{"id":"https://openalex.org/W4416034879","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.554","title":"R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning","display_name":"R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034879","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.554"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.554","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.554","pdf_url":"https://aclanthology.org/2025.findings-emnlp.554.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: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.554.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116493713","display_name":"Li Yuan","orcid":"https://orcid.org/0000-0002-2120-5588"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101831407","display_name":"Qi Luo","orcid":"https://orcid.org/0000-0002-4103-7112"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi Luo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065623474","display_name":"Xiaonan Li","orcid":"https://orcid.org/0000-0002-3033-3119"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaonan Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051894630","display_name":"Bufan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bufan Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004651932","display_name":"Qinyuan Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qinyuan Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115695357","display_name":"Bo Wang","orcid":"https://orcid.org/0000-0002-8908-8891"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037160254","display_name":"Yining Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yining Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100427490","display_name":"Yuxin Wang","orcid":"https://orcid.org/0009-0004-4110-3513"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxin Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083955516","display_name":"Zhangyue Yin","orcid":"https://orcid.org/0009-0008-0620-8271"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhangyue Yin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5044665993","display_name":"Xipeng Qiu","orcid":"https://orcid.org/0000-0001-7163-5247"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xipeng Qiu","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":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10491","last_page":"10507"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.42669999599456787,"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":0.42669999599456787,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.1362999975681305,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.062199998646974564,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.4641000032424927},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.36079999804496765},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.35199999809265137},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.26600000262260437},{"id":"https://openalex.org/keywords/hybrid-learning","display_name":"Hybrid learning","score":0.2619999945163727}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4641000032424927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42410001158714294},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.41339999437332153},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3849000036716461},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.36079999804496765},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3531000018119812},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.35199999809265137},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C3018790387","wikidata":"https://www.wikidata.org/wiki/Q869010","display_name":"Hybrid learning","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.25619998574256897},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.25519999861717224},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.554","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.554","pdf_url":"https://aclanthology.org/2025.findings-emnlp.554.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: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.554","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.554","pdf_url":"https://aclanthology.org/2025.findings-emnlp.554.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: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034879.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}
