{"id":"https://openalex.org/W4404741209","doi":"https://doi.org/10.1109/icbase63199.2024.10762312","title":"Enhancing Mathematical Problem Solving in Large Language Models through Tool-Integrated Reasoning and Python Code Execution","display_name":"Enhancing Mathematical Problem Solving in Large Language Models through Tool-Integrated Reasoning and Python Code Execution","publication_year":2024,"publication_date":"2024-09-20","ids":{"openalex":"https://openalex.org/W4404741209","doi":"https://doi.org/10.1109/icbase63199.2024.10762312"},"language":"en","primary_location":{"id":"doi:10.1109/icbase63199.2024.10762312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icbase63199.2024.10762312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 5th International Conference on Big Data &amp;amp; Artificial Intelligence &amp;amp; Software Engineering (ICBASE)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053414139","display_name":"Suo Li","orcid":"https://orcid.org/0000-0002-9742-367X"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Siyue Li","raw_affiliation_strings":["Northeastern University,Santa Clara,USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University,Santa Clara,USA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5053414139"],"corresponding_institution_ids":["https://openalex.org/I12912129"],"apc_list":null,"apc_paid":null,"fwci":2.9009,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.92257739,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"165","last_page":"168"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.7067999839782715,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.7067999839782715,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.6640999913215637,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/python","display_name":"Python (programming language)","score":0.8335292339324951},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.7970921993255615},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7843465805053711},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33200642466545105}],"concepts":[{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.8335292339324951},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.7970921993255615},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7843465805053711},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33200642466545105}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icbase63199.2024.10762312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icbase63199.2024.10762312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 5th International Conference on Big Data &amp;amp; Artificial Intelligence &amp;amp; Software Engineering (ICBASE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1840435438","https://openalex.org/W2923014074","https://openalex.org/W2963617989","https://openalex.org/W4401005187","https://openalex.org/W4401578177","https://openalex.org/W6755207826","https://openalex.org/W6758604235","https://openalex.org/W6762592649","https://openalex.org/W6768021236","https://openalex.org/W6771324808","https://openalex.org/W6778883912","https://openalex.org/W6791376898","https://openalex.org/W6798182279","https://openalex.org/W6872229276","https://openalex.org/W6872794210"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2341492732","https://openalex.org/W3187193180","https://openalex.org/W106542691","https://openalex.org/W1699080303","https://openalex.org/W4297799326","https://openalex.org/W2207495067","https://openalex.org/W1906486629"],"abstract_inverted_index":{"Mathematical":[0],"problem":[1],"solving":[2],"remains":[3],"a":[4,29,60,69,78,97,136,162],"significant":[5,124],"challenge":[6],"for":[7,164],"large":[8],"language":[9,74],"models":[10,143],"(LLMs)":[11],"due":[12],"to":[13,41,109,168],"the":[14,21,47,55,85,92,107,128,145,152],"inherent":[15],"complexity":[16],"of":[17,51,72,80,88,103,117,133,139,154],"mathematical":[18,48,75,155],"reasoning":[19,49,89,156,170],"and":[20,37,45,111,135,171],"precision":[22],"required":[23],"in":[24,144,157,174],"calculations.":[25],"This":[26,147],"paper":[27],"introduces":[28],"novel":[30],"approach":[31],"that":[32,100],"leverages":[33],"Tool-Integrated":[34],"Reasoning":[35],"(TIR)":[36],"Python":[38,113],"code":[39,114],"execution":[40],"address":[42],"these":[43],"challenges":[44],"enhance":[46],"capabilities":[50],"LLMs.":[52],"We":[53],"fine-tune":[54],"DeepSeekMath-Base":[56],"7B":[57],"model":[58,108,129],"using":[59,77],"two-stage":[61],"process.":[62,120],"The":[63],"first":[64],"stage":[65],"involves":[66],"training":[67],"on":[68],"diverse":[70],"dataset":[71,99],"natural":[73],"problems":[76],"Chain":[79],"Thought":[81],"(CoT)":[82],"template,":[83],"improving":[84],"model\u2019s":[86],"understanding":[87],"paths.":[90],"In":[91],"second":[93],"stage,":[94],"we":[95],"introduce":[96],"synthetic":[98],"includes":[101],"examples":[102],"tool-integrated":[104],"reasoning,":[105],"enabling":[106],"generate":[110],"execute":[112],"as":[115],"part":[116],"its":[118],"problem-solving":[119],"Our":[121],"results":[122],"demonstrate":[123],"performance":[125],"improvements,":[126],"with":[127],"achieving":[130],"an":[131],"accuracy":[132],"0.7782":[134],"maj@N":[137],"score":[138],"0.7344,":[140],"outperforming":[141],"existing":[142],"domain.":[146],"research":[148],"not":[149],"only":[150],"advances":[151],"state":[153],"LLMs":[158],"but":[159],"also":[160],"provides":[161],"framework":[163],"integrating":[165],"external":[166],"tools":[167],"improve":[169],"decision-making":[172],"processes":[173],"AI":[175],"systems.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}
