{"id":"https://openalex.org/W7159672934","doi":"https://doi.org/10.48550/arxiv.2604.27840","title":"CastFlow: Learning Role-Specialized Agentic Workflows for Time Series Forecasting","display_name":"CastFlow: Learning Role-Specialized Agentic Workflows for Time Series Forecasting","publication_year":2026,"publication_date":"2026-04-30","ids":{"openalex":"https://openalex.org/W7159672934","doi":"https://doi.org/10.48550/arxiv.2604.27840"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.27840","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.27840","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.2604.27840","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130266197","display_name":"\u6f58\u67cf\u51f1","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan, Bokai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134974861","display_name":"Mingyue Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Mingyue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134995971","display_name":"Zhiding Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Zhiding","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134931001","display_name":"Shuo Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Shuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134958421","display_name":"Xiaoyu Tao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao, Xiaoyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134935257","display_name":"Yuchong Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Yuchong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134956670","display_name":"Qi Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Qi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134967655","display_name":"Defu Lian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lian, Defu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134956577","display_name":"Enhong Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Enhong","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/T11918","display_name":"Forecasting Techniques and Applications","score":0.2379000037908554,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11918","display_name":"Forecasting Techniques and Applications","score":0.2379000037908554,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.12680000066757202,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.1062999963760376,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6197999715805054},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5131000280380249},{"id":"https://openalex.org/keywords/time-series","display_name":"Time series","score":0.5015000104904175},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.4828000068664551},{"id":"https://openalex.org/keywords/ensemble-forecasting","display_name":"Ensemble forecasting","score":0.4738999903202057},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4560999870300293},{"id":"https://openalex.org/keywords/series","display_name":"Series (stratigraphy)","score":0.42399999499320984},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.38280001282691956}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7615000009536743},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6471999883651733},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6197999715805054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5709999799728394},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5131000280380249},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.5015000104904175},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.4828000068664551},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.4738999903202057},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4560999870300293},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.42399999499320984},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.38280001282691956},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.38029998540878296},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3643999993801117},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2678000032901764},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.26669999957084656},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.26100000739097595},{"id":"https://openalex.org/C193809577","wikidata":"https://www.wikidata.org/wiki/Q3409300","display_name":"Demand forecasting","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C125014702","wikidata":"https://www.wikidata.org/wiki/Q4680749","display_name":"Adaptive learning","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.27840","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.27840","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.2604.27840","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.27840","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"have":[5],"shown":[6],"great":[7],"promise":[8],"in":[9,33,67],"time":[10,246],"series":[11,247],"forecasting.":[12,153,248],"However,":[13],"most":[14],"existing":[15],"LLM-based":[16],"forecasting":[17,40,76,92,100,171],"methods":[18],"still":[19],"follow":[20],"a":[21,34,73,118,126,135,143,157,164,184,191,239],"static":[22],"generative":[23],"paradigm":[24],"that":[25,78,121,129,146,195,222,233],"directly":[26],"maps":[27],"historical":[28],"observations":[29],"to":[30],"future":[31],"values":[32],"single":[35],"pass.":[36],"Under":[37,154],"this":[38,68,113,155,234],"paradigm,":[39],"is":[41,115],"constrained":[42],"by":[43,117],"limited":[44],"temporal":[45,81],"pattern":[46,82],"extraction,":[47,83],"single-round":[48],"acquisition":[49],"of":[50,58,211],"contextual":[51,85],"features,":[52],"one-shot":[53],"forecast":[54,89,138,176],"generation,":[55],"and":[56,91,106,125,133,200,220,244],"lack":[57],"support":[59],"from":[60,180],"ensemble":[61,94,137,175],"forecasts.":[62,95],"To":[63,182,207],"address":[64],"these":[65],"limitations,":[66],"work,":[69],"we":[70,188,213],"propose":[71],"CastFlow,":[72,212],"dynamic":[74],"agentic":[75,110],"framework":[77],"enables":[79],"multi-view":[80,127],"multi-round":[84],"features":[86],"acquisition,":[87],"iterative":[88],"refinement,":[90],"with":[93,150,203],"First,":[96],"CastFlow":[97,141],"organizes":[98],"the":[99,174,209],"process":[101],"into":[102],"planning,":[103],"action,":[104],"forecasting,":[105],"reflection,":[107],"establishing":[108],"an":[109],"workflow.":[111],"Second,":[112],"workflow":[114],"supported":[116],"memory":[119],"module":[120],"retrieves":[122],"prior":[123],"experience":[124],"toolkit":[128],"constructs":[130],"diagnostic":[131],"evidence":[132],"provides":[134],"reliable":[136],"baseline.":[139],"Third,":[140],"adopts":[142],"role-specialized":[144],"design":[145],"combines":[147,196],"general-purpose":[148,161],"reasoning":[149],"specialized":[151],"numerical":[152,170],"design,":[156],"frozen":[158],"LLM":[159,167],"preserves":[160],"reasoning,":[162],"while":[163],"fine-tuned":[165,185],"domain-specific":[166,186],"performs":[168],"evidence-guided":[169],"based":[172],"on":[173,217],"baseline,":[177],"rather":[178],"than":[179],"scratch.":[181],"optimize":[183],"LLM,":[187],"further":[189],"develop":[190],"two-stage":[192],"workflow-oriented":[193],"training":[194],"supervised":[197],"fine-tuning":[198],"(SFT)":[199],"reinforcement":[201],"learning":[202],"verifiable":[204],"rewards":[205],"(RLVR).":[206],"evaluate":[208],"effectiveness":[210],"conduct":[214],"extensive":[215],"experiments":[216],"diverse":[218],"datasets":[219],"show":[221],"it":[223],"achieves":[224],"superior":[225],"overall":[226],"results":[227],"against":[228],"strong":[229],"baselines.":[230],"We":[231],"hope":[232],"work":[235],"can":[236],"serve":[237],"as":[238],"step":[240],"toward":[241],"more":[242],"adaptive":[243],"accurate":[245]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-02T00:00:00"}