{"id":"https://openalex.org/W7166899400","doi":"https://doi.org/10.18653/v1/2026.findings-acl.189","title":"Eval-RAR: Evaluation-Driven Retrieval-Augmented Reasoning via Reinforcement Learning","display_name":"Eval-RAR: Evaluation-Driven Retrieval-Augmented Reasoning via Reinforcement Learning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166899400","doi":"https://doi.org/10.18653/v1/2026.findings-acl.189"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.189","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.189","pdf_url":"https://aclanthology.org/2026.findings-acl.189.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.189.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139731159","display_name":"Heng Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Yu","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence , University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence , University of Science and Technology of China","institution_ids":["https://openalex.org/I4210097554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139770245","display_name":"Rui Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Li","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence , University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence , University of Science and Technology of China","institution_ids":["https://openalex.org/I4210097554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139778144","display_name":"Qi Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"id":"https://openalex.org/I4210137491","display_name":"National Science Centre","ror":"https://ror.org/03ha2q922","country_code":"PL","type":"government","lineage":["https://openalex.org/I4210137491"]}],"countries":["CN","PL"],"is_corresponding":false,"raw_author_name":"Qi Liu","raw_affiliation_strings":["Institute of Artificial Intelligence , Hefei Comprehensive National Science Center","State Key Laboratory of Cognitive Intelligence , University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence , Hefei Comprehensive National Science Center","institution_ids":["https://openalex.org/I4210137491"]},{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence , University of Science and Technology of China","institution_ids":["https://openalex.org/I4210097554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139850260","display_name":"Wenjun Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjun Feng","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence , University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence , University of Science and Technology of China","institution_ids":["https://openalex.org/I4210097554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104271404","display_name":"Junfeng Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junfeng Kang","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence , University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence , University of Science and Technology of China","institution_ids":["https://openalex.org/I4210097554"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139813017","display_name":"Yi Zhan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Zhan","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence , University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence , University of Science and Technology of China","institution_ids":["https://openalex.org/I4210097554"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":0.8637073,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3900","last_page":"3912"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6057999730110168,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6057999730110168,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.08250000327825546,"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":0.05689999833703041,"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":0.4025999903678894},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3093000054359436},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.29260000586509705},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.2842000126838684},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.2728999853134155}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5543000102043152},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5220000147819519},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4025999903678894},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.2498999983072281},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2451000064611435}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.189","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.189","pdf_url":"https://aclanthology.org/2026.findings-acl.189.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.189","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.189","pdf_url":"https://aclanthology.org/2026.findings-acl.189.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166899400.pdf","grobid_xml":"https://content.openalex.org/works/W7166899400.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Retrieval-augmented":[0],"generation":[1],"(RAG)":[2],"effectively":[3],"extends":[4],"the":[5,37,53,77,119],"knowledge":[6],"boundaries":[7],"of":[8,24],"large":[9],"language":[10],"models":[11,29],"(LLMs)":[12],"for":[13,21,52],"complex":[14],"tasks,":[15],"yet":[16],"current":[17],"paradigms":[18],"typically":[19],"optimize":[20,102],"an":[22,67],"interleaving":[23],"reasoning":[25,55],"and":[26,125,132],"retrieval,":[27],"where":[28,76],"fail":[30],"to":[31,48,58,89,98,121],"critically":[32],"evaluate":[33],"retrieved":[34],"information":[35,60,97],"against":[36],"target":[38],"question.Most":[39],"existing":[40,140],"methods":[41],"rely":[42],"on":[43,129],"sparse":[44],"outcomebased":[45],"rewards,":[46],"failing":[47],"provide":[49],"explicit":[50,80],"supervision":[51],"internal":[54],"process":[56],"or":[57,94],"diagnose":[59],"inadequacy.To":[61],"address":[62],"this,":[63],"we":[64,105],"propose":[65],"Eval-RAR,":[66],"Evaluationdriven":[68],"Retrieval-Augmented":[69],"Reasoning":[70],"framework.Eval-RAR":[71],"introduces":[72],"a":[73,87,110],"\"Search-then-Evaluate\"":[74],"paradigm":[75],"model":[78,120],"performs":[79],"self-evaluation":[81],"after":[82],"each":[83],"search":[84],"step,":[85],"generating":[86],"rationale":[88],"either":[90],"identify":[91],"sufficient":[92],"evidence":[93],"specify":[95],"missing":[96],"guide":[99],"subsequent":[100],"queries.To":[101],"this":[103],"process,":[104],"employ":[106],"reinforcement":[107],"learning":[108],"with":[109],"fine-grained":[111],"evaluation":[112],"reward,":[113],"providing":[114],"intermediate":[115],"feedback":[116],"that":[117,137],"encourages":[118],"track":[122],"core":[123],"entities":[124],"maintain":[126],"logical":[127],"consistency.Experiments":[128],"seven":[130],"single-hop":[131],"multi-hop":[133],"QA":[134],"benchmarks":[135],"demonstrate":[136],"Eval-RAR":[138],"outperforms":[139],"methods.":[141]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2026-07-02T00:00:00"}