{"id":"https://openalex.org/W7213675668","doi":null,"title":"Evolution or Illusion? Rethinking Evaluation in LLM Evolutionary Search","display_name":"Evolution or Illusion? Rethinking Evaluation in LLM Evolutionary Search","publication_year":2026,"publication_date":"2026-09-17","ids":{"openalex":"https://openalex.org/W7213675668"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.19799","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.19799","pdf_url":"https://arxiv.org/pdf/2609.19799","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","is_traditional":true,"indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.19799","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116540615","display_name":"Tal Oved","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oved, Tal","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5096068527","display_name":"Roi Pony","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pony, Roi","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020146315","display_name":"Oshri Naparstek","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Naparstek, Oshri","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047102702","display_name":"Udi Barzelay","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Barzelay, Udi","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1341412227"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9940999746322632,"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":0.9940999746322632,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.0026000000070780516,"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":0.0010999999940395355,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/program-synthesis","display_name":"program synthesis","score":0.7910000085830688},{"id":"https://openalex.org/keywords/evaluation-protocol","display_name":"evaluation protocol","score":0.43799999356269836},{"id":"https://openalex.org/keywords/budget-allocation","display_name":"budget allocation","score":0.8529999852180481},{"id":"https://openalex.org/keywords/seed-width","display_name":"seed width","score":0.39399999380111694},{"id":"https://openalex.org/keywords/measurement-protocol","display_name":"measurement protocol","score":0.4620000123977661}],"concepts":[{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5874999761581421},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5619000196456909},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4869999885559082},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4537999927997589},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.4278999865055084},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.4075999855995178},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.3662000000476837},{"id":"https://openalex.org/C2777691475","wikidata":"https://www.wikidata.org/wiki/Q4897049","display_name":"Best value","level":2,"score":0.36480000615119934},{"id":"https://openalex.org/C105902424","wikidata":"https://www.wikidata.org/wiki/Q1197129","display_name":"Evolutionary computation","level":2,"score":0.3553999960422516},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3434999883174896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33480000495910645},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.32839998602867126},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3163999915122986},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.29789999127388},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.2962999939918518},{"id":"https://openalex.org/C8505890","wikidata":"https://www.wikidata.org/wiki/Q605095","display_name":"Budget constraint","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2718000113964081}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:arXiv.org:2609.19799","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.19799","pdf_url":"https://arxiv.org/pdf/2609.19799","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.19799","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.19799","pdf_url":"https://arxiv.org/pdf/2609.19799","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/W7213675668.pdf","grobid_xml":"https://content.openalex.org/works/W7213675668.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W4387293261","https://openalex.org/W4390647620","https://openalex.org/W4402733601","https://openalex.org/W4406492615","https://openalex.org/W4414973977","https://openalex.org/W4414982480","https://openalex.org/W4415186464","https://openalex.org/W7130718641","https://openalex.org/W7131425980","https://openalex.org/W7133214313","https://openalex.org/W7161550390","https://openalex.org/W7163346078"],"related_works":["https://openalex.org/W7162766506","https://openalex.org/W7156807052","https://openalex.org/W7160960363","https://openalex.org/W7223010173","https://openalex.org/W7201866534","https://openalex.org/W7221114610","https://openalex.org/W7166845721","https://openalex.org/W7208835078","https://openalex.org/W7151321365","https://openalex.org/W7215116981"],"abstract_inverted_index":{"LLM-driven":[0],"evolutionary":[1,44],"search":[2,45],"finds":[3],"programs":[4],"by":[5,53],"launching":[6],"seeds":[7,70,87,154],"and":[8,28,71,89,99,169],"iterating":[9],"each":[10],"one.":[11],"Papers":[12],"report":[13,59],"a":[14,23,66,82,161],"single":[15],"budget":[16,84,151],"setting,":[17],"usually":[18],"one":[19,33,117,125],"seed":[20,126],"run":[21,62],"for":[22,172],"fixed":[24,83],"number":[25,136],"of":[26,69,109,137],"iterations,":[27],"rank":[29],"methods":[30],"from":[31],"that":[32,76,106,121,152,164],"point.":[34],"We":[35,41,61,159],"show":[36],"this":[37],"is":[38,127,139],"not":[39],"enough.":[40],"evaluate":[42],"three":[43],"strategies":[46,110],"on":[47],"five":[48],"optimization":[49],"tasks,":[50],"commonly":[51],"used":[52],"papers":[54],"in":[55,145],"the":[56,63,77,95,97,100,107,114,119,134,142,166],"genre":[57],"to":[58,80],"results.":[60],"analysis":[64],"over":[65],"full":[67],"grid":[68],"iterations.":[72],"Our":[73],"findings":[74],"suggest":[75],"best":[78,128,135],"way":[79],"split":[81],"between":[85],"more":[86,90,153],"(width)":[88],"iterations":[91,138],"(depth)":[92],"changes":[93,112],"with":[94,113],"strategy,":[96],"task,":[98],"total":[101],"budget.":[102,115],"Furthermore,":[103],"we":[104],"observe":[105],"ranking":[108],"also":[111],"On":[116,132],"task":[118],"strategy":[120],"looks":[122],"worst":[123],"at":[124,129],"forty":[130],"seeds.":[131],"another":[133],"well":[140],"below":[141],"value":[143],"common":[144],"practice,":[146],"so":[147],"extra":[148],"depth":[149],"wastes":[150],"would":[155],"turn":[156],"into":[157],"score.":[158],"provide":[160],"measurement":[162],"protocol":[163],"reports":[165],"seeds-by-iterations":[167],"frontier":[168],"practical":[170],"guidance":[171],"using":[173],"it.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-20T00:00:00"}