{"id":"https://openalex.org/W7162796467","doi":"https://doi.org/10.48550/arxiv.2605.29319","title":"Rethinking Stepwise Model Routing: A Cost-Efficient Table Reasoning Perspective","display_name":"Rethinking Stepwise Model Routing: A Cost-Efficient Table Reasoning Perspective","publication_year":2026,"publication_date":"2026-05-28","ids":{"openalex":"https://openalex.org/W7162796467","doi":"https://doi.org/10.48550/arxiv.2605.29319"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.29319","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29319","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.2605.29319","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122381872","display_name":"Shenghao Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Shenghao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137343539","display_name":"Yuxiang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yuxiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137392999","display_name":"Yu Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137320049","display_name":"Dong Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Dong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137358777","display_name":"Shuangwu Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Shuangwu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137326507","display_name":"Jian Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Jian","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/T10028","display_name":"Topic Modeling","score":0.288100004196167,"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/T10028","display_name":"Topic Modeling","score":0.288100004196167,"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":0.2328999936580658,"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/T11719","display_name":"Data Quality and Management","score":0.1875,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.690500020980835},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6704000234603882},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5551999807357788},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5360000133514404},{"id":"https://openalex.org/keywords/model-based-reasoning","display_name":"Model-based reasoning","score":0.47290000319480896},{"id":"https://openalex.org/keywords/opportunistic-reasoning","display_name":"Opportunistic reasoning","score":0.4657999873161316},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.450300008058548},{"id":"https://openalex.org/keywords/reasoning-system","display_name":"Reasoning system","score":0.42969998717308044}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.692300021648407},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.690500020980835},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6704000234603882},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5551999807357788},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5360000133514404},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.47290000319480896},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.4657999873161316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4609000086784363},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.450300008058548},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.42969998717308044},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38530001044273376},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.36340001225471497},{"id":"https://openalex.org/C184896649","wikidata":"https://www.wikidata.org/wiki/Q290066","display_name":"Routing table","level":4,"score":0.35589998960494995},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32670000195503235},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C103057564","wikidata":"https://www.wikidata.org/wiki/Q4751139","display_name":"Analytic reasoning","level":3,"score":0.3095000088214874},{"id":"https://openalex.org/C156201811","wikidata":"https://www.wikidata.org/wiki/Q5418360","display_name":"Evidential reasoning approach","level":4,"score":0.2757999897003174},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C9616225","wikidata":"https://www.wikidata.org/wiki/Q3929429","display_name":"Semantic reasoner","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.29319","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29319","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.2605.29319","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29319","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Reasoning":[1],"Models":[2],"(LRMs)":[3],"achieve":[4],"strong":[5,177],"performance":[6],"on":[7,167],"table":[8,42,65,69,132,144,169],"reasoning":[9,19,30,43,52,104,136,170],"tasks":[10],"but":[11],"incur":[12],"substantial":[13],"inference":[14],"cost":[15],"due":[16],"to":[17,32,110,115,151],"long":[18],"traces.":[20],"Stepwise":[21],"model":[22,39,97,111],"routing":[23,40,117,128],"mitigates":[24],"this":[25],"issue":[26],"by":[27],"dynamically":[28],"assigning":[29],"steps":[31,53],"smaller":[33],"or":[34],"larger":[35],"models.":[36],"However,":[37,106],"stepwise":[38,127],"for":[41,130,155,164],"remains":[44],"underexplored.":[45],"Through":[46],"empirical":[47],"analysis,":[48],"we":[49,122],"find":[50],"that":[51,95,173],"involving":[54],"tables":[55],"contain":[56],"two":[57,162],"types":[58,89],"of":[59,86,143],"tokens":[60,66,79,145],"with":[61,92],"distinct":[62],"uncertainty":[63,85],"distributions:":[64],"grounded":[67],"in":[68,101],"structure,":[70],"such":[71],"as":[72],"cell":[73],"values":[74],"and":[75,77,146,159,179,186],"headers,":[76],"text":[78,147],"representing":[80],"surrounding":[81],"natural-language":[82],"reasoning.":[83,133],"The":[84],"both":[87],"token":[88],"is":[90],"correlated":[91],"the":[93,96,102,141,156,161],"risk":[94],"makes":[98],"an":[99],"error":[100],"next":[103],"step.":[105],"existing":[107],"methods":[108],"fail":[109],"them":[112,150],"separately,":[113],"leading":[114],"suboptimal":[116],"decisions.":[118],"To":[119],"address":[120],"this,":[121],"propose":[123],"EcoTab,":[124],"a":[125,181],"table-aware":[126],"framework":[129],"efficient":[131],"At":[134],"each":[135],"step,":[137],"EcoTab":[138,174],"separately":[139],"estimates":[140],"uncertainties":[142],"tokens,":[148],"maps":[149],"next-step":[152],"failure":[153],"risks":[154,163],"small":[157],"model,":[158],"combines":[160],"routing.":[165],"Experiments":[166],"multiple":[168],"benchmarks":[171],"show":[172],"consistently":[175],"outperforms":[176],"baselines":[178],"achieves":[180],"better":[182],"balance":[183],"between":[184],"accuracy":[185],"efficiency.":[187]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-30T00:00:00"}