{"id":"https://openalex.org/W7160951781","doi":"https://doi.org/10.48550/arxiv.2605.09959","title":"G-Zero: Self-Play for Open-Ended Generation from Zero Data","display_name":"G-Zero: Self-Play for Open-Ended Generation from Zero Data","publication_year":2026,"publication_date":"2026-05-11","ids":{"openalex":"https://openalex.org/W7160951781","doi":"https://doi.org/10.48550/arxiv.2605.09959"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.09959","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.09959","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":"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.2605.09959","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135930743","display_name":"Chengsong Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Chengsong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136001345","display_name":"Haolin Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Haolin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135964431","display_name":"Tong Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Tong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136001547","display_name":"Runpeng Dai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai, Runpeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092240623","display_name":"Langlin Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Langlin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135921348","display_name":"Jinyuan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jinyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135964742","display_name":"Zongxia Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zongxia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135912385","display_name":"Zhepei Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Zhepei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136000161","display_name":"Yu Meng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135933372","display_name":"Jiaxin Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Jiaxin","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/T12535","display_name":"Machine Learning and Data Classification","score":0.23109999299049377,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.23109999299049377,"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":0.15569999814033508,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.09239999949932098,"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/verifiable-secret-sharing","display_name":"Verifiable secret sharing","score":0.6880000233650208},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.6015999913215637},{"id":"https://openalex.org/keywords/proxy","display_name":"Proxy (statistics)","score":0.5975000262260437},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.4999000132083893},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4390999972820282},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.336899995803833},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.30489999055862427}],"concepts":[{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.6880000233650208},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.6015999913215637},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.5975000262260437},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.53329998254776},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.4999000132083893},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4390999972820282},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.336899995803833},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.30329999327659607},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.2766999900341034},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26969999074935913},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2630000114440918},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25870001316070557}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.09959","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.09959","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":"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.2605.09959","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.09959","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":"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":[{"score":0.6002714037895203,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Self-evolving":[0],"LLMs":[1],"excel":[2],"in":[3,8],"verifiable":[4],"domains":[5],"but":[6],"struggle":[7],"open-ended":[9],"tasks,":[10],"where":[11],"reliance":[12],"on":[13,59],"proxy":[14],"LLM":[15,153],"judges":[16],"introduces":[17],"capability":[18,141],"bottlenecks":[19],"and":[20,55,84,121],"reward":[21,43],"hacking.":[22],"To":[23],"overcome":[24],"this,":[25],"we":[26,100],"introduce":[27],"G-Zero,":[28,112],"a":[29,50,60,66,102,147],"verifier-free,":[30],"co-evolutionary":[31],"framework":[32],"for":[33,106,151],"autonomous":[34],"self-improvement.":[35],"Our":[36],"core":[37],"innovation":[38],"is":[39,69,89],"Hint-$\u03b4$,":[40],"an":[41,107],"intrinsic":[42],"that":[44,114],"quantifies":[45],"the":[46,76,115,122,140],"predictive":[47],"shift":[48],"between":[49],"Generator":[51,88],"model's":[52],"unassisted":[53],"response":[54,57],"its":[56],"conditioned":[58],"self-generated":[61],"hint.":[62],"Using":[63],"this":[64],"signal,":[65],"Proposer":[67,116],"model":[68],"trained":[70],"via":[71,92],"GRPO":[72],"to":[73,94],"continuously":[74],"target":[75],"Generator's":[77],"blind":[78],"spots":[79],"by":[80],"synthesizing":[81],"challenging":[82],"queries":[83],"informative":[85],"hints.":[86],"The":[87],"concurrently":[90],"optimized":[91],"DPO":[93],"internalize":[95],"these":[96],"hint-guided":[97],"improvements.":[98],"Theoretically,":[99],"prove":[101],"best-iterate":[103],"suboptimality":[104],"guarantee":[105],"idealized":[108],"standard-DPO":[109],"version":[110],"of":[111,143],"provided":[113],"induces":[117],"sufficient":[118],"exploration":[119],"coverage":[120],"data":[123],"filteration":[124],"keeps":[125],"pseudo-label":[126],"score":[127],"noise":[128],"low.":[129],"By":[130],"deriving":[131],"supervision":[132],"entirely":[133],"from":[134],"internal":[135],"distributional":[136],"dynamics,":[137],"G-Zero":[138],"bypasses":[139],"ceilings":[142],"external":[144],"judges,":[145],"providing":[146],"scalable,":[148],"robust":[149],"pathway":[150],"continuous":[152],"self-evolution":[154],"across":[155],"unverifiable":[156],"domains.":[157]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-13T00:00:00"}