{"id":"https://openalex.org/W4416528736","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1752","title":"Better LLM Reasoning via Dual-Play","display_name":"Better LLM Reasoning via Dual-Play","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4416528736","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1752"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1752","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1752","pdf_url":"https://aclanthology.org/2026.findings-acl.1752.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1752.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101644732","display_name":"Zhengxin Zhang","orcid":"https://orcid.org/0000-0003-4576-7275"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhengxin Zhang","raw_affiliation_strings":["Cornell University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019261957","display_name":"Chenyu Huang","orcid":"https://orcid.org/0000-0001-9521-5650"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chengyu Huang","raw_affiliation_strings":["Cornell University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091493188","display_name":"A. Li","orcid":"https://orcid.org/0000-0001-5012-6013"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aochong Oliver Li","raw_affiliation_strings":["Cornell University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120609559","display_name":"Claire Cardie","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Claire Cardie","raw_affiliation_strings":["Cornell University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02716141,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"35111","last_page":"35139"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6930000185966492,"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/T10028","display_name":"Topic Modeling","score":0.6930000185966492,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.04100000113248825,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.02850000001490116,"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/adversarial-system","display_name":"Adversarial system","score":0.7506999969482422},{"id":"https://openalex.org/keywords/verifiable-secret-sharing","display_name":"Verifiable secret sharing","score":0.5396000146865845},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.5339000225067139},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.49880000948905945},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4562000036239624},{"id":"https://openalex.org/keywords/problem-solver","display_name":"Problem solver","score":0.4537999927997589},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.39629998803138733},{"id":"https://openalex.org/keywords/base","display_name":"Base (topology)","score":0.37610000371932983}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7885000109672546},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7506999969482422},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5493999719619751},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.5396000146865845},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.5339000225067139},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.49880000948905945},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4562000036239624},{"id":"https://openalex.org/C3019612716","wikidata":"https://www.wikidata.org/wiki/Q730920","display_name":"Problem solver","level":2,"score":0.4537999927997589},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.39629998803138733},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.37610000371932983},{"id":"https://openalex.org/C91306197","wikidata":"https://www.wikidata.org/wiki/Q45767","display_name":"Competition (biology)","level":2,"score":0.3646000027656555},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3352000117301941},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C86844869","wikidata":"https://www.wikidata.org/wiki/Q2798820","display_name":"Hacker","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26840001344680786}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1752","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1752","pdf_url":"https://aclanthology.org/2026.findings-acl.1752.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.11881","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.11881","pdf_url":"https://arxiv.org/pdf/2511.11881","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,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.11881","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.11881","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,"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:10.18653/v1/2026.findings-acl.1752","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1752","pdf_url":"https://aclanthology.org/2026.findings-acl.1752.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416528736.pdf","grobid_xml":"https://content.openalex.org/works/W4416528736.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"achieved":[5],"remarkable":[6],"progress":[7],"through":[8,27],"Reinforcement":[9],"Learning":[10],"with":[11,102,116],"Verifiable":[12],"Rewards":[13],"(RLVR),":[14],"yet":[15],"still":[16],"rely":[17],"heavily":[18],"on":[19,42],"external":[20,43],"supervision":[21],"(e.g.,":[22],"curated":[23],"labels).Adversarial":[24],"learning,":[25],"particularly":[26],"self-play,":[28],"offers":[29],"a":[30,81,96,106,119],"promising":[31],"alternative":[32],"that":[33,141,162],"enables":[34],"models":[35,54,89],"to":[36,52,72,110,122],"learn":[37],"from":[38,91,118],"themselves-thus":[39],"reducing":[40],"reliance":[41],"supervision.Dual-play":[44],"extends":[45],"adversarial":[46],"learning":[47],"by":[48],"assigning":[49],"specialized":[50],"roles":[51],"two":[53,88],"and":[55,64,105,127,155],"training":[56,71],"them":[57,153],"against":[58],"each":[59],"other,":[60],"fostering":[61],"sustained":[62],"competition":[63],"mutual":[65],"evolution.Despite":[66],"its":[67],"promise,":[68],"adapting":[69],"dual-play":[70,84],"LLMs":[73],"remains":[74],"limited.In":[75],"this":[76],"paper,":[77],"we":[78],"introduce":[79],"PasoDoble,":[80],"novel":[82],"LLM":[83],"framework.PasoDoble":[85],"adversarially":[86],"trains":[87],"initialized":[90],"the":[92,114,124,132,143,147,166],"same":[93],"base":[94],"model:":[95],"Proposer,":[97],"which":[98,108],"generates":[99],"challenging":[100],"questions":[101,140],"ground-truth":[103],"answers,":[104],"Solver,":[107],"attempts":[109],"solve":[111],"them.We":[112],"enrich":[113],"Proposer":[115,133],"knowledge":[117],"pre-training":[120],"dataset":[121],"ensure":[123],"questions'":[125],"quality":[126],"diversity.To":[128],"avoid":[129],"reward":[130],"hacking,":[131],"is":[134,149],"rewarded":[135,150],"for":[136,151],"producing":[137],"only":[138],"valid":[139],"push":[142],"Solver's":[144],"limit,":[145],"while":[146],"Solver":[148],"solving":[152],"correctly,":[154],"both":[156],"are":[157],"updated":[158],"jointly.Experimental":[159],"results":[160],"show":[161],"PasoDoble":[163],"can":[164],"improve":[165],"math":[167],"reasoning":[168],"performance":[169],"of":[170],"LLMs.":[171]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-11-19T00:00:00"}