{"id":"https://openalex.org/W7131669269","doi":"https://doi.org/10.48550/arxiv.2602.21265","title":"ToolMATH: A Math Tool Benchmark for Realistic Long-Horizon Multi-Tool Reasoning","display_name":"ToolMATH: A Math Tool Benchmark for Realistic Long-Horizon Multi-Tool Reasoning","publication_year":2026,"publication_date":"2026-02-24","ids":{"openalex":"https://openalex.org/W7131669269","doi":"https://doi.org/10.48550/arxiv.2602.21265"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.21265","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","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":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123887920","display_name":"Hyeonje Choi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Choi, Hyeonje","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126888585","display_name":"Jeongsoo Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Jeongsoo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126899960","display_name":"Hyojun Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Hyojun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5110801176","display_name":"Jay Yoon Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Jay-Yoon","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5123887920"],"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.2863999903202057,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.2863999903202057,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.08820000290870667,"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/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.08179999887943268,"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/benchmark","display_name":"Benchmark (surveying)","score":0.8605999946594238},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6848999857902527},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.47269999980926514},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.46470001339912415},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.4528999924659729},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.44760000705718994}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8605999946594238},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7099999785423279},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6848999857902527},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.47269999980926514},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.46470001339912415},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.4528999924659729},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4498000144958496},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.44760000705718994},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.4253999888896942},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3986000120639801},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.39480000734329224},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.36550000309944153},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32429999113082886},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C2780210234","wikidata":"https://www.wikidata.org/wiki/Q422638","display_name":"Action plan","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.25290000438690186}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.21265","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.21265","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.21265","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":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.21265","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"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":{"We":[0],"introduce":[1],"\\ToolMATH,":[2],"a":[3,32],"math-grounded":[4],"benchmark":[5,35,140],"that":[6,99,142,176],"evaluates":[7],"tool-augmented":[8,68],"language":[9],"models":[10,165],"in":[11,67,157],"realistic":[12],"multi-tool":[13],"environments":[14],"where":[15],"the":[16,53,56,72,100,107,113,144],"output":[17],"depends":[18],"on":[19],"calling":[20],"schema-specified":[21],"tools":[22,150],"and":[23,51,83,94,119,184,190],"sustaining":[24],"multi-step":[25],"execution.":[26],"It":[27],"turns":[28],"math":[29],"problems":[30],"into":[31,135,166],"controlled,":[33],"correctness-checkable":[34],"with":[36,92],"tool":[37,49,168],"sets,":[38],"enabling":[39],"systematic":[40],"evaluation":[41,97],"of":[42,55,64,115,193],"model":[43],"reliability":[44],"under":[45],"(1)":[46],"large,":[47],"overlapping":[48],"catalogs":[50],"(2)":[52],"absence":[54],"intended":[57,145],"capability.":[58],"\\ToolMATH":[59,78],"provides":[60],"actionable":[61],"diagnostic":[62],"evidence":[63],"failure":[65,102],"modes":[66],"agents,":[69],"helping":[70],"identify":[71],"control":[73],"mechanisms":[74],"required":[75],"for":[76],"robustness.":[77],"roughly":[79],"contains":[80],"8k":[81],"questions":[82,93],"12k":[84],"tools;":[85],"we":[86],"provide":[87],"an":[88],"additional":[89],"hard-set":[90],"\\ToolMATHHard":[91],"tools.":[95],"Our":[96],"reveals":[98],"key":[101],"factor":[103],"is":[104,147],"due":[105],"to":[106,109,112],"inability":[108],"reason,":[110],"leading":[111],"accumulation":[114],"intermediate":[116],"results'":[117],"errors":[118],"constrain":[120],"later":[121],"decisions.":[122],"Tool-list":[123],"redundancy":[124],"do":[125],"not":[126],"simply":[127],"add":[128],"noise,":[129],"but":[130],"amplify":[131],"small":[132],"early":[133],"deviations":[134],"irreversible":[136],"execution":[137],"drift.":[138],"The":[139],"highlights":[141],"when":[143],"capability":[146],"missing,":[148],"distractor":[149],"can":[151,162],"sometimes":[152],"serve":[153],"as":[154],"partial":[155],"substitutes":[156],"solution":[158],"paths,":[159],"yet":[160],"they":[161],"also":[163],"mislead":[164],"ungrounded":[167],"trajectories.":[169],"Finally,":[170],"comparisons":[171],"between":[172],"tool-use":[173],"protocols":[174],"emphasize":[175],"improvements":[177],"come":[178],"less":[179],"from":[180,186],"local":[181],"action":[182],"selection":[183],"more":[185],"long-range":[187],"plan":[188],"coherence":[189],"disciplined":[191],"use":[192],"observations.":[194]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-27T00:00:00"}
