{"id":"https://openalex.org/W7204098099","doi":"https://doi.org/10.18653/2026.emnlp-main.1054","title":"CAS: Conformalized Agentic Search via Adaptive Retrieval and Policy Weighting","display_name":"CAS: Conformalized Agentic Search via Adaptive Retrieval and Policy Weighting","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7204098099","doi":"https://doi.org/10.18653/2026.emnlp-main.1054"},"language":"en","primary_location":{"id":"doi:10.18653/2026.emnlp-main.1054","doi":"https://doi.org/10.18653/2026.emnlp-main.1054","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1054","pdf_url":"https://aclanthology.org/2026.emnlp-main.1054.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","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 2026 Conference on Empirical Methods in Natural Language Processing","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://aclanthology.org/2026.emnlp-main.1054.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5147910353","display_name":"Zixi Zhu","orcid":null,"observed_orcids":[]},"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":"Zixi Zhu","raw_affiliation_strings":["ZJU-UIUC Institute , Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ZJU-UIUC Institute , Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147917075","display_name":"Jiayuan Su","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayuan Su","raw_affiliation_strings":["Tencent Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Inc","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139227938","display_name":"Jian Zhang","orcid":null,"observed_orcids":[]},"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":"Jian Zhang","raw_affiliation_strings":["ZJU-UIUC Institute , Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ZJU-UIUC Institute , Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124932166","display_name":"Yu Lin","orcid":null,"observed_orcids":[]},"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":"Yu Lin","raw_affiliation_strings":["ZJU-UIUC Institute , Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ZJU-UIUC Institute , Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5147960140","display_name":"Hongwei Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongwei Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"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":0.66918906,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"24191","last_page":"24210"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.8446999788284302,"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":0.8446999788284302,"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":0.06109999865293503,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.012799999676644802,"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/conformal-prediction","display_name":"conformal prediction","score":0.9380000233650208},{"id":"https://openalex.org/keywords/adaptive-retrieval","display_name":"adaptive retrieval","score":0.5460000038146973},{"id":"https://openalex.org/keywords/group-relative-policy-optimization","display_name":"Group Relative Policy Optimization","score":0.7639999985694885},{"id":"https://openalex.org/keywords/answer-confidence","display_name":"answer confidence","score":0.47600001096725464},{"id":"https://openalex.org/keywords/hallucination-mitigation","display_name":"hallucination mitigation","score":0.5630000233650208},{"id":"https://openalex.org/keywords/top-k-retrieval","display_name":"top-k retrieval","score":0.47999998927116394},{"id":"https://openalex.org/keywords/multi-hop-question-answering","display_name":"multi-hop question answering","score":0.7409999966621399},{"id":"https://openalex.org/keywords/reinforcement-learning-fine-tuning","display_name":"reinforcement learning fine-tuning","score":0.7409999966621399}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7095000147819519},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5587000250816345},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5346999764442444},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5152999758720398},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5102999806404114},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4726000130176544},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47119998931884766},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.42820000648498535},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42160001397132874},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4009999930858612},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.36980000138282776},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.35249999165534973},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3382999897003174},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.26919999718666077},{"id":"https://openalex.org/C106195933","wikidata":"https://www.wikidata.org/wiki/Q7847935","display_name":"Truncation (statistics)","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25839999318122864}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.emnlp-main.1054","doi":"https://doi.org/10.18653/2026.emnlp-main.1054","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1054","pdf_url":"https://aclanthology.org/2026.emnlp-main.1054.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","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 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2608.20771","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.20771","pdf_url":"https://arxiv.org/pdf/2608.20771","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.2608.20771","doi":"https://doi.org/10.48550/arxiv.2608.20771","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.20771","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/2026.emnlp-main.1054","doi":"https://doi.org/10.18653/2026.emnlp-main.1054","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1054","pdf_url":"https://aclanthology.org/2026.emnlp-main.1054.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","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 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G584828216","display_name":null,"funder_award_id":"62276230","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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204098099.pdf","grobid_xml":"https://content.openalex.org/works/W7204098099.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415275447","https://openalex.org/W7124817799","https://openalex.org/W7204500131","https://openalex.org/W7128767543","https://openalex.org/W7168291226","https://openalex.org/W7127650377","https://openalex.org/W7168279185","https://openalex.org/W4416036494","https://openalex.org/W4417440823","https://openalex.org/W4414808182"],"abstract_inverted_index":{"Search":[0,48],"Agents":[1],"face":[2],"a":[3,70,98,158],"severe":[4],"reliability":[5,52],"crisis":[6],"during":[7],"reinforcement":[8],"learning":[9],"(RL)":[10],"fine-tuning.Heuristic":[11],"Top-K":[12],"retrieval":[13,57,63],"often":[14],"causes":[15],"critical":[16],"evidence":[17],"loss":[18],"or":[19],"noise":[20],"inclusion,":[21],"while":[22,151],"overconfidence":[23],"induced":[24],"by":[25],"progressive":[26],"RL":[27],"leads":[28],"to":[29,81,109,117],"hallucinated":[30],"answers":[31],"and":[32,44,58,139,161],"redundant":[33,154],"searches.To":[34],"build":[35],"highly":[36,159],"reliable":[37,135,160],"agents,":[38],"we":[39],"introduce":[40],"Conformal":[41,95],"Prediction":[42,67],"(CP)":[43],"propose":[45],"Conformalized":[46],"Agentic":[47],"(CAS).This":[49],"framework":[50,146],"establishes":[51],"guarantees":[53],"on":[54,61,90],"both":[55],"the":[56,62,91,122,130],"training":[59,92],"sides:":[60],"side,":[64,93],"an":[65],"Adaptive":[66,94],"Set":[68],"(APS),":[69],"specific":[71],"CP":[72,100],"realization,":[73],"translates":[74],"statistical":[75],"coverage":[76,108],"into":[77],"dynamic":[78,99],"document":[79],"truncation":[80],"construct":[82],"prediction":[83,104],"sets":[84,105],"that":[85,144],"are":[86],"adaptive":[87],"in":[88],"size;":[89],"Inference":[96],"(ACI),":[97],"algorithm,":[101],"dynamically":[102],"constructs":[103],"with":[106],"controllable":[107],"quantify":[110],"answer":[111],"confidence,":[112],"which":[113],"is":[114,166],"then":[115],"used":[116],"penalize":[118],"low-confidence":[119],"trajectories":[120],"within":[121],"Group":[123],"Relative":[124],"Policy":[125],"Optimization":[126],"(GRPO)":[127],"objective,":[128],"ensuring":[129],"model":[131],"learns":[132],"only":[133],"from":[134],"ones.Experiments":[136],"across":[137],"single-hop":[138],"multi-hop":[140],"QA":[141],"datasets":[142],"demonstrate":[143],"our":[145],"significantly":[147],"improves":[148],"reasoning":[149],"accuracy":[150],"drastically":[152],"reducing":[153],"tool":[155],"invocations,":[156],"establishing":[157],"efficient":[162],"agent":[163],"paradigm.Our":[164],"code":[165],"available":[167],"at":[168],"https:":[169],"//github.com":[170]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2026-08-25T00:00:00"}