{"id":"https://openalex.org/W7166802108","doi":"https://doi.org/10.18653/v1/2026.acl-long.702","title":"STReasoner: Empowering LLMs for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learning","display_name":"STReasoner: Empowering LLMs for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166802108","doi":"https://doi.org/10.18653/v1/2026.acl-long.702"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.702","doi":"https://doi.org/10.18653/v1/2026.acl-long.702","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.702","pdf_url":"https://aclanthology.org/2026.acl-long.702.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.acl-long.702.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139738297","display_name":"Juntong Ni","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juntong Ni","raw_affiliation_strings":["Emory University , 2 Microsoft ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Emory University , 2 Microsoft ,","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121986331","display_name":"Shiyu Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiyu Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139789436","display_name":"Qi He","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122009556","display_name":"Ming Jin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I11701301","display_name":"Griffith University","ror":"https://ror.org/02sc3r913","country_code":"AU","type":"education","lineage":["https://openalex.org/I11701301"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ming Jin","raw_affiliation_strings":["Griffith University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Griffith University","institution_ids":["https://openalex.org/I11701301"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109029396","display_name":"Wei Jin","orcid":"https://orcid.org/0009-0006-8681-0718","observed_orcids":["https://orcid.org/0009-0006-8681-0718"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Jin","raw_affiliation_strings":["Emory University , 2 Microsoft ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Emory University , 2 Microsoft ,","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I150468666"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":18.8756,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.99223687,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"15369","last_page":"15416"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.8842999935150146,"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":0.8842999935150146,"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/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.022700000554323196,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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/T10028","display_name":"Topic Modeling","score":0.022600000724196434,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spatio-temporal-reasoning","display_name":"spatio-temporal reasoning","score":0.9990000128746033},{"id":"https://openalex.org/keywords/time-series","display_name":"time series","score":0.8980000019073486},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9169999957084656},{"id":"https://openalex.org/keywords/graph-diffusion-models","display_name":"graph diffusion models","score":0.4880000054836273},{"id":"https://openalex.org/keywords/entity-identification","display_name":"entity identification","score":0.8320000171661377}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4424000084400177},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.4153999984264374},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4099999964237213},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.40779998898506165},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.39800000190734863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.383899986743927},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.36800000071525574},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.3111000061035156},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.29190000891685486},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.702","doi":"https://doi.org/10.18653/v1/2026.acl-long.702","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.702","pdf_url":"https://aclanthology.org/2026.acl-long.702.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.702","doi":"https://doi.org/10.18653/v1/2026.acl-long.702","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.702","pdf_url":"https://aclanthology.org/2026.acl-long.702.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G5859890489","display_name":"Collaborative Research: III: Medium: Empowering Graph Neural Networks from a Data Perspective","funder_award_id":"2504088","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337355","display_name":"National Institute of Allergy and Infectious Diseases","ror":"https://ror.org/043z4tv69"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166802108.pdf","grobid_xml":"https://content.openalex.org/works/W7166802108.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4414988559","https://openalex.org/W7172256022","https://openalex.org/W4417299775","https://openalex.org/W7104818873","https://openalex.org/W7135093348","https://openalex.org/W4410636960","https://openalex.org/W4412889845","https://openalex.org/W4417302307","https://openalex.org/W7131641735","https://openalex.org/W7163184220"],"abstract_inverted_index":{"Spatio-temporal":[0],"reasoning":[1],"in":[2,23],"time":[3,87],"series":[4],"involves":[5],"the":[6,34,48,130],"explicit":[7,94],"synthesis":[8,77],"of":[9,56,132],"temporal":[10],"dynamics,":[11],"spatial":[12,114],"dependencies,":[13],"and":[14,31,67,91,125,135],"textual":[15],"context.This":[16],"capability":[17],"is":[18,142],"vital":[19],"for":[20,93],"high-stakes":[21],"decision-making":[22],"systems":[24],"such":[25],"as":[26],"traffic":[27],"networks,":[28],"power":[29],"grids,":[30],"disease":[32],"propagation.However,":[33],"field":[35],"remains":[36],"underdeveloped":[37],"because":[38],"most":[39],"existing":[40],"works":[41],"prioritize":[42],"predictive":[43],"accuracy":[44,121],"over":[45],"reasoning.To":[46,95],"address":[47],"gap,":[49],"we":[50,100],"introduce":[51,101],"ST-Bench,":[52],"a":[53,72,103],"benchmark":[54],"consisting":[55],"four":[57],"core":[58],"tasks,":[59],"including":[60],"etiological":[61],"reasoning,":[62,66],"entity":[63],"identification,":[64],"correlation":[65],"in-context":[68],"forecasting,":[69],"developed":[70],"via":[71],"network":[73],"SDE-based":[74],"multi-agent":[75],"data":[76],"pipeline.We":[78],"then":[79],"propose":[80],"STReasoner,":[81],"which":[82],"empowers":[83],"LLM":[84],"to":[85,113,138],"integrate":[86],"series,":[88],"graph":[89],"structure,":[90],"text":[92],"promote":[96],"spatially":[97],"grounded":[98],"logic,":[99],"S-GRPO,":[102],"reinforcement":[104],"learning":[105],"algorithm":[106],"that":[107,117],"rewards":[108],"performance":[109],"gains":[110,122],"specifically":[111],"attributable":[112],"information.Experiments":[115],"show":[116],"STReasoner":[118],"achieves":[119],"average":[120],"between":[123],"17%":[124],"135%":[126],"at":[127,144],"only":[128],"0.004\u00d7":[129],"cost":[131],"proprietary":[133],"models":[134],"generalizes":[136],"robustly":[137],"real-world":[139],"data.Our":[140],"code":[141],"available":[143],"https://github.com/LingFengGold/STReasoner.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2026-07-02T00:00:00"}