{"id":"https://openalex.org/W7155008169","doi":"https://doi.org/10.48550/arxiv.2604.16278","title":"Learning to Reason with Insight for Informal Theorem Proving","display_name":"Learning to Reason with Insight for Informal Theorem Proving","publication_year":2026,"publication_date":"2026-04-17","ids":{"openalex":"https://openalex.org/W7155008169","doi":"https://doi.org/10.48550/arxiv.2604.16278"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.16278","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.16278","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.16278","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134064045","display_name":"Yunhe Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yunhe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134095032","display_name":"Hao Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134053696","display_name":"Bowen Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deng, Bowen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134031388","display_name":"wei Wang","orcid":"https://orcid.org/0000-0001-7825-3874"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102808478","display_name":"M. Ruan","orcid":"https://orcid.org/0009-0008-0458-5751"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruan, Mengzhe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039863234","display_name":"Hanxu Hou","orcid":"https://orcid.org/0000-0001-7328-9341"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hou, Hanxu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134061447","display_name":"Zhongxiang Dai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai, Zhongxiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134053695","display_name":"Siyang Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Siyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100407080","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0003-0089-8140"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Chao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134045658","display_name":"Shuang Qiu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiu, Shuang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134039190","display_name":"Linqi Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Linqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":11,"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/T10126","display_name":"Logic, programming, and type systems","score":0.4361000061035156,"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":0.4361000061035156,"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":0.10760000348091125,"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/T11435","display_name":"Polynomial and algebraic computation","score":0.07410000264644623,"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/mathematical-proof","display_name":"Mathematical proof","score":0.84170001745224},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.6833000183105469},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6668000221252441},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5983999967575073},{"id":"https://openalex.org/keywords/automated-theorem-proving","display_name":"Automated theorem proving","score":0.58160001039505},{"id":"https://openalex.org/keywords/automated-reasoning","display_name":"Automated reasoning","score":0.4138000011444092},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4088999927043915}],"concepts":[{"id":"https://openalex.org/C108710211","wikidata":"https://www.wikidata.org/wiki/Q11538","display_name":"Mathematical proof","level":2,"score":0.84170001745224},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.6833000183105469},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6729000210762024},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6668000221252441},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5983999967575073},{"id":"https://openalex.org/C206880738","wikidata":"https://www.wikidata.org/wiki/Q431667","display_name":"Automated theorem proving","level":2,"score":0.58160001039505},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.4138000011444092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41119998693466187},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4088999927043915},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4058000147342682},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.40220001339912415},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3889999985694885},{"id":"https://openalex.org/C94461902","wikidata":"https://www.wikidata.org/wiki/Q2762418","display_name":"Formal proof","level":3,"score":0.3359000086784363},{"id":"https://openalex.org/C203265346","wikidata":"https://www.wikidata.org/wiki/Q11387554","display_name":"Proof assistant","level":3,"score":0.33160001039505005},{"id":"https://openalex.org/C124978682","wikidata":"https://www.wikidata.org/wiki/Q1201019","display_name":"Proof of concept","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C47884741","wikidata":"https://www.wikidata.org/wiki/Q1166618","display_name":"Mathematical logic","level":2,"score":0.2912999987602234}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.16278","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.16278","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":"doi:10.48550/arxiv.2604.16278","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.16278","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":"article"},"sustainable_development_goals":[{"score":0.8572438955307007,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Although":[0],"most":[1],"of":[2,43,48,85],"the":[3,46,50,106,117,122],"automated":[4],"theorem-proving":[5],"approaches":[6],"depend":[7],"on":[8,147],"formal":[9],"proof":[10,103,124],"systems,":[11],"informal":[12,37,95],"theorem":[13,38],"proving":[14,39],"can":[15,172],"align":[16],"better":[17],"with":[18],"large":[19],"language":[20,26],"models'":[21],"(LLMs)":[22],"strength":[23],"in":[24,36],"natural":[25],"processing.":[27],"In":[28],"this":[29,71,142,153],"work,":[30],"we":[31,61],"identify":[32,167],"a":[33,41,64,90,110,133],"primary":[34],"bottleneck":[35],"as":[40],"lack":[42],"insight,":[44],"namely":[45],"difficulty":[47],"recognizing":[49],"core":[51,100,170],"techniques":[52,101,171],"required":[53],"to":[54,69,78,166],"solve":[55],"complex":[56],"problems.":[57],"To":[58],"address":[59],"this,":[60],"propose":[62],"$\\texttt{DeepInsight}$,":[63],"unified":[65],"training":[66],"framework":[67,83],"designed":[68],"cultivate":[70],"essential":[72],"reasoning":[73],"skill":[74],"and":[75,102,127,130,168],"enable":[76],"LLMs":[77],"perform":[79],"insightful":[80],"reasoning.":[81,177],"Our":[82,145],"consists":[84],"three":[86],"components:":[87],"(1)":[88],"$\\texttt{DeepInsightTheorem}$,":[89],"hierarchical":[91],"dataset":[92],"that":[93,115,137,152,163],"structures":[94],"proofs":[96],"by":[97],"explicitly":[98],"extracting":[99],"sketches":[104],"alongside":[105],"final":[107],"proof;":[108],"(2)":[109],"Progressive":[111],"Multi-Stage":[112],"SFT":[113],"strategy":[114,156],"mimics":[116],"human":[118],"learning":[119],"process,":[120],"teaching":[121,164],"model":[123],"writing,":[125],"planning,":[126],"insight":[128,143],"identification;":[129],"(3)":[131],"$\\texttt{InsightPO}$,":[132],"policy":[134],"optimization":[135],"method":[136],"assigns":[138],"structured":[139],"rewards":[140],"over":[141],"hierarchy.":[144],"experiments":[146],"challenging":[148],"mathematical":[149,176],"benchmarks":[150],"demonstrate":[151,162],"insight-aware":[154],"generation":[155],"significantly":[157],"outperforms":[158],"baselines.":[159],"These":[160],"results":[161],"models":[165],"apply":[169],"substantially":[173],"improve":[174],"their":[175]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-21T00:00:00"}