{"id":"https://openalex.org/W4412377895","doi":"https://doi.org/10.1145/3726302.3730102","title":"ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewarding","display_name":"ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewarding","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412377895","doi":"https://doi.org/10.1145/3726302.3730102"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3730102","doi":"https://doi.org/10.1145/3726302.3730102","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730102","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730102","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730102","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012452889","display_name":"Zhongxiang Sun","orcid":"https://orcid.org/0000-0002-6109-4704","observed_orcids":["https://orcid.org/0000-0002-6109-4704"]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongxiang Sun","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin Unversity of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6109-4704","affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin Unversity of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qipeng Wang","orcid":"https://orcid.org/0009-0003-0061-5769","observed_orcids":["https://orcid.org/0009-0003-0061-5769"]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qipeng Wang","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-0061-5769","affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016774863","display_name":"Weijie Yu","orcid":"https://orcid.org/0000-0002-5676-4339","observed_orcids":["https://orcid.org/0000-0002-5676-4339"]},"institutions":[{"id":"https://openalex.org/I146563203","display_name":"University of International Business and Economics","ror":"https://ror.org/05khqpb71","country_code":"CN","type":"education","lineage":["https://openalex.org/I146563203"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weijie Yu","raw_affiliation_strings":["School of Information Technology and Management, University of International Business and Economics, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5676-4339","affiliations":[{"raw_affiliation_string":"School of Information Technology and Management, University of International Business and Economics, Beijing, China","institution_ids":["https://openalex.org/I146563203"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049537668","display_name":"Xiaoxue Zang","orcid":"https://orcid.org/0000-0002-5923-3429","observed_orcids":["https://orcid.org/0000-0002-5923-3429"]},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xiaoxue Zang","raw_affiliation_strings":["Kuaishou Technology Co., Ltd., Beijing, Japan"],"raw_orcid":"https://orcid.org/0000-0002-5923-3429","affiliations":[{"raw_affiliation_string":"Kuaishou Technology Co., Ltd., Beijing, Japan","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032234550","display_name":"Kai Zheng","orcid":"https://orcid.org/0009-0006-3822-2815","observed_orcids":["https://orcid.org/0009-0006-3822-2815"]},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Zheng","raw_affiliation_strings":["Kuaishou Technology Co., Ltd., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-3822-2815","affiliations":[{"raw_affiliation_string":"Kuaishou Technology Co., Ltd., Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020766468","display_name":"Jun Xu","orcid":"https://orcid.org/0000-0001-7170-111X","observed_orcids":["https://orcid.org/0000-0001-7170-111X","https://orcid.org/0009-0003-3277-561X"]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Xu","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin Unversity of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7170-111X","affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin Unversity of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100320847","display_name":"Xiao Zhang","orcid":"https://orcid.org/0000-0001-7397-5632","observed_orcids":["https://orcid.org/0000-0001-7397-5632"]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Zhang","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7397-5632","affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083873109","display_name":"Yang Song","orcid":"https://orcid.org/0000-0002-1714-5527","observed_orcids":["https://orcid.org/0000-0002-1714-5527"]},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Song","raw_affiliation_strings":["Kuaishou Technology Co., Ltd., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1714-5527","affiliations":[{"raw_affiliation_string":"Kuaishou Technology Co., Ltd., Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020615530","display_name":"Han Li","orcid":"https://orcid.org/0009-0000-9801-9292","observed_orcids":["https://orcid.org/0009-0000-9801-9292"]},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Li","raw_affiliation_strings":["Kuaishou Technology Co., Ltd., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-9801-9292","affiliations":[{"raw_affiliation_string":"Kuaishou Technology Co., Ltd., Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.0428,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.95775685,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1251","last_page":"1261"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8384000062942505,"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":0.8384000062942505,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.055799998342990875,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.03460000082850456,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.9539999961853027},{"id":"https://openalex.org/keywords/process-reward-models","display_name":"process reward models","score":0.7039999961853027},{"id":"https://openalex.org/keywords/multi-step-reasoning","display_name":"multi-step reasoning","score":0.8370000123977661},{"id":"https://openalex.org/keywords/chain-of-thought-reasoning","display_name":"chain-of-thought