{"id":"https://openalex.org/W7162788548","doi":"https://doi.org/10.48550/arxiv.2605.29847","title":"EvoRubric: Self-Evolving Rubric-Driven RL for Open-Ended Generation","display_name":"EvoRubric: Self-Evolving Rubric-Driven RL for Open-Ended Generation","publication_year":2026,"publication_date":"2026-05-28","ids":{"openalex":"https://openalex.org/W7162788548","doi":"https://doi.org/10.48550/arxiv.2605.29847"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.29847","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29847","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,"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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.29847","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137359564","display_name":"Xin Guan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guan, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137389172","display_name":"Xiaomeng Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Xiaomeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102275870","display_name":"Shen Huang","orcid":"https://orcid.org/0009-0006-7826-1667"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Shen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137330502","display_name":"Zhenyi Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zhenyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137318418","display_name":"Bo Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Bo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137331499","display_name":"Zijian Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zijian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137389176","display_name":"Pengjun Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Pengjun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137364369","display_name":"Bo Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Bo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137375856","display_name":"Jiuxin Cao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Jiuxin","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/T10028","display_name":"Topic Modeling","score":0.2849000096321106,"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/T10028","display_name":"Topic Modeling","score":0.2849000096321106,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.19740000367164612,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.1501999944448471,"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/rubric","display_name":"Rubric","score":0.7893000245094299},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5776000022888184},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5738000273704529},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5504999756813049},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.46129998564720154},{"id":"https://openalex.org/keywords/verifiable-secret-sharing","display_name":"Verifiable secret sharing","score":0.44679999351501465},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.43320000171661377},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.42260000109672546}],"concepts":[{"id":"https://openalex.org/C111640148","wikidata":"https://www.wikidata.org/wiki/Q847349","display_name":"Rubric","level":2,"score":0.7893000245094299},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7531999945640564},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5776000022888184},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5738000273704529},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5504999756813049},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.46129998564720154},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.44679999351501465},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.43320000171661377},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.42260000109672546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38760000467300415},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3865000009536743},{"id":"https://openalex.org/C519536355","wikidata":"https://www.wikidata.org/wiki/Q21021151","display_name":"Repurposing","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C9616225","wikidata":"https://www.wikidata.org/wiki/Q3929429","display_name":"Semantic reasoner","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C97686452","wikidata":"https://www.wikidata.org/wiki/Q7604153","display_name":"Static analysis","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2671000063419342},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.25690001249313354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.29847","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29847","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,"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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.29847","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29847","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,"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":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.5991060733795166,"display_name":"Reduced inequalities"}],"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],"(RL)":[2],"has":[3],"significantly":[4],"advanced":[5],"Large":[6],"Language":[7],"Models":[8],"(LLMs)":[9],"in":[10],"verifiable":[11],"domains,":[12],"but":[13],"aligning":[14],"models":[15,56],"for":[16,57],"open-ended":[17],"generation":[18,87,90],"remains":[19],"profoundly":[20],"challenging":[21],"due":[22],"to":[23,147],"the":[24,74,112],"lack":[25],"of":[26,114],"definitive":[27],"rewards.":[28],"Current":[29],"rubric-based":[30],"RL":[31,70],"methods":[32],"mitigate":[33],"this":[34,61],"by":[35],"employing":[36],"explicit":[37],"criteria;":[38],"however,":[39],"they":[40],"rely":[41],"heavily":[42],"on":[43,76,80,197],"static,":[44],"human-annotated":[45],"rubrics":[46],"that":[47,72,161],"inevitably":[48],"cause":[49],"policy":[50],"lag,":[51],"or":[52],"expensive":[53],"external":[54,81],"proprietary":[55],"dynamic":[58],"updates.":[59],"In":[60],"paper,":[62],"we":[63,117],"propose":[64],"EvoRubric,":[65],"a":[66,92,100,103,119,124,129,140],"novel":[67],"single-policy":[68],"co-evolutionary":[69],"framework":[71,173],"eliminates":[73],"reliance":[75],"static":[77,166,198],"criteria":[78,135],"and":[79,88,102,110,128,157,167],"rubric":[82,89],"generators.":[83],"By":[84],"unifying":[85],"response":[86],"under":[91],"single":[93],"parameterized":[94],"policy,":[95],"EvoRubric":[96,162,184],"dynamically":[97,137],"alternates":[98],"between":[99],"Reasoner":[101],"Rubric":[104],"Generator.":[105],"To":[106],"prevent":[107],"reward":[108],"hacking":[109],"ensure":[111],"reliability":[113],"generated":[115],"signals,":[116],"introduce":[118],"multi-level":[120],"verification":[121],"pipeline":[122],"featuring":[123],"meta-verifier,":[125],"zero-variance":[126],"pruning,":[127],"Leave-One-Out":[130],"peer":[131],"consensus":[132],"mechanism.":[133],"Validated":[134],"are":[136],"archived":[138],"into":[139],"memory":[141],"pool,":[142],"yielding":[143],"dense,":[144],"multi-objective":[145],"rewards":[146],"continuously":[148],"co-optimize":[149],"both":[150],"roles.":[151],"Extensive":[152],"experiments":[153],"across":[154],"Medical,":[155],"Writing,":[156],"Science":[158],"domains":[159],"demonstrate":[160],"consistently":[163],"outperforms":[164],"traditional":[165],"external-LLM-driven":[168],"alignment":[169],"methods.":[170],"Notably,":[171],"our":[172],"is":[174],"compatible":[175],"with":[176,181],"human-expert":[177],"priors.":[178],"When":[179],"initialized":[180],"expert-annotated":[182],"rubrics,":[183],"can":[185],"further":[186],"uncover":[187],"novel,":[188],"discriminative":[189],"dimensions,":[190],"achieving":[191],"better":[192],"performance":[193],"than":[194],"relying":[195],"solely":[196],"expert":[199],"annotations.":[200]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-30T00:00:00"}