{"id":"https://openalex.org/W4416434652","doi":"https://doi.org/10.18653/v1/2026.findings-acl.799","title":"Prompt-R1: Collaborative Automatic Prompting Framework via End-to-end Reinforcement Learning","display_name":"Prompt-R1: Collaborative Automatic Prompting Framework via End-to-end Reinforcement Learning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4416434652","doi":"https://doi.org/10.18653/v1/2026.findings-acl.799"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.799","doi":"https://doi.org/10.18653/v1/2026.findings-acl.799","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.799","pdf_url":"https://aclanthology.org/2026.findings-acl.799.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.findings-acl.799.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101461651","display_name":"Wenjin Liu","orcid":"https://orcid.org/0000-0003-2855-0277","observed_orcids":["https://orcid.org/0000-0003-2855-0277"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenjin Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101634508","display_name":"Haoran Luo","orcid":"https://orcid.org/0000-0003-2727-0361","observed_orcids":["https://orcid.org/0000-0003-2727-0361"]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haoran Luo","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xueyuan Lin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xueyuan Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Haoming Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoming Liu","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010025622","display_name":"Tiesunlong Shen","orcid":"https://orcid.org/0000-0002-7666-0406","observed_orcids":["https://orcid.org/0000-0002-7666-0406"]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tiesunlong Shen","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiapu Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiapu Wang","raw_affiliation_strings":["Nanjing University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rui Mao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Rui Mao","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100752356","display_name":"Erik Cambria","orcid":"https://orcid.org/0000-0002-3030-1280","observed_orcids":["https://orcid.org/0000-0002-3030-1280","https://orcid.org/0009-0009-3320-2526"]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Erik Cambria","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.6196,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.93107449,"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":"16260","last_page":"16280"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8554999828338623,"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":0.8554999828338623,"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":0.09160000085830688,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.01140000019222498,"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/automatic-prompt-generation","display_name":"automatic prompt generation","score":0.7440000176429749},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6809999942779541},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.5669999718666077},{"id":"https://openalex.org/keywords/multi-turn-interaction","display_name":"multi-turn interaction","score":0.6660000085830688},{"id":"https://openalex.org/keywords/prompt-engineering","display_name":"prompt engineering","score":0.41499999165534973},{"id":"https://openalex.org/keywords/complex-reasoning","display_name":"complex reasoning","score":0.578000009059906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.774399995803833},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7443000078201294},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5842000246047974},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5503000020980835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5160999894142151},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5105999708175659},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4546999931335449},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.43880000710487366},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.438400000333786},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.30399999022483826},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2565000057220459}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.799","doi":"https://doi.org/10.18653/v1/2026.findings-acl.799","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.799","pdf_url":"https://aclanthology.org/2026.findings-acl.799.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.01016","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2511.01016","pdf_url":"https://arxiv.org/pdf/2511.01016","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.2511.01016","doi":"https://doi.org/10.48550/arxiv.2511.01016","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.01016","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/v1/2026.findings-acl.799","doi":"https://doi.org/10.18653/v1/2026.findings-acl.799","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.799","pdf_url":"https://aclanthology.org/2026.findings-acl.799.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3523415498","display_name":null,"funder_award_id":"2023YFF0905404","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416434652.pdf","grobid_xml":"https://content.openalex.org/works/W4416434652.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4399794854","https://openalex.org/W4413432108","https://openalex.org/W7222310595","https://openalex.org/W4416290380","https://openalex.org/W4388032133","https://openalex.org/W4402669970","https://openalex.org/W4396570218","https://openalex.org/W7084386390","https://openalex.org/W4417298827","https://openalex.org/W4366565380"],"abstract_inverted_index":{"Recently,":[0],"various":[1,118,133],"excellent":[2],"and":[3,33,86,89,103,115],"powerful":[4],"large":[5],"language":[6],"models":[7],"(LLMs)":[8],"have":[9],"been":[10],"utilized":[11],"to":[12,30,36,62,71,100],"solve":[13],"a":[14,57,78,108],"wide":[15],"range":[16],"of":[17,105],"human":[18],"problems.However,":[19],"when":[20],"faced":[21],"with":[22,38,64,117],"complex":[23,94],"problems,":[24],"most":[25],"users":[26,70],"are":[27],"often":[28],"unable":[29],"provide":[31],"accurate":[32],"effective":[34],"prompts":[35],"interact":[37,72],"LLMs,":[39],"thus":[40],"limiting":[41],"their":[42],"performance.To":[43],"address":[44],"this":[45],"challenge,":[46],"we":[47],"propose":[48],"Prompt-R1,":[49],"an":[50],"endto-end":[51],"reinforcement":[52],"learning":[53],"framework":[54,110],"that":[55,111,126],"utilizes":[56],"small-scale":[58,83],"LLM":[59,84,92],"(as":[60,67],"agent)":[61],"collaborate":[63],"large-scale":[65,91,119],"LLMs":[66,131],"environment),":[68],"replacing":[69],"better.This":[73],"collaboration":[74],"is":[75,98,136],"presented":[76],"as":[77],"multi-turn":[79],"interaction,":[80],"where":[81],"the":[82,90],"thinks":[85],"generates":[87],"prompts,":[88],"performs":[93],"reasoning.A":[95],"doubleconstrained":[96],"reward":[97],"designed":[99],"optimize":[101],"correctness":[102],"quality":[104],"generation.Prompt-R1":[106],"provides":[107],"plug-and-play":[109],"supports":[112],"both":[113],"inference":[114],"training":[116],"LLMs.Experimental":[120],"results":[121],"on":[122],"twelve":[123],"datasets":[124],"show":[125],"Prompt-R1":[127],"significantly":[128],"outperforms":[129],"baseline":[130],"across":[132],"tasks.Our":[134],"code":[135],"available":[137],"at":[138],"https:":[139],"//github.com/QwenQKing/Prompt-R1.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2025-11-06T00:00:00"}