{"id":"https://openalex.org/W4405425550","doi":"https://doi.org/10.48550/arxiv.2408.11172","title":"SubgoalXL: Subgoal-based Expert Learning for Theorem Proving","display_name":"SubgoalXL: Subgoal-based Expert Learning for Theorem Proving","publication_year":2024,"publication_date":"2024-08-20","ids":{"openalex":"https://openalex.org/W4405425550","doi":"https://doi.org/10.48550/arxiv.2408.11172"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2408.11172","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.11172","pdf_url":"https://arxiv.org/pdf/2408.11172","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2408.11172","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101702140","display_name":"Xueliang Zhao","orcid":"https://orcid.org/0000-0003-0436-1084","observed_orcids":["https://orcid.org/0000-0003-0436-1084"]},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhao, Xueliang","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052137404","display_name":"Lin Zheng","orcid":"https://orcid.org/0000-0003-0351-4827","observed_orcids":["https://orcid.org/0000-0003-0351-4827"]},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zheng, Lin","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110158653","display_name":"Haige Bo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo, Haige","raw_affiliation_strings":["SambaNova Systems"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SambaNova Systems","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056709204","display_name":"Changran Hu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Changran","raw_affiliation_strings":["SambaNova Systems"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SambaNova Systems","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090396089","display_name":"Urmish Thakker","orcid":"https://orcid.org/0000-0002-0515-9155","observed_orcids":["https://orcid.org/0000-0002-0515-9155"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thakker, Urmish","raw_affiliation_strings":["SambaNova Systems"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SambaNova Systems","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101497114","display_name":"Lingpeng Kong","orcid":"https://orcid.org/0000-0002-9407-7193","observed_orcids":["https://orcid.org/0000-0002-9407-7193"]},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kong, Lingpeng","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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/T10126","display_name":"Logic, programming, and type systems","score":0.36739999055862427,"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/T10126","display_name":"Logic, programming, and type systems","score":0.36739999055862427,"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":0.301800012588501,"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"}},{"id":"https://openalex.org/T13904","display_name":"Artificial Intelligence Applications","score":0.09109999984502792,"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/formal-theorem-proving","display_name":"formal theorem proving","score":0.9660000205039978},{"id":"https://openalex.org/keywords/expert-learning","display_name":"expert learning","score":0.8299999833106995},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9459999799728394},{"id":"https://openalex.org/keywords/isabelle-proof-assistant","display_name":"Isabelle","score":0.8859999775886536},{"id":"https://openalex.org/keywords/proof-generation","display_name":"proof generation","score":0.5429999828338623},{"id":"https://openalex.org/keywords/data-efficiency","display_name":"data efficiency","score":0.7059999704360962},{"id":"https://openalex.org/keywords/multi-step-reasoning","display_name":"multi-step reasoning","score":0.9200000166893005},{"id":"https://openalex.org/keywords/mathematical-problem-solving","display_name":"mathematical problem solving","score":0.5049999952316284}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.43748319149017334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40524691343307495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.38838106393814087},{"id":"https://openalex.org/C2777686260","wikidata":"https://www.wikidata.org/wiki/Q144037","display_name":"Calculus (dental)","level":2,"score":0.3706090748310089},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.34338992834091187},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.11002281308174133},{"id":"https://openalex.org/C199343813","wikidata":"https://www.wikidata.org/wiki/Q12128","display_name":"Dentistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2408.11172","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.11172","pdf_url":"https://arxiv.org/pdf/2408.11172","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2408.11172","doi":"https://doi.org/10.48550/arxiv.2408.11172","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2408.11172","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2408.11172","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.11172","pdf_url":"https://arxiv.org/pdf/2408.11172","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405425550.pdf","grobid_xml":"https://content.openalex.org/works/W4405425550.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415145323","https://openalex.org/W4404088889","https://openalex.org/W4415329738","https://openalex.org/W7116981254","https://openalex.org/W4404783189","https://openalex.org/W4415337241","https://openalex.org/W4404352990","https://openalex.org/W4417126526","https://openalex.org/W4398796786","https://openalex.org/W4417268860"],"abstract_inverted_index":{"Formal":[0],"theorem":[1,44,170],"proving,":[2,171],"a":[3,28,118],"field":[4],"at":[5,185],"the":[6,47,55,64,109,127,154,174],"intersection":[7],"of":[8,57,122,135,156,177],"mathematics":[9,59],"and":[10,60,63,77,105,145,161],"computer":[11],"science,":[12],"has":[13],"seen":[14],"renewed":[15],"interest":[16],"with":[17,35,95],"advancements":[18],"in":[19,42,71,113,124,168],"large":[20],"language":[21],"models":[22],"(LLMs).":[23],"This":[24],"paper":[25],"introduces":[26],"SubgoalXL,":[27],"novel":[29],"approach":[30],"that":[31],"synergizes":[32],"subgoal-based":[33,114],"proofs":[34],"expert":[36,97],"learning":[37,98],"to":[38,173],"enhance":[39],"LLMs'":[40],"capabilities":[41],"formal":[43,102,169],"proving":[45],"within":[46],"Isabelle":[48,110,125],"environment.":[49],"SubgoalXL":[50,81,116,138],"addresses":[51],"two":[52],"critical":[53],"challenges:":[54],"scarcity":[56],"specialized":[58],"theorem-proving":[61],"data,":[62],"need":[65],"for":[66,165],"improved":[67],"multi-step":[68],"reasoning":[69,167,179],"abilities":[70],"LLMs.":[72],"By":[73],"optimizing":[74],"data":[75,159],"efficiency":[76],"employing":[78,162],"subgoal-level":[79],"supervision,":[80],"extracts":[82],"richer":[83],"information":[84],"from":[85,149],"limited":[86,158],"human-generated":[87],"proofs.":[88],"The":[89,181],"framework":[90],"integrates":[91],"subgoal-oriented":[92],"proof":[93],"strategies":[94],"an":[96,132],"system,":[99],"iteratively":[100],"refining":[101],"statement,":[103],"proof,":[104],"subgoal":[106],"generators.":[107],"Leveraging":[108],"environment's":[111],"advantages":[112],"proofs,":[115],"achieves":[117],"new":[119],"state-of-the-art":[120],"performance":[121],"56.1\\%":[123],"on":[126],"standard":[128],"miniF2F":[129],"dataset,":[130],"marking":[131],"absolute":[133],"improvement":[134],"4.9\\%.":[136],"Notably,":[137],"successfully":[139],"solves":[140],"41":[141],"AMC12,":[142],"9":[143],"AIME,":[144],"3":[146],"IMO":[147],"problems":[148],"miniF2F.":[150],"These":[151],"results":[152],"underscore":[153],"effectiveness":[155],"maximizing":[157],"utility":[160],"targeted":[163],"guidance":[164],"complex":[166],"contributing":[172],"ongoing":[175],"advancement":[176],"AI":[178],"capabilities.":[180],"implementation":[182],"is":[183],"available":[184],"\\url{https://github.com/zhaoxlpku/SubgoalXL}.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2024-12-16T00:00:00"}