{"id":"https://openalex.org/W7224933001","doi":"https://doi.org/10.48550/arxiv.2610.39295","title":"There Is No Free Lunch in RLVR: Every pass@1 Gain Has a pass@k Price","display_name":"There Is No Free Lunch in RLVR: Every pass@1 Gain Has a pass@k Price","publication_year":2026,"publication_date":"2026-10-29","ids":{"openalex":"https://openalex.org/W7224933001","doi":"https://doi.org/10.48550/arxiv.2610.39295"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.39295","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39295","pdf_url":"https://arxiv.org/pdf/2610.39295","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/2610.39295","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160236193","display_name":"Yinuo Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Liu, Yinuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5160236193"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.7738999724388123,"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":0.7738999724388123,"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":0.05169999971985817,"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":0.04610000178217888,"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":0.9800000190734863},{"id":"https://openalex.org/keywords/entropy-collapse","display_name":"entropy collapse","score":0.43299999833106995},{"id":"https://openalex.org/keywords/language-model-reasoning","display_name":"language model reasoning","score":0.6010000109672546},{"id":"https://openalex.org/keywords/sampling-budget","display_name":"sampling budget","score":0.4050000011920929},{"id":"https://openalex.org/keywords/sign-variation","display_name":"sign variation","score":0.3919999897480011}],"concepts":[{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.545199990272522},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5421000123023987},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.5238999724388123},{"id":"https://openalex.org/C122507166","wikidata":"https://www.wikidata.org/wiki/Q628906","display_name":"Crossover","level":2,"score":0.4799000024795532},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4562999904155731},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.43059998750686646},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42410001158714294},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.3797000050544739},{"id":"https://openalex.org/C139676723","wikidata":"https://www.wikidata.org/wiki/Q1193832","display_name":"Sign (mathematics)","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.3375999927520752},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.3352999985218048},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33500000834465027},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.31929999589920044},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.28949999809265137},{"id":"https://openalex.org/C197115733","wikidata":"https://www.wikidata.org/wiki/Q1003136","display_name":"Forcing (mathematics)","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C2779432360","wikidata":"https://www.wikidata.org/wiki/Q16963779","display_name":"Instant","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.39295","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39295","pdf_url":"https://arxiv.org/pdf/2610.39295","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.2610.39295","doi":"https://doi.org/10.48550/arxiv.2610.39295","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.39295","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:2610.39295","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39295","pdf_url":"https://arxiv.org/pdf/2610.39295","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224933001.pdf","grobid_xml":"https://content.openalex.org/works/W7224933001.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7214054207","https://openalex.org/W7170567086","https://openalex.org/W4414927448","https://openalex.org/W7164911192","https://openalex.org/W6948538263","https://openalex.org/W7204059813","https://openalex.org/W7206199124","https://openalex.org/W4417531499","https://openalex.org/W7140162979","https://openalex.org/W7083683602"],"abstract_inverted_index":{"Reinforcement":[0,225],"learning":[1],"with":[2,57,215],"verifiable":[3],"rewards":[4],"(RLVR)":[5],"makes":[6],"a":[7,39,47,58,63,78,104,123,138,158,180,184,238,244,266],"language":[8],"model":[9,29],"solve":[10],"more":[11,50],"problems":[12],"on":[13,108,122],"the":[14,27,55,99,113,119,130,133,142,149,153,168,188,196,200,212,228,248,250,254],"first":[15],"try":[16],"and":[17,65,116,141,165,194,211,253],"fewer":[18],"when":[19],"given":[20],"many":[21],"tries:":[22],"it":[23,31,136,231],"raises":[24,95],"pass@1":[25,96,190,202],"while":[26],"base":[28,79],"overtakes":[30],"at":[32,147,237],"large":[33],"sampling":[34],"budget":[35],"k.":[36],"Is":[37],"this":[38],"failure":[40],"of":[41,77,101,144,152],"RL":[42],"to":[43,182],"add":[44],"reasoning,":[45],"or":[46],"transient":[48],"that":[49,88,94,162,166,246],"training":[51],"removes?":[52],"We":[53],"settle":[54],"question":[56],"theorem.":[59],"The":[60,176,204],"reversal":[61],"is":[62,112,125,146,163,178,261],"price,":[64],"we":[66,86,240],"compute":[67],"its":[68,173],"exact":[69,114,189],"rate.":[70],"Modeling":[71],"RLVR":[72],"as":[73,172],"an":[74,216],"exponential":[75],"tilt":[76,206],"policy":[80],"over":[81],"strategies":[82],"shared":[83],"across":[84],"prompts,":[85,135],"prove":[87],"under":[89,222],"exclusive":[90],"specialization":[91],"every":[92],"update":[93,186],"strictly":[97,105],"lowers":[98],"success":[100],"some":[102],"prompt;":[103],"positive":[106,160],"price":[107,239,255],"prompts":[109],"(Stiemke":[110],"duality)":[111],"condition,":[115],"being":[117],"merely":[118],"best":[120],"strategy":[121],"prompt":[124],"provably":[126],"not":[127,179],"enough.":[128],"When":[129],"loss":[131],"reaches":[132],"hardest":[134],"forces":[137],"pass@k":[139,192],"crossover,":[140],"number":[143],"crossings":[145],"most":[148],"sign":[150],"variation":[151],"shift":[154],"in":[155],"per-prompt":[156],"success,":[157],"totally":[159],"bound":[161],"tight":[164],"recovers":[167],"known":[169],"single-crossover":[170],"result":[171],"order-preserving":[174,251],"case.":[175],"crossover":[177,197],"bug":[181],"patch:":[183],"constrained":[185],"traces":[187],"versus":[191],"frontier,":[193],"removing":[195],"entirely":[198],"costs":[199],"entire":[201],"gain.":[203],"same":[205],"identity":[207],"yields":[208],"entropy":[209],"collapse":[210],"entropy-performance":[213],"law":[214],"identifiable":[217],"exponent,":[218],"unifying":[219],"two":[220],"literatures":[221],"one":[223],"mechanism.":[224],"cannot":[226],"widen":[227],"reasoning":[229],"frontier;":[230],"can":[232],"only":[233,265],"move":[234],"along":[235],"it,":[236],"make":[241],"measurable":[242],"by":[243],"diagnostic":[245],"reads":[247],"bound,":[249],"test,":[252],"from":[256],"any":[257],"evaluation":[258],"log.":[259],"There":[260],"no":[262],"free":[263],"lunch,":[264],"price.":[267]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-10-31T00:00:00"}