{"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":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.69","doi":"https://doi.org/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":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.acl-long.69.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009277751","display_name":"Jiongxiao Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiongxiao Wang","raw_affiliation_strings":["University of Wisconsin-Madison ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison ;","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119858288","display_name":"Qiaojing Yan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiaojing Yan","raw_affiliation_strings":["AWS Agentic AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS Agentic AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139850229","display_name":"Yawei Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yawei Wang","raw_affiliation_strings":["AWS Agentic AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS Agentic AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139719280","display_name":"Yijun Tian","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yijun Tian","raw_affiliation_strings":["AWS Agentic AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS Agentic AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139806551","display_name":"Soumya Smruti Mishra","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Soumya Smruti Mishra","raw_affiliation_strings":["AWS Agentic AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS Agentic AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139799273","display_name":"Zhichao Xu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhichao Xu","raw_affiliation_strings":["AWS Agentic AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS Agentic AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121073643","display_name":"Megha Gandhi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Megha Gandhi","raw_affiliation_strings":["AWS Agentic AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS Agentic AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024059541","display_name":"Panpan Xu","orcid":"https://orcid.org/0000-0001-7966-2389","observed_orcids":["https://orcid.org/0000-0001-7966-2389","https://orcid.org/0000-0001-8180-7460"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Panpan Xu","raw_affiliation_strings":["AWS Agentic AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS Agentic AI","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049488691","display_name":"Lin Lee Cheong","orcid":"https://orcid.org/0009-0006-8935-6602","observed_orcids":["https://orcid.org/0009-0006-8935-6602"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin Lee Cheong","raw_affiliation_strings":["AWS Agentic AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS Agentic AI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.9348,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.97264089,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":96},"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":0.8842999935150146,"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":0.8842999935150146,"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":0.03849999979138374,"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"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.029100000858306885,"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":0.8690000176429749},{"id":"https://openalex.org/keywords/self-improving-agents","display_name":"self-improving agents","score":0.9190000295639038},{"id":"https://openalex.org/keywords/skill-library","display_name":"skill library","score":0.9179999828338623},{"id":"https://openalex.org/keywords/skill-acquisition","display_name":"skill acquisition","score":0.5109999775886536},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"natural language processing","score":0.35100001096725464}],"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","doi":"https://doi.org/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":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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","doi":"https://doi.org/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":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality education","score":0.8001416325569153}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":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":["https://openalex.org/W7154299763","https://openalex.org/W7160957554","https://openalex.org/W7160646979","https://openalex.org/W7163219078","https://openalex.org/W7202371197","https://openalex.org/W7128138590","https://openalex.org/W2963140198","https://openalex.org/W7166889546","https://openalex.org/W7135374254","https://openalex.org/W4402671772"],"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":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2026-07-02T00:00:00"}