{"id":"https://openalex.org/W7141406657","doi":"https://doi.org/10.48550/arxiv.2603.25184","title":"Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model","display_name":"Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model","publication_year":2026,"publication_date":"2026-03-26","ids":{"openalex":"https://openalex.org/W7141406657","doi":"https://doi.org/10.48550/arxiv.2603.25184"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.25184","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.25184","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.25184","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130803605","display_name":"Jiahao Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wu, Jiahao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130728224","display_name":"Ning Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Ning","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069592134","display_name":"S. Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Shengcai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130807302","display_name":"Kun Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Kun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130800335","display_name":"Yanting Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yanting","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130778680","display_name":"Li Qing","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qing, Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130784303","display_name":"Ke Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Ke","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5130803605"],"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.21780000627040863,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.21780000627040863,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.20170000195503235,"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":0.12110000103712082,"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/selection","display_name":"Selection (genetic algorithm)","score":0.6065999865531921},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5501000285148621},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5231999754905701},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5182999968528748},{"id":"https://openalex.org/keywords/proxy","display_name":"Proxy (statistics)","score":0.49549999833106995},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4316999912261963},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.41909998655319214},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.41839998960494995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7814000248908997},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6065999865531921},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5605000257492065},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5501000285148621},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.550000011920929},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5231999754905701},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5182999968528748},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.49549999833106995},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4316999912261963},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.41909998655319214},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.41839998960494995},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.33410000801086426},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2791000008583069},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.25679999589920044},{"id":"https://openalex.org/C3017489831","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Running time","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.25184","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.25184","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.25184","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.25184","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,85],"(RL)":[2],"has":[3],"become":[4],"essential":[5],"for":[6,119,127],"post-training":[7],"large":[8,44],"language":[9],"models":[10],"(LLMs)":[11],"in":[12],"reasoning":[13,150],"tasks.":[14],"While":[15],"scaling":[16],"rollouts":[17,36],"can":[18],"stabilize":[19],"training":[20,103],"and":[21,51,81,97,112,130,152],"enhance":[22],"performance,":[23],"the":[24,69,83,89,92],"computational":[25],"overhead":[26],"is":[27,79],"a":[28,43,116,135],"critical":[29],"issue.":[30],"In":[31],"algorithms":[32],"like":[33],"GRPO,":[34],"multiple":[35,148],"per":[37],"prompt":[38,114,132],"incur":[39],"prohibitive":[40],"costs,":[41],"as":[42,102,134],"portion":[45],"of":[46,54,94],"prompts":[47,67],"provide":[48],"negligible":[49],"gradients":[50],"are":[52],"thus":[53],"low":[55],"utility.":[56,143],"To":[57],"address":[58],"this":[59],"problem,":[60],"we":[61,108,154],"investigate":[62],"how":[63],"to":[64,138],"select":[65],"high-utility":[66],"before":[68],"rollout":[70,160],"phase.":[71],"Our":[72],"experimental":[73],"analysis":[74],"reveals":[75],"that":[76,156],"sample":[77],"utility":[78],"non-uniform":[80],"evolving:":[82],"strongest":[84],"signals":[86],"concentrate":[87],"at":[88],"``learning":[90],"edge\",":[91],"intersection":[93],"intermediate":[95],"difficulty":[96],"high":[98],"uncertainty,":[99],"which":[100],"shifts":[101],"proceeds.":[104],"Motivated":[105],"by":[106],"this,":[107],"propose":[109],"HIVE":[110,122,146,157],"(History-Informed":[111],"online-VErified":[113],"selection),":[115],"dual-stage":[117],"framework":[118],"data-efficient":[120],"RL.":[121],"utilizes":[123],"historical":[124],"reward":[125],"trajectories":[126],"coarse":[128],"selection":[129],"employs":[131],"entropy":[133],"real-time":[136],"proxy":[137],"prune":[139],"instances":[140],"with":[141],"stale":[142],"By":[144],"evaluating":[145],"across":[147],"math":[149],"benchmarks":[151],"models,":[153],"show":[155],"yields":[158],"significant":[159],"efficiency":[161],"without":[162],"compromising":[163],"performance.":[164]},"counts_by_year":[],"updated_date":"2026-03-28T06:16:51.555046","created_date":"2026-03-28T00:00:00"}