{"id":"https://openalex.org/W7166822968","doi":"https://doi.org/10.18653/v1/2026.acl-long.1022","title":"Learning from Cognition: Enhancing RL Efficiency for LLM Reasoning via Hierarchical Metacognitive Decomposition and Refinement","display_name":"Learning from Cognition: Enhancing RL Efficiency for LLM Reasoning via Hierarchical Metacognitive Decomposition and Refinement","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166822968","doi":"https://doi.org/10.18653/v1/2026.acl-long.1022"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1022","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1022","pdf_url":"https://aclanthology.org/2026.acl-long.1022.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":"Proceedings of the 64th 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":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.1022.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139794759","display_name":"Zexu Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zexu Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035793423","display_name":"Yongcheng Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongcheng Zeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001749693","display_name":"Erxue Min","orcid":"https://orcid.org/0000-0002-1972-6608"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Erxue Min","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036086679","display_name":"Heyang Gao","orcid":"https://orcid.org/0009-0006-9743-2732"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heyang Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109640208","display_name":"Bokai Ji","orcid":"https://orcid.org/0009-0008-4676-1629"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bokai Ji","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139838777","display_name":"Dugang Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dugang Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139740036","display_name":"Xing Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xing Tang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083350101","display_name":"Xiuqiang He","orcid":"https://orcid.org/0000-0002-4115-8205"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiuqiang He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139736822","display_name":"Xu Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu Chen","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.81226726,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22331","last_page":"22348"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5350000262260437,"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":0.5350000262260437,"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":0.10170000046491623,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.03959999978542328,"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/decomposition","display_name":"Decomposition","score":0.5770999789237976},{"id":"https://openalex.org/keywords/automated-reasoning","display_name":"Automated reasoning","score":0.33379998803138733},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.3183000087738037},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.31220000982284546},{"id":"https://openalex.org/keywords/metacognition","display_name":"Metacognition","score":0.31209999322891235},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.30329999327659607}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6272000074386597},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.5770999789237976},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5763999819755554},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3553999960422516},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.33379998803138733},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C118147538","wikidata":"https://www.wikidata.org/wiki/Q1126970","display_name":"Metacognition","level":3,"score":0.31209999322891235},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28439998626708984},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2734000086784363}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1022","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1022","pdf_url":"https://aclanthology.org/2026.acl-long.1022.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1022","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1022","pdf_url":"https://aclanthology.org/2026.acl-long.1022.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7327746152877808,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322499","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166822968.pdf","grobid_xml":"https://content.openalex.org/works/W7166822968.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Zexu":[0],"Sun,":[1],"Yongcheng":[2],"Zeng,":[3],"Erxue":[4],"Min,":[5],"Heyang":[6],"Gao,":[7],"Bokai":[8],"Ji,":[9],"Dugang":[10],"Liu,":[11],"Xing":[12],"Tang,":[13],"Xiuqiang":[14],"He,":[15],"Xu":[16],"Chen.":[17],"Proceedings":[18],"of":[19,24],"the":[20,25],"64th":[21],"Annual":[22],"Meeting":[23],"Association":[26],"for":[27],"Computational":[28],"Linguistics":[29],"(Volume":[30],"1:":[31],"Long":[32],"Papers).":[33],"2026.":[34]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}
