{"id":"https://openalex.org/W4414980802","doi":"https://doi.org/10.48550/arxiv.2510.05950","title":"Training-Free Time Series Classification via In-Context Reasoning with LLM Agents","display_name":"Training-Free Time Series Classification via In-Context Reasoning with LLM Agents","publication_year":2025,"publication_date":"2025-10-07","ids":{"openalex":"https://openalex.org/W4414980802","doi":"https://doi.org/10.48550/arxiv.2510.05950"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2510.05950","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.05950","pdf_url":"https://arxiv.org/pdf/2510.05950","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.05950","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092734213","display_name":"Songyuan Sui","orcid":"https://orcid.org/0009-0004-1989-8700","observed_orcids":["https://orcid.org/0009-0004-1989-8700"]},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sui, Songyuan","raw_affiliation_strings":["Rice University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rice University","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006638908","display_name":"Zihang Xu","orcid":"https://orcid.org/0000-0002-1081-5559","observed_orcids":["https://orcid.org/0000-0002-1081-5559"]},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xu, Zihang","raw_affiliation_strings":["Rice University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rice University","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048791081","display_name":"Yu-Neng Chuang","orcid":"https://orcid.org/0000-0002-7492-0817","observed_orcids":["https://orcid.org/0000-0002-7492-0817"]},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hu, Xia","raw_affiliation_strings":["Rice University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rice University","institution_ids":["https://openalex.org/I74775410"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74775410"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":8,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9984999895095825,"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"}},"topics":[{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9984999895095825,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0003000000142492354,"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/T11309","display_name":"Music and Audio Processing","score":9.999999747378752e-05,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/time-series-classification","display_name":"time series classification","score":0.9919999837875366},{"id":"https://openalex.org/keywords/training-free-classification","display_name":"training-free classification","score":0.8059999942779541},{"id":"https://openalex.org/keywords/in-context-learning","display_name":"in-context learning","score":0.7739999890327454},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7379999756813049},{"id":"https://openalex.org/keywords/multi-agent-framework","display_name":"multi-agent framework","score":0.7450000047683716},{"id":"https://openalex.org/keywords/confidence-estimation","display_name":"confidence estimation","score":0.8080000281333923},{"id":"https://openalex.org/keywords/zero-shot-learning","display_name":"zero-shot learning","score":0.6050000190734863},{"id":"https://openalex.org/keywords/interpretability","display_name":"interpretability","score":0.44699999690055847}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9072999954223633},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.739799976348877},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7110999822616577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6176000237464905},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5202999711036682},{"id":"https://openalex.org/C180505990","wikidata":"https://www.wikidata.org/wiki/Q498267","display_name":"News aggregator","level":2,"score":0.5162000060081482},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4754999876022339},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.46720001101493835},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.46050000190734863},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38920000195503235},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.38690000772476196},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.34689998626708984},{"id":"https://openalex.org/C2185349","wikidata":"https://www.wikidata.org/wiki/Q190558","display_name":"Negation","level":2,"score":0.3449999988079071},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33169999718666077},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C161584116","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate statistics","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2510.05950","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.05950","pdf_url":"https://arxiv.org/pdf/2510.05950","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.05950","doi":"https://doi.org/10.48550/arxiv.2510.05950","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.05950","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.05950","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.05950","pdf_url":"https://arxiv.org/pdf/2510.05950","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414980802.pdf","grobid_xml":"https://content.openalex.org/works/W4414980802.