{"id":"https://openalex.org/W4412945240","doi":"https://doi.org/10.18653/v1/2025.acl-long.747","title":"EPO: Explicit Policy Optimization for Strategic Reasoning in LLMs via Reinforcement Learning","display_name":"EPO: Explicit Policy Optimization for Strategic Reasoning in LLMs via Reinforcement Learning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945240","doi":"https://doi.org/10.18653/v1/2025.acl-long.747"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.747","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.747","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5103231035","display_name":"Xiaoqian Liu","orcid":"https://orcid.org/0000-0002-2814-3404"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoqian Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040414354","display_name":"Ke Wang","orcid":"https://orcid.org/0000-0002-8306-1663"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ke Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100644428","display_name":"Yongbin Li","orcid":"https://orcid.org/0009-0008-4504-2163"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongbin Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036775649","display_name":"Yuchuan Wu","orcid":"https://orcid.org/0000-0001-8487-7587"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuchuan Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038531069","display_name":"Wentao Ma","orcid":"https://orcid.org/0000-0002-7816-5150"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wentao Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115780953","display_name":"Aobo Kong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aobo Kong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075411298","display_name":"Fei Huang","orcid":"https://orcid.org/0000-0002-5290-2490"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fei Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110088325","display_name":"Jianbin Jiao","orcid":"https://orcid.org/0000-0003-0454-3929"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianbin Jiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5109012644","display_name":"Junge Zhang","orcid":"https://orcid.org/0000-0002-9970-394X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junge Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"15371","last_page":"15396"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.9664999842643738,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.9664999842643738,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7628132104873657},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5000886917114258},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4697953462600708},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3094519376754761},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.21601331233978271},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.16073697805404663}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7628132104873657},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5000886917114258},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4697953462600708},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3094519376754761},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.21601331233978271},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.16073697805404663}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.747","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.747","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}