{"id":"https://openalex.org/W7134827806","doi":"https://doi.org/10.48550/arxiv.2603.07528","title":"TableMind++: An Uncertainty-Aware Programmatic Agent for Tool-Augmented Table Reasoning","display_name":"TableMind++: An Uncertainty-Aware Programmatic Agent for Tool-Augmented Table Reasoning","publication_year":2026,"publication_date":"2026-03-08","ids":{"openalex":"https://openalex.org/W7134827806","doi":"https://doi.org/10.48550/arxiv.2603.07528"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.07528","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.07528","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.2603.07528","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054174049","display_name":"Mingyue Cheng","orcid":"https://orcid.org/0000-0001-9873-7681"},"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/A5128631160","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/A5128665388","display_name":"Chuang Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Chuang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128656602","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/A5128650875","display_name":"Qingyang Mao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mao, Qingyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128662852","display_name":"Jie Ouyang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ouyang, Jie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128649324","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":"last","author":{"id":"https://openalex.org/A5128655372","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.39079999923706055,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.39079999923706055,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.16750000417232513,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.09440000355243683,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/inference","display_name":"Inference","score":0.5918999910354614},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5748000144958496},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5662000179290771},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5450000166893005},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.47269999980926514},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.45179998874664307},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.44839999079704285},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.37459999322891235}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7946000099182129},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5918999910354614},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5748000144958496},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5662000179290771},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5450000166893005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5440000295639038},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5127000212669373},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.47269999980926514},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.45179998874664307},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.44839999079704285},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.37459999322891235},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3720000088214874},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.37049999833106995},{"id":"https://openalex.org/C65682993","wikidata":"https://www.wikidata.org/wiki/Q1056451","display_name":"Reflection (computer programming)","level":2,"score":0.36469998955726624},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3384999930858612},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.32760000228881836},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.27070000767707825},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.26350000500679016}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.07528","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.07528","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.2603.07528","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.07528","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":[{"score":0.41708287596702576,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Table":[0],"reasoning":[1,20,191],"requires":[2],"models":[3,207],"to":[4,112,121,130,139,151,168,184,208],"jointly":[5],"perform":[6],"semantic":[7],"understanding":[8],"and":[9,29,62,77,85,145,170,205],"precise":[10],"numerical":[11,31],"operations.":[12],"Most":[13],"existing":[14],"methods":[15],"rely":[16],"on":[17,73,195],"a":[18,42,52,65,82,95,107,125,186],"single-turn":[19],"paradigm":[21],"over":[22],"tables":[23],"which":[24,164],"suffers":[25],"from":[26,189],"context":[27],"overflow":[28],"weak":[30],"sensitivity.":[32],"To":[33,155],"address":[34,152],"these":[35],"limitations,":[36],"we":[37,117,134,159,179],"previously":[38],"proposed":[39],"TableMind":[40,58,93],"as":[41],"tuning-based":[43],"autonomous":[44,214],"programmatic":[45,99],"agent":[46],"that":[47,110,199],"simulates":[48],"human-like":[49],"interaction":[50],"within":[51],"lightweight":[53],"large":[54],"language":[55],"model":[56],"(LLM).":[57],"internalizes":[59],"planning,":[60],"action,":[61],"reflection":[63],"through":[64],"two-stage":[66],"training":[67,215],"strategy":[68],"involving":[69],"supervised":[70],"fine-tuning":[71],"(SFT)":[72],"filtered":[74],"high-quality":[75],"data":[76],"reinforcement":[78],"learning":[79],"(RL)":[80],"via":[81],"multi-perspective":[83],"reward":[84],"the":[86,101,210],"Rank-Aware":[87],"Policy":[88],"Optimization":[89],"(RAPO)":[90],"algorithm.":[91],"While":[92],"establishes":[94],"solid":[96],"foundation":[97,120],"for":[98,143,174],"agents,":[100],"inherent":[102],"stochasticity":[103],"of":[104,212],"LLMs":[105],"remains":[106],"critical":[108],"challenge":[109],"leads":[111],"hallucinations.":[113,132],"In":[114],"this":[115,119],"paper,":[116],"extend":[118],"TableMind++":[122,200],"by":[123],"introducing":[124],"novel":[126],"uncertainty-aware":[127],"inference":[128],"framework":[129],"mitigate":[131],"Specifically,":[133],"propose":[135],"memory-guided":[136],"plan":[137],"pruning":[138],"retrieve":[140],"historical":[141],"trajectories":[142],"validating":[144],"filtering":[146],"out":[147],"logically":[148],"flawed":[149],"plans":[150],"epistemic":[153],"uncertainty.":[154],"ensure":[156],"execution":[157],"precision,":[158],"introduce":[160],"confidence-based":[161],"action":[162],"refinement":[163],"monitors":[165],"token-level":[166],"probabilities":[167],"detect":[169],"self-correct":[171],"syntactic":[172],"noise":[173],"aleatoric":[175],"uncertainty":[176,217],"mitigation.":[177],"Finally,":[178],"employ":[180],"dual-weighted":[181],"trajectory":[182],"aggregation":[183],"synthesize":[185],"robust":[187],"consensus":[188],"multiple":[190],"paths.":[192],"Extensive":[193],"experiments":[194],"diverse":[196],"benchmarks":[197],"demonstrate":[198],"consistently":[201],"outperforms":[202],"previous":[203],"baselines":[204],"proprietary":[206],"validate":[209],"effectiveness":[211],"integrating":[213],"with":[216],"quantification.":[218],"Our":[219],"code":[220],"is":[221],"available.":[222]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-11T00:00:00"}