{"id":"https://openalex.org/W7225193643","doi":"https://doi.org/10.48550/arxiv.2611.03625","title":"FADE: Factored Ability--Difficulty Filtering for Online RLVR Scheduling","display_name":"FADE: Factored Ability--Difficulty Filtering for Online RLVR Scheduling","publication_year":2026,"publication_date":"2026-11-02","ids":{"openalex":"https://openalex.org/W7225193643","doi":"https://doi.org/10.48550/arxiv.2611.03625"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2611.03625","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.03625","pdf_url":"https://arxiv.org/pdf/2611.03625","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/2611.03625","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5159135489","display_name":"Tomas Duncun","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duncun, Tomas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159099582","display_name":"Jonah Ellison","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ellison, Jonah","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138023125","display_name":"Mateo Ruiz","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruiz, Mateo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143790145","display_name":"Hanae Fujita","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fujita, Hanae","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5044902733","display_name":"Ingrid Solberg","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Solberg, Ingrid","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":0.4494999945163727,"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":0.4494999945163727,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.10270000249147415,"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/T10028","display_name":"Topic Modeling","score":0.07029999792575836,"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/reinforcement-learning-with-verifiable-rewards","display_name":"reinforcement learning with verifiable rewards","score":0.8050000071525574},{"id":"https://openalex.org/keywords/reasoning-benchmarks","display_name":"reasoning benchmarks","score":0.460999995470047}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6262000203132629},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.582099974155426},{"id":"https://openalex.org/C100521375","wikidata":"https://www.wikidata.org/wiki/Q2015382","display_name":"Competence (human resources)","level":2,"score":0.5410000085830688},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.4871000051498413},{"id":"https://openalex.org/C140331021","wikidata":"https://www.wikidata.org/wiki/Q1868104","display_name":"Logit","level":2,"score":0.46239998936653137},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.4228000044822693},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.37310001254081726},{"id":"https://openalex.org/C205203396","wikidata":"https://www.wikidata.org/wiki/Q612143","display_name":"Bilinear interpolation","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C169087156","wikidata":"https://www.wikidata.org/wiki/Q2131593","display_name":"Framing (construction)","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C73602740","wikidata":"https://www.wikidata.org/wiki/Q7795822","display_name":"Thompson sampling","level":3,"score":0.3156999945640564},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.28619998693466187},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.28060001134872437},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.2777000069618225},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.2587999999523163},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2611.03625","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.03625","pdf_url":"https://arxiv.org/pdf/2611.03625","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.2611.03625","doi":"https://doi.org/10.48550/arxiv.2611.03625","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.03625","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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2611.03625","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.03625","pdf_url":"https://arxiv.org/pdf/2611.03625","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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7204216741","https://openalex.org/W7171778161","https://openalex.org/W7124157306","https://openalex.org/W7128371695","https://openalex.org/W7160833816","https://openalex.org/W7128518505","https://openalex.org/W7223835989","https://openalex.org/W7212012286","https://openalex.org/W7161724498","https://openalex.org/W7222340647"],"abstract_inverted_index":{"Group-based":[0],"reinforcement":[1],"learning":[2],"with":[3,125],"verifiable":[4],"rewards":[5],"(RLVR)":[6],"learns":[7],"only":[8],"from":[9],"prompts":[10,86,166],"whose":[11],"sampled":[12],"completions":[13],"disagree:":[14],"all-pass":[15],"and":[16,23,62,181,204,218],"all-fail":[17],"groups":[18],"produce":[19],"zero":[20],"relative":[21,83],"advantage":[22],"burn":[24],"generation":[25],"budget":[26],"without":[27],"moving":[28],"the":[29,82,106,116,147,177,189],"policy.":[30],"Adaptive":[31],"schedulers":[32],"try":[33],"to":[34,163],"steer":[35],"rollouts":[36],"toward":[37],"informative":[38],"prompts,":[39],"yet":[40],"they":[41],"rely":[42],"on":[43],"per-prompt":[44],"pass-rate":[45],"trackers":[46],"that":[47,104,167],"entangle":[48],"two":[49,107,201],"quantities":[50],"evolving":[51],"at":[52,77],"very":[53],"different":[54],"speeds---the":[55],"policy's":[56],"shifting":[57],"competence":[58,161],"across":[59],"reasoning":[60,199],"skills":[61,170],"each":[63,111,140],"prompt's":[64,112],"intrinsic":[65],"difficulty.":[66],"When":[67],"a":[68,100,120,126,132,155,185,193,209],"single":[69],"exponential":[70],"average":[71],"or":[72],"Beta":[73],"counter":[74],"tracks":[75],"both":[76],"once,":[78],"short":[79],"memory":[80,89],"scrambles":[81],"ordering":[84],"of":[85,119,142,191],"whereas":[87],"long":[88],"reports":[90],"stale":[91],"pass":[92],"rates.":[93],"We":[94],"introduce":[95],"FADE":[96,109,213],"(Factored":[97],"Ability--Difficulty":[98],"Estimation),":[99],"bilinear":[101],"state-space":[102],"filter":[103],"separates":[105],"timescales.":[108],"represents":[110],"success":[113],"logit":[114],"as":[115],"inner":[117],"product":[118],"whitened":[121],"$K$-dimensional":[122,148],"skill":[123],"loading":[124],"fast-drifting":[127],"policy":[128],"ability":[129,149],"vector,":[130],"minus":[131],"slow-shrinking":[133],"scalar":[134],"item":[135,173],"intercept.":[136],"Using":[137],"P\u00f3lya--Gamma":[138],"augmentation,":[139],"minibatch":[141],"binary":[143],"rollout":[144,195,211],"outcomes":[145],"updates":[146],"posterior":[150,179],"in":[151],"closed":[152],"form":[153],"via":[154],"rank-$K$":[156],"Woodbury":[157],"step,":[158],"instantly":[159],"transferring":[160],"shifts":[162],"all":[164],"unobserved":[165],"share":[168],"those":[169],"while":[171,220],"leaving":[172],"intercepts":[174],"stable.":[175],"From":[176],"resulting":[178],"mean":[180],"variance":[182],"we":[183],"derive":[184],"closed-form":[186],"utility":[187],"for":[188],"probability":[190],"drawing":[192],"non-degenerate":[194],"group.":[196],"Across":[197],"five":[198],"benchmarks,":[200],"base":[202],"models,":[203],"four":[205],"scheduling":[206],"paradigms":[207],"under":[208],"matched":[210],"budget,":[212],"consistently":[214],"improves":[215],"downstream":[216],"accuracy":[217],"calibration":[219],"adding":[221],"less":[222],"than":[223],"$0.6$\\,ms":[224],"per":[225],"step.":[226]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-11-04T00:00:00"}