},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5547000169754028},{"id":"https://openalex.org/C199163554","wikidata":"https://www.wikidata.org/wiki/Q1681619","display_name":"Univariate","level":3,"score":0.5098999738693237},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4429999887943268},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.398499995470047},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.39570000767707825},{"id":"https://openalex.org/C2779110517","wikidata":"https://www.wikidata.org/wiki/Q1240788","display_name":"Supervisor","level":2,"score":0.3944999873638153},{"id":"https://openalex.org/C158007255","wikidata":"https://www.wikidata.org/wiki/Q1055222","display_name":"Spectrum analyzer","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2750999927520752},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C161584116","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate statistics","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C516976414","wikidata":"https://www.wikidata.org/wiki/Q1606582","display_name":"Nasalization","level":3,"score":0.2547000050544739},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.05725","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.05725","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.2605.05725","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.05725","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":0.5549399852752686,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"studies":[1,148],"have":[2],"explored":[3],"large":[4],"language":[5],"models":[6],"for":[7,33,43,49,65],"time-series":[8],"anomaly":[9,24,35,51,59,93],"detection,":[10],"yet":[11],"existing":[12],"approaches":[13],"often":[14],"rely":[15],"on":[16],"a":[17,46],"single":[18],"general-purpose":[19],"model":[20],"to":[21,81],"directly":[22],"infer":[23],"indices":[25],"or":[26,126],"intervals,":[27],"limiting":[28],"controllability,":[29],"interpretability,":[30],"and":[31,69,78,97,144,149,161],"reliability":[32,160],"complex":[34],"patterns.":[36],"We":[37],"propose":[38],"SAGE":[39,111,135],"(Specialized":[40],"Analyzer":[41,73],"Group":[42],"Expert-like":[44],"Detection),":[45],"multi-agent":[47],"framework":[48,157],"structured":[50,105],"diagnosis":[52],"in":[53],"univariate":[54],"time":[55],"series.":[56],"It":[57],"decomposes":[58],"analysis":[60],"into":[61,91,107],"four":[62],"specialized":[63],"Analyzers":[64],"point,":[66],"structural,":[67],"seasonal,":[68],"pattern":[70],"anomalies.":[71],"Each":[72],"applies":[74],"family-specific":[75],"numerical":[76],"tools":[77],"diagnostic":[79,109,166],"visualizations":[80],"generate":[82],"evidence,":[83],"while":[84],"an":[85],"evidence-grounded":[86],"Detector":[87],"consolidates":[88],"the":[89,137,155,162],"evidence":[90],"confidence-scored":[92],"records":[94,106],"with":[95],"intervals":[96],"candidate":[98],"types.":[99],"A":[100],"Supervisor":[101],"then":[102],"converts":[103],"these":[104],"analyst-facing":[108],"reports.":[110],"further":[112,152],"constructs":[113],"synthetic":[114],"in-context":[115,130],"examples":[116],"from":[117],"normal-reference":[118],"training":[119],"segments,":[120],"without":[121],"using":[122],"real":[123],"anomalous":[124],"segments":[125],"anomaly-type":[127],"labels":[128],"as":[129],"examples.":[131],"Across":[132],"three":[133],"benchmarks,":[134],"achieves":[136],"best":[138],"average":[139],"performance":[140],"among":[141],"strong":[142],"ML/DL":[143],"language-model-based":[145],"baselines.":[146],"Ablation":[147],"human":[150],"evaluation":[151],"show":[153],"that":[154],"proposed":[156],"improves":[158],"detection":[159],"practical":[163],"usefulness":[164],"of":[165],"outputs.":[167]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-09T00:00:00"}