{"id":"https://openalex.org/W7163567245","doi":"https://doi.org/10.48550/arxiv.2606.04503","title":"Smart Picks in the Dark: Towards Efficient RLVR for Reasoning via Tracing Metacognitive Pivots","display_name":"Smart Picks in the Dark: Towards Efficient RLVR for Reasoning via Tracing Metacognitive Pivots","publication_year":2026,"publication_date":"2026-06-03","ids":{"openalex":"https://openalex.org/W7163567245","doi":"https://doi.org/10.48550/arxiv.2606.04503"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.04503","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.04503","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.04503","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000700814","display_name":"G. Zhu","orcid":"https://orcid.org/0000-0003-4364-866X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Guangcheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137841083","display_name":"Shenzhi Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Shenzhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137837910","display_name":"Haobo Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Haobo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114804130","display_name":"Xing Zheng","orcid":"https://orcid.org/0000-0003-3171-6506"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Xing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137815515","display_name":"Yingfan MA","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"MA, Yingfan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022434855","display_name":"Xuening Feng","orcid":"https://orcid.org/0009-0004-4070-1941"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Xuening","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102157705","display_name":"Zhongqi Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Zhongqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137868716","display_name":"Bowen Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Bowen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137870161","display_name":"Weiqiang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Weiqiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137912376","display_name":"Gang Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Gang","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":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5170000195503235,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5170000195503235,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.2134000062942505,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.03889999911189079,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.5052000284194946},{"id":"https://openalex.org/keywords/tracing","display_name":"Tracing","score":0.504800021648407},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.45730000734329224},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.43320000171661377},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.4291999936103821},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.42910000681877136},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4133000075817108},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.40139999985694885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7785999774932861},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5856999754905701},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5562999844551086},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5052000284194946},{"id":"https://openalex.org/C138673069","wikidata":"https://www.wikidata.org/wiki/Q322229","display_name":"Tracing","level":2,"score":0.504800021648407},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.45730000734329224},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.43320000171661377},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4291999936103821},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.42910000681877136},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4133000075817108},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.40139999985694885},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3873000144958496},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.3779999911785126},{"id":"https://openalex.org/C125209513","wikidata":"https://www.wikidata.org/wiki/Q4037520","display_name":"Doors","level":2,"score":0.36899998784065247},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.3402000069618225},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.33809998631477356},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.31790000200271606},{"id":"https://openalex.org/C118147538","wikidata":"https://www.wikidata.org/wiki/Q1126970","display_name":"Metacognition","level":3,"score":0.31220000982284546},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29170000553131104},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27559998631477356},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.04503","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.04503","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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:10.48550/arxiv.2606.04503","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.04503","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"with":[2,186],"verifiable":[3],"rewards":[4],"(RLVR)":[5],"has":[6],"greatly":[7],"advanced":[8],"large":[9],"reasoning":[10],"models":[11],"(LRMs),":[12],"but":[13,51],"it":[14],"requires":[15],"timely":[16],"training":[17,108,135,177],"on":[18,54,74,122,138],"a":[19,41,55,123,144],"huge":[20],"fully-annotated":[21],"dataset.":[22],"To":[23],"this":[24,139],"end,":[25],"data-efficient":[26],"RLVR":[27,63],"methods":[28,39,64],"have":[29],"been":[30],"widely":[31],"studied":[32],"from":[33],"two":[34],"perspectives:":[35],"(i)":[36],"data":[37,132,146,169],"selection":[38],"identify":[40],"small":[42],"subset":[43],"of":[44,58,111,131],"\"golden\"":[45],"samples":[46,102,190],"that":[47,103,118,149],"yield":[48],"near-full-data":[49],"performance,":[50],"they":[52,79],"rely":[53],"pre-existing":[56],"pool":[57],"labeled":[59],"data.":[60],"(ii)":[61],"unsupervised":[62],"train":[65],"the":[66,86,89,182],"model":[67],"using":[68],"its":[69],"own":[70],"internal":[71],"supervision":[72],"signals":[73],"large-scale":[75],"unlabeled":[76,101],"data,":[77],"yet":[78],"exhibit":[80],"suboptimal":[81],"performance.":[82],"Accordingly,":[83],"we":[84,116,141],"investigate":[85],"\"pick":[87],"in":[88],"dark\"":[90],"setup":[91],"for":[92,107,133],"RLVR,":[93],"which":[94],"aims":[95],"to":[96,127,153,171],"select,":[97],"without":[98],"prior":[99],"supervision,":[100],"are":[104],"most":[105],"beneficial":[106],"and":[109,176,191],"worthy":[110],"annotation.":[112],"Through":[113],"systematic":[114],"analysis,":[115],"demonstrate":[117],"smart":[119],"picks":[120],"hinge":[121],"well-calibrated":[124],"uncertainty":[125,162],"estimator":[126],"enable":[128],"strategic":[129],"partitioning":[130],"adaptive":[134],"regimes.":[136],"Building":[137],"insight,":[140],"propose":[142],"PivotTrace,":[143],"three-way":[145],"triage":[147],"framework":[148],"leverages":[150],"attention":[151],"dynamics":[152],"trace":[154],"metacognitive":[155],"pivots":[156],"during":[157],"reasoning.":[158],"By":[159],"precisely":[160],"quantifying":[161],"through":[163],"pivot":[164],"density,":[165],"PivotTrace":[166,180],"achieves":[167],"automated":[168],"routing":[170],"synergistically":[172],"maximize":[173],"both":[174],"annotation":[175],"efficiency.":[178],"Empirically,":[179],"surpasses":[181],"fully":[183],"supervised":[184],"LRM":[185],"only":[187],"29.3%":[188],"annotated":[189],"2.75":[192],"faster":[193],"convergence.":[194]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-05T00:00:00"}