{"id":"https://openalex.org/W7166807240","doi":"https://doi.org/10.18653/v1/2026.acl-long.69","title":"Reinforcement Learning for Self-Improving Agent with Skill Library","display_name":"Reinforcement Learning for Self-Improving Agent with Skill Library","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166807240","doi":"https://doi.org/10.18653/v1/2026.acl-long.69"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.69","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.69","pdf_url":"https://aclanthology.org/2026.acl-long.69.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.69.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009277751","display_name":"Jiongxiao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiongxiao Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119858288","display_name":"Qiaojing Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiaojing Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139850229","display_name":"Yawei Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yawei Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139719280","display_name":"Yijun Tian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yijun Tian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139806551","display_name":"Soumya Smruti Mishra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Soumya Smruti Mishra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139799273","display_name":"Zhichao Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhichao Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121073643","display_name":"Megha Gandhi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Megha Gandhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139763089","display_name":"Panpan Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Panpan Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139751189","display_name":"Lin Lee Cheong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin Lee Cheong","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":0.79705288,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1529","last_page":"1550"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.16249999403953552,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.16249999403953552,"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/T10320","display_name":"Neural Networks and Applications","score":0.042500000447034836,"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/T10028","display_name":"Topic Modeling","score":0.03849999979138374,"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":0.49459999799728394},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.38519999384880066},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.3163999915122986},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.2906999886035919},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.2732999920845032}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.49459999799728394},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4629000127315521},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43369999527931213},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.38519999384880066},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.36809998750686646},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2793000042438507},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2621999979019165},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.25029999017715454},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.69","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.69","pdf_url":"https://aclanthology.org/2026.acl-long.69.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.69","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.69","pdf_url":"https://aclanthology.org/2026.acl-long.69.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":0.8001416325569153,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166807240.pdf","grobid_xml":"https://content.openalex.org/works/W7166807240.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Jiongxiao":[0],"Wang,":[1,5],"Qiaojing":[2],"Yan,":[3],"Yawei":[4],"Yijun":[6],"Tian,":[7],"Soumya":[8],"Smruti":[9],"Mishra,":[10],"Zhichao":[11],"Xu,":[12,16],"Megha":[13],"Gandhi,":[14],"Panpan":[15],"Lin":[17],"Lee":[18],"Cheong.":[19],"Proceedings":[20],"of":[21,26],"the":[22,27],"64th":[23],"Annual":[24],"Meeting":[25],"Association":[28],"for":[29],"Computational":[30],"Linguistics":[31],"(Volume":[32],"1:":[33],"Long":[34],"Papers).":[35],"2026.":[36]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}
