{"id":"https://openalex.org/W6891997121","doi":"https://doi.org/10.48550/arxiv.2506.21638","title":"R1-Ranker: Teaching LLM Rankers to Reason","display_name":"R1-Ranker: Teaching LLM Rankers to Reason","publication_year":2025,"publication_date":"2025-06-25","ids":{"openalex":"https://openalex.org/W6891997121","doi":"https://doi.org/10.48550/arxiv.2506.21638"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2506.21638","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.21638","pdf_url":"https://arxiv.org/pdf/2506.21638","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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.21638","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Feng, Tao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Hua, Zhigang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hua, Zhigang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134799033","display_name":"Zijie Lei","orcid":"https://orcid.org/0009-0009-0309-0674","observed_orcids":["https://orcid.org/0009-0009-0309-0674"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei, Zijie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Xie, Yan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075728990","display_name":"Shuang Yang","orcid":"https://orcid.org/0000-0002-1607-7446","observed_orcids":["https://orcid.org/0000-0002-1607-7446"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Shuang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Long, Bo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Long, Bo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5003491365","display_name":"Jiaxuan You","orcid":"https://orcid.org/0000-0003-1812-7598","observed_orcids":["https://orcid.org/0000-0003-1812-7598"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"You, Jiaxuan","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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.8339999914169312,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.8339999914169312,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.11320000141859055,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.03959999978542328,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/large-language-models","display_name":"large language models","score":0.7099999785423279},{"id":"https://openalex.org/keywords/ranking-tasks","display_name":"ranking tasks","score":0.609000027179718},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.6949999928474426},{"id":"https://openalex.org/keywords/recommender-systems","display_name":"recommender systems","score":0.7919999957084656},{"id":"https://openalex.org/keywords/llm-routing","display_name":"LLM routing","score":0.949999988079071},{"id":"https://openalex.org/keywords/passage-ranking","display_name":"passage ranking","score":0.9229999780654907},{"id":"https://openalex.org/keywords/retrieval-ranking","display_name":"retrieval ranking","score":0.6420000195503235},{"id":"https://openalex.org/keywords/zero-shot-generalization","display_name":"zero-shot generalization","score":0.7739999890327454},{"id":"https://openalex.org/keywords/reasoning-traces","display_name":"reasoning traces","score":0.44999998807907104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6640999913215637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6283000111579895},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6222000122070312},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6003999710083008},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.5806999802589417},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5616999864578247},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5526999831199646},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5310999751091003},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4887999892234802},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4828999936580658},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42559999227523804},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.382099986076355},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.3407999873161316},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.3314000070095062},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.305400013923645},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28630000352859497},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C117619785","wikidata":"https://www.wikidata.org/wiki/Q6094414","display_name":"Iterative learning control","level":3,"score":0.25380000472068787}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2506.21638","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.21638","pdf_url":"https://arxiv.org/pdf/2506.21638","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.2506.21638","doi":"https://doi.org/10.48550/arxiv.2506.21638","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.21638","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":"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":"pmh:oai:arXiv.org:2506.21638","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.21638","pdf_url":"https://arxiv.org/pdf/2506.21638","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"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.7610242962837219,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2,133],"(LLMs)":[3],"have":[4],"recently":[5],"shown":[6],"strong":[7],"reasoning":[8,39,65,171,202],"abilities":[9],"in":[10,90,203],"domains":[11],"like":[12],"mathematics,":[13],"coding,":[14],"and":[15,31,54,93,120,137,145,156,170,197],"scientific":[16],"problem-solving,":[17],"yet":[18],"their":[19,59],"potential":[20],"for":[21,199],"ranking":[22,97,186,204],"tasks,":[23,136],"where":[24],"prime":[25],"examples":[26],"include":[27],"retrieval,":[28],"recommender":[29],"systems,":[30],"LLM":[32,201],"routing,":[33,119],"remains":[34],"underexplored.":[35],"Ranking":[36],"requires":[37],"complex":[38],"across":[40],"heterogeneous":[41],"candidates,":[42],"but":[43],"existing":[44],"LLM-based":[45],"rankers":[46],"are":[47],"often":[48],"domain-specific,":[49],"tied":[50],"to":[51,61,106,178],"fixed":[52],"backbones,":[53],"lack":[55],"iterative":[56,100,157],"refinement,":[57],"limiting":[58],"ability":[60],"fully":[62],"exploit":[63],"LLMs'":[64],"potential.":[66],"To":[67],"address":[68],"these":[69],"challenges,":[70],"we":[71],"propose":[72],"R1-Ranker,":[73],"a":[74,139,189],"reasoning-incentive":[75],"framework":[76],"built":[77],"on":[78,114,134,167],"reinforcement":[79,154],"learning,":[80],"with":[81,103,159,188],"two":[82],"complementary":[83],"designs:":[84],"DRanker,":[85],"which":[86,95],"generates":[87],"full":[88],"rankings":[89],"one":[91],"shot,":[92],"IRanker,":[94],"decomposes":[96],"into":[98],"an":[99],"elimination":[101],"process":[102],"step-wise":[104],"rewards":[105],"encourage":[107],"deeper":[108],"reasoning.":[109],"We":[110],"evaluate":[111],"unified":[112],"R1-Rankers":[113],"nine":[115],"datasets":[116],"spanning":[117],"recommendation,":[118],"passage":[121],"ranking,":[122],"showing":[123],"that":[124,183],"IRanker-3B":[125,160],"consistently":[126],"achieves":[127],"state-of-the-art":[128],"performance,":[129],"surpasses":[130],"larger":[131],"7B":[132],"some":[135],"yields":[138],"15.7%":[140],"average":[141],"relative":[142],"improvement.":[143],"Ablation":[144],"generalization":[146],"experiments":[147],"further":[148],"confirm":[149],"the":[150],"critical":[151],"role":[152],"of":[153],"learning":[155],"reasoning,":[158],"improving":[161],"zero-shot":[162],"performance":[163],"by":[164,176],"over":[165],"9%":[166],"out-of-domain":[168],"tasks":[169,187],"traces":[172],"boosting":[173],"other":[174],"LLMs":[175],"up":[177],"22.87%.":[179],"These":[180],"results":[181],"demonstrate":[182],"unifying":[184],"diverse":[185],"single":[190],"reasoning-driven":[191],"foundation":[192],"model":[193],"is":[194],"both":[195],"effective":[196],"essential":[198],"advancing":[200],"scenarios.":[205]},"counts_by_year":[],"updated_date":"2026-10-17T09:40:24.721904","created_date":"2025-10-10T00:00:00"}