{"id":"https://openalex.org/W7083291402","doi":"https://doi.org/10.48550/arxiv.2509.19349","title":"ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution","display_name":"ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution","publication_year":2025,"publication_date":"2025-09-17","ids":{"openalex":"https://openalex.org/W7083291402","doi":"https://doi.org/10.48550/arxiv.2509.19349"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2509.19349","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.19349","pdf_url":"https://arxiv.org/pdf/2509.19349","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/2509.19349","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Lange, Robert Tjarko","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lange, Robert Tjarko","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114424089","display_name":"Yuki Imajuku","orcid":"https://orcid.org/0009-0005-7470-8305","observed_orcids":["https://orcid.org/0009-0005-7470-8305"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Imajuku, Yuki","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5005809555","display_name":"Edoardo Cetin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cetin, Edoardo","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":true,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9926999807357788,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9926999807357788,"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/T10260","display_name":"Software Engineering Research","score":0.005499999970197678,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10533","display_name":"Teaching and Learning Programming","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/software-evolution","display_name":"software evolution","score":0.9129999876022339},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7990000247955322},{"id":"https://openalex.org/keywords/sample-efficiency","display_name":"sample efficiency","score":0.7210000157356262},{"id":"https://openalex.org/keywords/circle-packing","display_name":"circle packing","score":0.8130000233650208},{"id":"https://openalex.org/keywords/loss-function-design","display_name":"loss function design","score":0.5220000147819519},{"id":"https://openalex.org/keywords/scientific-discovery","display_name":"scientific discovery","score":0.45500001311302185}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6870999932289124},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.65420001745224},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6207000017166138},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.5526000261306763},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4498000144958496},{"id":"https://openalex.org/C110332635","wikidata":"https://www.wikidata.org/wiki/Q629498","display_name":"Genetic programming","level":2,"score":0.4410000145435333},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.40860000252723694},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.39579999446868896},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3953000009059906},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3939000070095062},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38040000200271606},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.36640000343322754},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32749998569488525},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.32440000772476196},{"id":"https://openalex.org/C105902424","wikidata":"https://www.wikidata.org/wiki/Q1197129","display_name":"Evolutionary computation","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2906999886035919},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2736000120639801},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C111065885","wikidata":"https://www.wikidata.org/wiki/Q1189053","display_name":"Fuzz testing","level":3,"score":0.26089999079704285},{"id":"https://openalex.org/C100279318","wikidata":"https://www.wikidata.org/wiki/Q467440","display_name":"Sample space","level":2,"score":0.25690001249313354}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2509.19349","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.19349","pdf_url":"https://arxiv.org/pdf/2509.19349","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.2509.19349","doi":"https://doi.org/10.48550/arxiv.2509.19349","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.19349","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:2509.19349","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.19349","pdf_url":"https://arxiv.org/pdf/2509.19349","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/W4415108068","https://openalex.org/W7223200371","https://openalex.org/W7092287101","https://openalex.org/W7128708936","https://openalex.org/W7165647483","https://openalex.org/W7117990715","https://openalex.org/W7161602368","https://openalex.org/W7138238694","https://openalex.org/W7127711023","https://openalex.org/W4414981074"],"abstract_inverted_index":{"We":[0,116],"introduce":[1],"ShinkaEvolve:":[2],"a":[3,93,110,133],"new":[4,134],"open-source":[5,188],"framework":[6],"leveraging":[7],"large":[8],"language":[9],"models":[10],"(LLMs)":[11],"to":[12,52,73,154],"advance":[13],"scientific":[14,37],"discovery":[15,196],"with":[16,182],"state-of-the-art":[17,135],"performance":[18],"and":[19,77,83,99,109,128,159,190],"unprecedented":[20],"efficiency.":[21,185],"Recent":[22],"advances":[23],"in":[24,35,125],"scaling":[25],"inference":[26],"time":[27],"compute":[28],"of":[29,71,171],"LLMs":[30,48],"have":[31],"enabled":[32],"significant":[33],"progress":[34],"generalized":[36],"discovery.":[38],"These":[39],"approaches":[40],"rely":[41],"on":[42],"evolutionary":[43],"agentic":[44,145],"harnesses":[45,146],"that":[46,167,177],"leverage":[47],"as":[49],"mutation":[50],"operators":[51],"generate":[53],"candidate":[54],"solutions.":[55],"However,":[56],"current":[57],"code":[58,101],"evolution":[59],"methods":[60],"suffer":[61],"from":[62],"critical":[63],"limitations:":[64],"they":[65],"are":[66],"sample":[67,126,184],"inefficient,":[68],"requiring":[69],"thousands":[70],"samples":[72],"identify":[74],"effective":[75],"solutions,":[76,158],"remain":[78],"closed-source,":[79],"hindering":[80],"broad":[81,180],"adoption":[82],"extension.":[84],"ShinkaEvolve":[85,118,131,178],"addresses":[86],"these":[87],"limitations,":[88],"introducing":[89],"three":[90],"key":[91],"innovations:":[92],"parent":[94],"sampling":[95],"technique":[96],"balancing":[97,164],"exploration":[98],"exploitation,":[100],"novelty":[102],"rejection-sampling":[103],"for":[104,147],"efficient":[105],"search":[106],"space":[107,170],"exploration,":[108],"bandit-based":[111],"LLM":[112],"ensemble":[113],"selection":[114],"strategy.":[115],"evaluate":[117],"across":[119,197],"diverse":[120,198],"tasks,":[121,151],"demonstrating":[122],"consistent":[123],"improvements":[124,153],"efficiency":[127],"solution":[129,138],"quality.":[130],"discovers":[132,160],"circle":[136],"packing":[137],"using":[139],"only":[140],"150":[141],"samples,":[142],"designs":[143],"high-performing":[144],"AIME":[148],"mathematical":[149],"reasoning":[150],"identifies":[152],"ALE-Bench":[155],"competitive":[156],"programming":[157],"novel":[161],"mixture-of-expert":[162],"load":[163],"loss":[165],"functions":[166],"illuminate":[168],"the":[169],"optimization":[172],"strategies.":[173],"Our":[174],"results":[175],"demonstrate":[176],"achieves":[179],"applicability":[181],"exceptional":[183],"By":[186],"providing":[187],"accessibility":[189],"cost-efficiency,":[191],"this":[192],"work":[193],"democratizes":[194],"open-ended":[195],"computational":[199],"problems.":[200]},"counts_by_year":[],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2025-10-10T00:00:00"}