reasoning","score":0.7950000166893005},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.7929999828338623},{"id":"https://openalex.org/keywords/training-data-bias","display_name":"training data bias","score":0.6320000290870667},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.699999988079071},{"id":"https://openalex.org/keywords/explanation-generation","display_name":"explanation generation","score":0.42500001192092896}],"concepts":[{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.8238651752471924},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.77851402759552},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6523329019546509},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42420676350593567},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3837520480155945},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17220690846443176},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.1166037917137146}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3726302.3730102","doi":"https://doi.org/10.1145/3726302.3730102","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730102","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730102","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2501.07861","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.07861","pdf_url":"https://arxiv.org/pdf/2501.07861","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2501.07861","doi":"https://doi.org/10.48550/arxiv.2501.07861","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2501.07861","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":"doi:10.1145/3726302.3730102","doi":"https://doi.org/10.1145/3726302.3730102","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730102","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730102","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1840373507","display_name":null,"funder_award_id":"62376275","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5278239020","display_name":null,"funder_award_id":"62472426, 62376275","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322499","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412377895.pdf","grobid_xml":"https://content.openalex.org/works/W4412377895.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W2126316555","https://openalex.org/W2131600418","https://openalex.org/W2889787757","https://openalex.org/W2990138404","https://openalex.org/W3115947671","https://openalex.org/W3159959439","https://openalex.org/W3190126809","https://openalex.org/W4214717370","https://openalex.org/W4385571271","https://openalex.org/W4389520103","https://openalex.org/W4389523718","https://openalex.org/W4401042753","https://openalex.org/W4401857375","https://openalex.org/W4402671620","https://openalex.org/W4402671689","https://openalex.org/W4410088787","https://openalex.org/W6600195515","https://openalex.org/W6600291067"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2076536433","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W90316445","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Retrieval-Augmented":[0,81],"Generation":[1],"(RAG)":[2],"systems":[3],"for":[4,20,115,125,195],"Large":[5],"Language":[6],"Models":[7],"(LLMs)":[8],"have":[9,29],"shown":[10],"promise":[11],"in":[12,56,62,181,202],"knowledge-intensive":[13],"tasks,":[14],"yet":[15],"their":[16],"reasoning":[17,35,73,94,215,222,230],"capabilities,":[18],"particularly":[19],"complex":[21],"multi-step":[22,214],"reasoning,":[23],"remain":[24],"limited.":[25],"Although":[26],"recent":[27],"approaches":[28],"explored":[30],"integrating":[31],"RAG":[32,92,233],"with":[33,40],"chain-of-thought":[34],"or":[36],"incorporating":[37,192],"test-time":[38,100],"search":[39,209],"process":[41],"reward":[42],"model":[43,158],"(PRM),":[44],"these":[45,77],"methods":[46],"face":[47],"several":[48],"untrustworthy":[49],"challenges,":[50],"including":[51],"lack":[52],"of":[53,232],"explanations,":[54,129],"bias":[55,61,180,201],"PRM":[57,63,171,182],"training":[58,183],"data,":[59,151,184],"early-step":[60,200],"scores,":[64],"and":[65,99,119,172,191,198],"ignoring":[66],"post-training":[67,98],"that":[68,90,218],"fails":[69],"to":[70,146,155,227],"fully":[71],"optimize":[72,156],"potential.":[74],"To":[75],"address":[76],"issues,":[78],"we":[79,135],"propose":[80],"Reasoning":[82],"through":[83,96,159,175],"Trustworthy":[84,107,143],"Process":[85,108,112,121,144],"Rewarding":[86,109,145],"(ReARTeR),":[87],"a":[88,111,120,187,206],"framework":[89],"enhances":[91],"systems'":[93],"capabilities":[95],"both":[97],"scaling.":[101],"At":[102],"test":[103],"time,":[104],"ReARTeR":[105,163,219],"introduces":[106],"via":[110,205],"Reward":[113],"Model":[114,123],"accurate":[116],"scalar":[117],"scoring":[118],"Explanation":[122],"(PEM)":[124],"generating":[126],"natural":[127],"language":[128],"enabling":[130],"step":[131],"refinement.":[132],"During":[133],"post-training,":[134],"leverage":[136],"Monte":[137],"Carlo":[138],"Tree":[139],"Search":[140],"guided":[141],"by":[142,186],"collect":[147],"high-quality":[148],"step-level":[149],"preference":[150,177],"which":[152],"is":[153],"used":[154],"the":[157,229],"Iterative":[160],"Preference":[161],"Optimization.":[162],"tackles":[164],"three":[165],"key":[166],"challenges:":[167],"(1)":[168],"misalignment":[169],"between":[170],"PEM,":[173],"addressed":[174],"off-policy":[176],"learning;":[178],"(2)":[179],"mitigated":[185],"balanced":[188],"annotation":[189],"method":[190],"stronger":[193],"annotations":[194],"difficult":[196],"examples;":[197],"(3)":[199],"PRM,":[203],"resolved":[204],"temporal-difference-based":[207],"look-ahead":[208],"strategy.":[210],"Experimental":[211],"results":[212],"on":[213],"benchmarks":[216],"demonstrate":[217],"significantly":[220],"improves":[221],"performance,":[223],"highlighting":[224],"its":[225],"potential":[226],"advance":[228],"capability":[231],"systems.":[234]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2025-10-10T00:00:00"}