{"id":"https://openalex.org/W7138195392","doi":"https://doi.org/10.1609/aaai.v40i39.40603","title":"RAG-R1:Incentivizing the Search and Reasoning Capabilities of LLMs Through Multi-Query Parallelism","display_name":"RAG-R1:Incentivizing the Search and Reasoning Capabilities of LLMs Through Multi-Query Parallelism","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138195392","doi":"https://doi.org/10.1609/aaai.v40i39.40603"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i39.40603","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i39.40603","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40603/44564","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40603/44564","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129651881","display_name":"Zhiwen Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiwen Tan","raw_affiliation_strings":["Ant Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129652849","display_name":"Jiaming Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaming Huang","raw_affiliation_strings":["Zhejiang University\nAnt Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University\nAnt Group","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010366027","display_name":"Qintong Wu","orcid":"https://orcid.org/0000-0002-5885-3984"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qintong Wu","raw_affiliation_strings":["Ant Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129681272","display_name":"Hongxuan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210135679","display_name":"Antea Group (France)","ror":"https://ror.org/03kfw6k71","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210101086","https://openalex.org/I4210135679"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Hongxuan Zhang","raw_affiliation_strings":["Nanjing university\nAnt Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing university\nAnt Group","institution_ids":["https://openalex.org/I4210135679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129647192","display_name":"Chenyi Zhuang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenyi Zhuang","raw_affiliation_strings":["Ant Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129668284","display_name":"Jinjie Gu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinjie Gu","raw_affiliation_strings":["Ant Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"39","first_page":"33187","last_page":"33195"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7728000283241272,"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":0.7728000283241272,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.13910000026226044,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.01549999974668026,"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/inference","display_name":"Inference","score":0.7293999791145325},{"id":"https://openalex.org/keywords/hallucinating","display_name":"Hallucinating","score":0.6491000056266785},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6480000019073486},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5013999938964844},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.3815000057220459},{"id":"https://openalex.org/keywords/opportunistic-reasoning","display_name":"Opportunistic reasoning","score":0.357699990272522},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.35429999232292175},{"id":"https://openalex.org/keywords/debiasing","display_name":"Debiasing","score":0.35100001096725464}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7293999791145325},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7222999930381775},{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.6491000056266785},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6480000019073486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5206000208854675},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5013999938964844},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45840001106262207},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.3815000057220459},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.357699990272522},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.35429999232292175},{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.35100001096725464},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3375000059604645},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.33070001006126404},{"id":"https://openalex.org/C166088908","wikidata":"https://www.wikidata.org/wiki/Q308495","display_name":"Abductive reasoning","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.27810001373291016},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i39.40603","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i39.40603","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40603/44564","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/40603","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/40603","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i39.40603","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i39.40603","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40603/44564","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6038297414779663,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138195392.pdf","grobid_xml":"https://content.openalex.org/works/W7138195392.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs),":[3],"despite":[4],"their":[5,18],"remarkable":[6],"capabilities,":[7],"are":[8,36],"prone":[9],"to":[10,17,44,70,87,120],"generating":[11],"hallucinated":[12],"or":[13],"outdated":[14],"content":[15],"due":[16],"static":[19],"internal":[20,73],"knowledge.":[21],"While":[22],"Retrieval-Augmented":[23],"Generation":[24],"(RAG)":[25],"integrated":[26],"with":[27],"Reinforcement":[28],"Learning":[29],"(RL)":[30],"offers":[31],"a":[32,40,57],"solution,":[33],"these":[34,52],"methods":[35],"fundamentally":[37],"constrained":[38],"by":[39,118,126],"single-query":[41,85],"mode,":[42],"leading":[43],"prohibitive":[45],"latency":[46],"and":[47,74,122],"inherent":[48],"brittleness.":[49],"To":[50],"overcome":[51],"limitations,":[53],"we":[54],"introduce":[55],"RAG-R1,":[56],"novel":[58],"two-stage":[59],"training":[60],"framework":[61,67],"centered":[62],"around":[63],"multi-query":[64,88],"parallelism.":[65,89],"Our":[66],"enables":[68],"LLMs":[69],"adaptively":[71],"leverage":[72],"external":[75],"knowledge":[76],"during":[77],"the":[78,84,108,115],"reasoning":[79,94],"process":[80],"while":[81,96],"transitioning":[82],"from":[83],"mode":[86],"This":[90],"architectural":[91],"shift":[92],"bolsters":[93],"robustness":[95],"significantly":[97],"reducing":[98],"inference":[99,124],"latency.":[100],"Extensive":[101],"experiments":[102],"on":[103],"seven":[104],"question-answering":[105],"benchmarks":[106],"confirm":[107],"superiority":[109],"of":[110],"our":[111],"method,":[112],"which":[113],"outperforms":[114],"strongest":[116],"baseline":[117],"up":[119],"13.7%":[121],"decreases":[123],"time":[125],"11.1%.":[127]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}