{"id":"https://openalex.org/W7204237163","doi":"https://doi.org/10.18653/2026.findings-emnlp.499","title":"SkillForge: Evolving Verifiable Skills for Reinforcement Learning Agents","display_name":"SkillForge: Evolving Verifiable Skills for Reinforcement Learning Agents","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7204237163","doi":"https://doi.org/10.18653/2026.findings-emnlp.499"},"language":"en","primary_location":{"id":"doi:10.18653/2026.findings-emnlp.499","doi":"https://doi.org/10.18653/2026.findings-emnlp.499","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.499","pdf_url":"https://aclanthology.org/2026.findings-emnlp.499.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.findings-emnlp.499.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121250414","display_name":"Shidong Yang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shidong Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122840592","display_name":"Ziyu Ma","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziyu Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148234410","display_name":"Tongwen Huang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tongwen Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138340464","display_name":"Xucong Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xucong Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129661930","display_name":"Renda Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Renda Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122825848","display_name":"Yiming Hu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yiming Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144355735","display_name":"Yong Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yong Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101512474","display_name":"Xiangxiang Chu","orcid":"https://orcid.org/0000-0003-2548-0605","observed_orcids":["https://orcid.org/0000-0003-2548-0605"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangxiang Chu","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":0.68022374,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10448","last_page":"10469"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9932000041007996,"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":0.9932000041007996,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.00279999990016222,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.0005000000237487257,"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/skill-evolution","display_name":"skill evolution","score":0.6340000033378601},{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.753000020980835},{"id":"https://openalex.org/keywords/alfworld","display_name":"ALFWorld","score":0.6779999732971191},{"id":"https://openalex.org/keywords/webshop","display_name":"WebShop","score":0.8679999709129333}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.744700014591217},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.714900016784668},{"id":"https://openalex.org/C2776527387","wikidata":"https://www.wikidata.org/wiki/Q1671839","display_name":"Invocation","level":2,"score":0.5552999973297119},{"id":"https://openalex.org/C132758656","wikidata":"https://www.wikidata.org/wiki/Q5307365","display_name":"Dreyfus model of skill acquisition","level":2,"score":0.5127000212669373},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4194999933242798},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.39730000495910645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38440001010894775},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3837999999523163},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.32820001244544983},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.27230000495910645},{"id":"https://openalex.org/C2986563244","wikidata":"https://www.wikidata.org/wiki/Q6822310","display_name":"Learning to learn","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.findings-emnlp.499","doi":"https://doi.org/10.18653/2026.findings-emnlp.499","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.499","pdf_url":"https://aclanthology.org/2026.findings-emnlp.499.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2608.24747","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24747","pdf_url":"https://arxiv.org/pdf/2608.24747","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,"listed_in":[],"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.2608.24747","doi":"https://doi.org/10.48550/arxiv.2608.24747","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.24747","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/2026.findings-emnlp.499","doi":"https://doi.org/10.18653/2026.findings-emnlp.499","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.499","pdf_url":"https://aclanthology.org/2026.findings-emnlp.499.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204237163.pdf","grobid_xml":"https://content.openalex.org/works/W7204237163.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7220978366","https://openalex.org/W7160957554","https://openalex.org/W7128545450","https://openalex.org/W7116881161","https://openalex.org/W7203696443","https://openalex.org/W7160902796","https://openalex.org/W7214972836","https://openalex.org/W7163174640","https://openalex.org/W7163194927","https://openalex.org/W7171874410"],"abstract_inverted_index":{"Large":[0],"language":[1],"model":[2],"(LLM)":[3],"agents":[4,17],"are":[5],"trained":[6],"with":[7],"reinforcement":[8],"learning":[9],"(RL)":[10],"for":[11,66],"complex":[12],"decision-making":[13],"tasks.However,":[14],"most":[15],"RL-trained":[16],"remain":[18,57],"episodic":[19],"and":[20,76,95,104,123],"cannot":[21],"accumulate":[22],"reusable":[23],"knowledge":[24],"across":[25],"episodes.Recent":[26],"skill-based":[27],"approaches,":[28],"such":[29],"as":[30,48],"SKILLRL,":[31,130],"attempt":[32],"to":[33,73,112],"address":[34],"this":[35,59],"issue":[36],"by":[37],"extracting":[38],"skills":[39,56,72,137],"from":[40],"raw":[41],"trajectories,":[42],"but":[43],"treat":[44],"the":[45,109,132],"skill":[46,68,82,96,102,106,110],"bank":[47,111],"an":[49],"append-only":[50],"repository":[51],"without":[52],"verifying":[53],"whether":[54],"stored":[55],"effective.In":[58],"paper,":[60],"we":[61],"propose":[62],"SKILL-FORGE,":[63],"a":[64],"framework":[65],"continuous":[67],"evolution":[69],"that":[70,126],"enables":[71],"be":[74],"verified":[75,136],"refined":[77],"through":[78],"environment":[79,93],"interaction.By":[80],"making":[81],"usage":[83],"explicit":[84],"during":[85],"agent":[86],"interaction,":[87],"RL":[88],"can":[89],"directly":[90],"optimize":[91],"both":[92],"actions":[94],"invocation":[97],"decisions.SKILL-FORGE":[98],"further":[99],"introduces":[100],"evidence-based":[101],"verification":[103],"multi-pathway":[105],"induction,":[107],"allowing":[108],"continuously":[113,135],"grow":[114],"while":[115],"maintaining":[116],"its":[117],"quality.Extensive":[118],"experiments":[119],"on":[120],"ALFWorld,":[121],"WebShop,":[122],"Ap-pWorld":[124],"show":[125],"SKILLFORGE":[127],"consistently":[128],"outperforms":[129],"demonstrating":[131],"effectiveness":[133],"of":[134],"in":[138],"training":[139],"stronger":[140],"LLM":[141],"agents.":[142]},"counts_by_year":[],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2026-08-27T00:00:00"}