{"id":"https://openalex.org/W4416075279","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1896","title":"R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement Learning","display_name":"R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement Learning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4416075279","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1896"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1896","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1896","pdf_url":"https://aclanthology.org/2026.findings-acl.1896.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":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1896.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047419128","display_name":"Qi Zhao","orcid":"https://orcid.org/0000-0003-3054-8934"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingfei Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100778735","display_name":"Ruobing Wang","orcid":"https://orcid.org/0000-0002-2414-8777"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruobing Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055908165","display_name":"Dongsheng Xu","orcid":"https://orcid.org/0000-0002-8477-5377"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dingling Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051666209","display_name":"Daren Zha","orcid":"https://orcid.org/0009-0002-6042-3454"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daren Zha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ma Bowen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma Bowen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhichun Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhichun Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Shijie Jia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shijie Jia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079281573","display_name":"Limin Liu","orcid":"https://orcid.org/0000-0001-8577-1661"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Limin Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Xin Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Wang","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":0.01492273,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"38030","last_page":"38046"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.35749998688697815,"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":0.35749998688697815,"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":0.25,"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":0.06780000030994415,"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":0.6931999921798706},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6100999712944031},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.49230000376701355},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.47920000553131104},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.36820000410079956}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7301999926567078},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6931999921798706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6324999928474426},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6100999712944031},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.49230000376701355},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.47920000553131104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41190001368522644},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.36820000410079956},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.31529998779296875},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.28349998593330383}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1896","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1896","pdf_url":"https://aclanthology.org/2026.findings-acl.1896.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"},{"id":"pmh:oai:arXiv.org:2506.04185","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.04185","pdf_url":"https://arxiv.org/pdf/2506.04185","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.04185","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.04185","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1896","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1896","pdf_url":"https://aclanthology.org/2026.findings-acl.1896.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":[{"id":"https://openalex.org/G4233126585","display_name":null,"funder_award_id":"62272457","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"},{"id":"https://openalex.org/F4320335892","display_name":"Youth Innovation Promotion Association","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416075279.pdf","grobid_xml":"https://content.openalex.org/works/W4416075279.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2,27],"(LLMs)":[3],"have":[4],"notably":[5],"progressed":[6],"in":[7,37,75],"multi-step":[8],"and":[9,63,103,129],"long-chain":[10],"reasoning.However,":[11],"extending":[12],"their":[13],"reasoning":[14,58,102],"capabilities":[15],"to":[16,30,51,54,83,87,96,111],"encompass":[17],"deep":[18,60,98],"interactions":[19],"with":[20,59],"search":[21,61,88],"remains":[22],"a":[23,42],"non-trivial":[24],"challenge,":[25],"as":[26],"often":[28],"fail":[29],"identify":[31],"optimal":[32,65],"reasoningsearch":[33],"interaction":[34,67,100],"trajectories,":[35],"resulting":[36],"suboptimal":[38],"responses.We":[39],"propose":[40],"R-Search,":[41],"novel":[43],"reinforcement":[44],"learning":[45],"framework":[46],"for":[47],"Reasoning-Search":[48],"integration,":[49],"designed":[50],"enable":[52],"LLMs":[53],"autonomously":[55],"execute":[56],"multistep":[57],"interaction,":[62],"learn":[64],"reasoning-search":[66,115],"trajectories":[68],"via":[69],"multi-reward":[70],"signals,":[71],"improving":[72],"response":[73],"quality":[74],"complex":[76],"logic-and":[77],"knowledge-intensive":[78],"tasks.R-Search":[79],"guides":[80],"the":[81,114],"LLM":[82],"dynamically":[84],"decide":[85],"when":[86],"or":[89],"reason,":[90],"while":[91],"globally":[92],"integrating":[93],"key":[94],"evidence":[95],"enhance":[97],"knowledge":[99],"between":[101],"search.During":[104],"RL":[105],"training,":[106],"R-Search":[107,122],"provides":[108],"multi-type":[109],"rewards":[110],"jointly":[112],"optimize":[113],"trajectory.Experiments":[116],"on":[117],"seven":[118],"datasets":[119],"show":[120],"that":[121],"significantly":[123],"outperforms":[124],"mainstream":[125],"RAG":[126],"baselines.The":[127],"code":[128],"data":[130],"are":[131],"available":[132],"at":[133],"https://github.com/QingFei1/":[134],"R-Search.":[135]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}