{"id":"https://openalex.org/W7166851443","doi":"https://doi.org/10.18653/v1/2026.findings-acl.951","title":"Unlocking Exploration in RLVR: Uncertainty-aware Advantage Shaping for Deeper Reasoning","display_name":"Unlocking Exploration in RLVR: Uncertainty-aware Advantage Shaping for Deeper Reasoning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166851443","doi":"https://doi.org/10.18653/v1/2026.findings-acl.951"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.951","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.951","pdf_url":"https://aclanthology.org/2026.findings-acl.951.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":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.951.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123970131","display_name":"Can Xie","orcid":null},"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":[],"is_corresponding":false,"raw_author_name":"Can Xie","raw_affiliation_strings":["Kuaishou Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139744794","display_name":"Ruotong Pan","orcid":null},"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":[],"is_corresponding":false,"raw_author_name":"Ruotong Pan","raw_affiliation_strings":["Kuaishou Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139841955","display_name":"Xiangyu Wu","orcid":null},"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":[],"is_corresponding":false,"raw_author_name":"Xiangyu Wu","raw_affiliation_strings":["Kuaishou Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100613465","display_name":"Yunfei Zhang","orcid":"https://orcid.org/0000-0001-8160-7995"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang Yunfei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019537342","display_name":"Jiayi Fu","orcid":null},"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":[],"is_corresponding":false,"raw_author_name":"Jiayi Fu","raw_affiliation_strings":["Kuaishou Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139808349","display_name":"Tingting Gao","orcid":null},"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":[],"is_corresponding":false,"raw_author_name":"Tingting Gao","raw_affiliation_strings":["Kuaishou Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139796952","display_name":"Guorui Zhou","orcid":null},"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":[],"is_corresponding":false,"raw_author_name":"Guorui Zhou","raw_affiliation_strings":["Kuaishou Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology","institution_ids":["https://openalex.org/I4401726859"]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"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":0.85781796,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19057","last_page":"19076"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.2013999968767166,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.2013999968767166,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.1868000030517578,"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/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.09520000219345093,"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/perspective","display_name":"Perspective (graphical)","score":0.33000001311302185},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.31139999628067017},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.2728999853134155},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.265500009059906},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.2612000107765198}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5390999913215637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3709000051021576},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.33000001311302185},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2515000104904175},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.25110000371932983},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2484000027179718}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.951","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.951","pdf_url":"https://aclanthology.org/2026.findings-acl.951.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"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.951","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.951","pdf_url":"https://aclanthology.org/2026.findings-acl.951.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":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166851443.pdf","grobid_xml":"https://content.openalex.org/works/W7166851443.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"with":[2],"Verifiable":[3],"Rewards":[4],"(RLVR)":[5],"has":[6],"shown":[7],"significant":[8],"promise":[9],"for":[10],"enhancing":[11],"the":[12,38,52,75,87,126],"reasoning":[13,133,164],"capabilities":[14],"of":[15,41,55,111],"large":[16],"language":[17],"models":[18],"(LLMs).However,":[19],"prevailing":[20],"algorithms":[21],"like":[22],"GRPO":[23],"broadcast":[24],"a":[25,33,66,91],"uniform":[26],"advantage":[27,89],"signal":[28],"across":[29,143],"all":[30],"tokens":[31],"in":[32,81],"sequence.This":[34],"coarse-grained":[35],"approach":[36],"overlooks":[37],"pivotal":[39],"role":[40],"uncertain,":[42],"high-stakes":[43],"decisions":[44],"during":[45],"reasoning,":[46,123],"leading":[47],"to":[48],"inefficient":[49],"exploration":[50,110],"and":[51,95,149,166],"well-documented":[53],"problem":[54],"entropy":[56,169],"collapse.To":[57],"address":[58],"this,":[59],"we":[60],"introduce":[61],"UnCertainty-aware":[62],"Advantage":[63],"Shaping":[64],"(UCAS),":[65],"model-free":[67],"method":[68],"that":[69,114,136,153],"refines":[70],"credit":[71],"assignment":[72],"by":[73],"leveraging":[74],"model's":[76],"internal":[77],"uncertainty":[78],"signals.UCAS":[79],"operates":[80],"two":[82],"stages:":[83],"it":[84],"first":[85],"modulates":[86],"response-level":[88],"using":[90],"logit-space":[92],"self-confidence":[93],"proxy,":[94],"then":[96],"applies":[97],"an":[98],"asymmetric":[99],"token-level":[100],"penalty":[101],"based":[102],"on":[103,130],"raw":[104],"logit":[105],"certainty.This":[106],"dual":[107],"mechanism":[108],"encourages":[109],"high-uncertainty":[112],"paths":[113],"yield":[115],"correct":[116],"answers":[117],"while":[118],"penalizing":[119],"overconfident":[120],"yet":[121],"erroneous":[122],"effectively":[124],"balancing":[125],"exploration-exploitation":[127],"trade-off.Extensive":[128],"experiments":[129],"five":[131],"mathematical":[132],"benchmarks":[134],"show":[135],"UCAS":[137,154],"significantly":[138],"outperforms":[139],"strong":[140],"RLVR":[141],"baselines":[142],"multiple":[144],"model":[145],"scales,":[146],"including":[147],"1.5B":[148],"7B.Our":[150],"analysis":[151],"confirms":[152],"not":[155],"only":[156],"achieves":[157],"higher":[158],"rewards":[159],"but":[160],"also":[161],"promotes":[162],"greater":[163],"diversity":[165],"successfully":[167],"mitigates":[168],"collapse.":[170]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}