{"id":"https://openalex.org/W4417132896","doi":"https://doi.org/10.18653/v1/2026.acl-long.1994","title":"RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization","display_name":"RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4417132896","doi":"https://doi.org/10.18653/v1/2026.acl-long.1994"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1994","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1994","pdf_url":"https://aclanthology.org/2026.acl-long.1994.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":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.1994.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077542599","display_name":"Yihong Dong","orcid":"https://orcid.org/0000-0002-6048-2377"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yihong Dong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087748031","display_name":"Xue Jiang","orcid":"https://orcid.org/0000-0001-7441-0828"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xue Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yongding Tao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongding Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011863353","display_name":"Huanyu Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huanyu Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069561378","display_name":"Kechi Zhang","orcid":"https://orcid.org/0000-0002-3290-0244"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kechi Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120725318","display_name":"Lili Mou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lili Mou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028500121","display_name":"Rongyu Cao","orcid":"https://orcid.org/0000-0002-3779-5885"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rongyu Cao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112915936","display_name":"Yingwei Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingwei MA","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100686861","display_name":"Jue Chen","orcid":"https://orcid.org/0000-0001-7508-2635"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jue Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053947739","display_name":"Binhua Li","orcid":"https://orcid.org/0009-0004-2963-4290"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Binhua Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049100391","display_name":"Zhi Jin","orcid":"https://orcid.org/0000-0003-1087-226X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhi Jin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024071911","display_name":"Fei Huang","orcid":"https://orcid.org/0000-0002-4001-7806"},"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/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":"last","author":{"id":"https://openalex.org/A5100447679","display_name":"Ge Li","orcid":"https://orcid.org/0000-0002-2078-8937"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ge Li","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":0.03393546,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"43029","last_page":"43053"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.21369999647140503,"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":0.21369999647140503,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.1704999953508377,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.09470000118017197,"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/boundary","display_name":"Boundary (topology)","score":0.6904000043869019},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6888999938964844},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.6809999942779541},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.49630001187324524},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.45350000262260437},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.4406000077724457},{"id":"https://openalex.org/keywords/base","display_name":"Base (topology)","score":0.4171000123023987},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.41620001196861267}],"concepts":[{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.6904000043869019},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6888999938964844},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.6809999942779541},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5676000118255615},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.49630001187324524},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.45350000262260437},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.4406000077724457},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4323999881744385},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.4171000123023987},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.41620001196861267},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.41260001063346863},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.3896999955177307},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.352400004863739},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.34310001134872437},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.33000001311302185},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3158999979496002},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C42023084","wikidata":"https://www.wikidata.org/wiki/Q5249231","display_name":"Decision boundary","level":3,"score":0.26930001378059387},{"id":"https://openalex.org/C182310444","wikidata":"https://www.wikidata.org/wiki/Q1332643","display_name":"Boundary value problem","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C55660270","wikidata":"https://www.wikidata.org/wiki/Q5164377","display_name":"Constrained optimization","level":2,"score":0.25999999046325684}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1994","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1994","pdf_url":"https://aclanthology.org/2026.acl-long.1994.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"},{"id":"pmh:oai:arXiv.org:2508.00222","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2508.00222","pdf_url":"https://arxiv.org/pdf/2508.00222","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.2508.00222","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.00222","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.acl-long.1994","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1994","pdf_url":"https://aclanthology.org/2026.acl-long.1994.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":[],"awards":[{"id":"https://openalex.org/G3446613798","display_name":null,"funder_award_id":"62192730","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5482656022","display_name":null,"funder_award_id":"62192731","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8449925957","display_name":null,"funder_award_id":"62192733","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417132896.pdf","grobid_xml":"https://content.openalex.org/works/W4417132896.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Yihong":[0],"Dong,":[1],"Xue":[2],"Jiang,":[3],"Yongding":[4],"Tao,":[5],"Huanyu":[6],"Liu,":[7],"Kechi":[8],"Zhang,":[9],"Lili":[10],"Mou,":[11],"Rongyu":[12],"Cao,":[13],"Yingwei":[14],"MA,":[15],"Jue":[16],"Chen,":[17],"Binhua":[18],"Li,":[19,25],"Zhi":[20],"Jin,":[21],"Fei":[22],"Huang,":[23],"Yongbin":[24],"Ge":[26],"Li.":[27],"Proceedings":[28],"of":[29,34],"the":[30,35],"64th":[31],"Annual":[32],"Meeting":[33],"Association":[36],"for":[37],"Computational":[38],"Linguistics":[39],"(Volume":[40],"1:":[41],"Long":[42],"Papers).":[43],"2026.":[44]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}