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1685464609","https://openalex.org/W2604847698","https://openalex.org/W2771712594","https://openalex.org/W2897997001","https://openalex.org/W2898647012","https://openalex.org/W2971121529","https://openalex.org/W3092172514","https://openalex.org/W3142110751","https://openalex.org/W3190152617","https://openalex.org/W3199148273","https://openalex.org/W4308900200","https://openalex.org/W4310416691","https://openalex.org/W4327810158","https://openalex.org/W4385965642","https://openalex.org/W4389664922","https://openalex.org/W4389984466","https://openalex.org/W4390784213","https://openalex.org/W4392240262","https://openalex.org/W4393027205","https://openalex.org/W4393153153","https://openalex.org/W4393177844","https://openalex.org/W4401306886","https://openalex.org/W4402500745","https://openalex.org/W4403929306","https://openalex.org/W4404782449","https://openalex.org/W4414281281","https://openalex.org/W4414892853","https://openalex.org/W4414939355","https://openalex.org/W4415798147","https://openalex.org/W4416935216","https://openalex.org/W4417279886","https://openalex.org/W7133215398"],"related_works":["https://openalex.org/W4414892853","https://openalex.org/W4416016825","https://openalex.org/W7127364130","https://openalex.org/W7160887595","https://openalex.org/W7114943192","https://openalex.org/W4413034357","https://openalex.org/W4403707317","https://openalex.org/W4416394448","https://openalex.org/W4403183073","https://openalex.org/W7154660906"],"abstract_inverted_index":{"Time":[0],"series":[1,55],"classification":[2],"(TSC)":[3],"spans":[4],"diverse":[5],"application":[6],"scenarios,":[7],"yet":[8],"labeled":[9,64],"data":[10],"are":[11],"often":[12],"scarce,":[13],"making":[14],"task-specific":[15],"training":[16],"costly":[17],"and":[18,69,110,114,120],"inflexible.":[19],"Recent":[20],"reasoning-oriented":[21],"large":[22],"language":[23],"models":[24],"(LLMs)":[25],"show":[26],"promise":[27],"in":[28],"understanding":[29],"temporal":[30],"patterns,":[31],"but":[32],"purely":[33],"zero-shot":[34],"usage":[35],"remains":[36],"suboptimal.":[37],"We":[38],"propose":[39],"FETA,":[40],"a":[41,53,60,71,87,133,145],"multi-agent":[42,146],"framework":[43,149],"for":[44,66,100],"training-free":[45,135],"TSC":[46,156],"via":[47],"exemplar-based":[48],"in-context":[49,147],"reasoning.":[50],"FETA":[51,128],"decomposes":[52],"multivariate":[54],"into":[56,153],"channel-wise":[57],"subproblems,":[58],"retrieves":[59],"few":[61],"structurally":[62],"similar":[63],"examples":[65],"each":[67],"channel,":[68],"leverages":[70],"reasoning":[72,148],"LLM":[73],"to":[74],"compare":[75],"the":[76,98],"query":[77],"against":[78],"these":[79],"exemplars,":[80],"producing":[81],"channel-level":[82],"labels":[83],"with":[84],"self-assessed":[85],"confidences;":[86],"confidence-weighted":[88],"aggregator":[89],"then":[90],"fuses":[91],"all":[92],"channel":[93],"decisions.":[94],"This":[95],"design":[96],"eliminates":[97],"need":[99],"pretraining":[101],"or":[102],"fine-tuning,":[103],"improves":[104],"efficiency":[105],"by":[106],"pruning":[107],"irrelevant":[108],"channels":[109],"controlling":[111],"input":[112],"length,":[113],"enhances":[115],"interpretability":[116],"through":[117],"exemplar":[118],"grounding":[119],"confidence":[121],"estimation.":[122],"On":[123],"nine":[124],"challenging":[125],"UEA":[126],"datasets,":[127],"achieves":[129],"strong":[130],"accuracy":[131],"under":[132],"fully":[134],"setting,":[136],"surpassing":[137],"multiple":[138],"trained":[139],"baselines.":[140],"These":[141],"results":[142],"demonstrate":[143],"that":[144],"can":[150],"transform":[151],"LLMs":[152],"competitive,":[154],"plug-and-play":[155],"solvers":[157],"without":[158],"any":[159],"parameter":[160],"training.":[161],"The":[162],"code":[163],"is":[164],"available":[165],"at":[166],"https://github.com/SongyuanSui/FETATSC.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}