{"id":"https://openalex.org/W7118302560","doi":"https://doi.org/10.48550/arxiv.2601.03248","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":"2026-01-06","ids":{"openalex":"https://openalex.org/W7118302560","doi":"https://doi.org/10.48550/arxiv.2601.03248"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2601.03248","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.03248","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2601.03248","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121995681","display_name":"Juntong Ni","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ni, Juntong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121986331","display_name":"Shiyu Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Shiyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122009556","display_name":"Ming Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Ming","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121995770","display_name":"Qi He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Qi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5121984551","display_name":"Wei Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Wei","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5121995681"],"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.2644999921321869,"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":0.2644999921321869,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.1574999988079071,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.13130000233650208,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7717000246047974},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.5167999863624573},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5080999732017517},{"id":"https://openalex.org/keywords/predictive-power","display_name":"Predictive power","score":0.4934999942779541},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.47510001063346863},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.46309998631477356},{"id":"https://openalex.org/keywords/time-series","display_name":"Time series","score":0.4390000104904175}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7717000246047974},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.652400016784668},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.597599983215332},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5564000010490417},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.5167999863624573},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5080999732017517},{"id":"https://openalex.org/C2778136018","wikidata":"https://www.wikidata.org/wiki/Q10350689","display_name":"Predictive power","level":2,"score":0.4934999942779541},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.47510001063346863},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.46309998631477356},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.4390000104904175},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.42820000648498535},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.4066999852657318},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.31040000915527344},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.2847999930381775},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2601.03248","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.03248","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2601.03248","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.03248","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":"article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7836431264877319}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Spatio-temporal":[0],"reasoning":[1],"in":[2,24],"time":[3,91],"series":[4],"involves":[5],"the":[6,36,51,136],"explicit":[7,98],"synthesis":[8,80],"of":[9,59,138],"temporal":[10],"dynamics,":[11],"spatial":[12,119],"dependencies,":[13],"and":[14,32,70,95,131,141],"textual":[15],"context.":[16],"This":[17],"capability":[18],"is":[19],"vital":[20],"for":[21,97],"high-stakes":[22],"decision-making":[23],"systems":[25],"such":[26],"as":[27],"traffic":[28],"networks,":[29],"power":[30],"grids,":[31],"disease":[33],"propagation.":[34],"However,":[35],"field":[37],"remains":[38],"underdeveloped":[39],"because":[40],"most":[41],"existing":[42],"works":[43],"prioritize":[44],"predictive":[45],"accuracy":[46,127],"over":[47],"reasoning.":[48,99],"To":[49,100],"address":[50],"gap,":[52],"we":[53,105],"introduce":[54,106],"ST-Bench,":[55],"a":[56,75,108],"benchmark":[57],"consisting":[58],"four":[60],"core":[61],"tasks,":[62],"including":[63],"etiological":[64],"reasoning,":[65,69],"entity":[66],"identification,":[67],"correlation":[68],"in-context":[71],"forecasting,":[72],"developed":[73],"via":[74],"network":[76],"SDE-based":[77],"multi-agent":[78],"data":[79],"pipeline.":[81],"We":[82],"then":[83],"propose":[84],"STReasoner,":[85],"which":[86],"empowers":[87],"LLM":[88],"to":[89,118,144],"integrate":[90],"series,":[92],"graph":[93],"structure,":[94],"text":[96],"promote":[101],"spatially":[102],"grounded":[103],"logic,":[104],"S-GRPO,":[107],"reinforcement":[109],"learning":[110],"algorithm":[111],"that":[112,123],"rewards":[113],"performance":[114],"gains":[115,128],"specifically":[116],"attributable":[117],"information.":[120],"Experiments":[121],"show":[122],"STReasoner":[124],"achieves":[125],"average":[126],"between":[129],"17%":[130],"135%":[132],"at":[133],"only":[134],"0.004X":[135],"cost":[137],"proprietary":[139],"models":[140],"generalizes":[142],"robustly":[143],"real-world":[145],"data.":[146]},"counts_by_year":[],"updated_date":"2026-01-08T20:10:11.968330","created_date":"2026-01-08T00:00:00"}