{"id":"https://openalex.org/W4414359190","doi":"https://doi.org/10.24963/ijcai.2025/1249","title":"Combining Code Generating Large Language Models and Self-Play to Iteratively Refine Strategies in Games","display_name":"Combining Code Generating Large Language Models and Self-Play to Iteratively Refine Strategies in Games","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359190","doi":"https://doi.org/10.24963/ijcai.2025/1249"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/1249","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/1249","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://oru.diva-portal.org/smash/get/diva2:2020923/FULLTEXT01","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062949033","display_name":"Yoram Bachrach","orcid":"https://orcid.org/0000-0002-4382-7636"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yoram Bachrach","raw_affiliation_strings":["Meta"],"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114634947","display_name":"Edan Toledo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Edan Toledo","raw_affiliation_strings":["Meta"],"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061387148","display_name":"Karen Hambardzumyan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karen Hambardzumyan","raw_affiliation_strings":["Meta"],"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020439365","display_name":"Despoina Magka","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Despoina Magka","raw_affiliation_strings":["Meta"],"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057031908","display_name":"Martin Josifoski","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin Josifoski","raw_affiliation_strings":["Meta"],"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017949957","display_name":"Minqi Jiang","orcid":"https://orcid.org/0000-0003-1285-0208"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minqi Jiang","raw_affiliation_strings":["Meta"],"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059094093","display_name":"Jakob Foerster","orcid":"https://orcid.org/0000-0001-9688-2498"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jakob Foerster","raw_affiliation_strings":["Meta"],"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018702533","display_name":"Roberta R\u0103ileanu","orcid":"https://orcid.org/0009-0003-2057-2903"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roberta Raileanu","raw_affiliation_strings":["Meta"],"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079740967","display_name":"Tatiana Shavrina","orcid":"https://orcid.org/0000-0002-6976-0185"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tatiana Shavrina","raw_affiliation_strings":["Meta"],"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004751764","display_name":"Nicola Cancedda","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicola Cancedda","raw_affiliation_strings":["Meta"],"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055550766","display_name":"Avraham Ruderman","orcid":"https://orcid.org/0000-0002-6044-5218"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Avraham Ruderman","raw_affiliation_strings":["Meta"],"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023079707","display_name":"Katie Millican","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Katie Millican","raw_affiliation_strings":["Meta"],"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086769710","display_name":"Andrei N. Lupu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrei Lupu","raw_affiliation_strings":["Meta"],"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070202776","display_name":"Rishi Hazra","orcid":"https://orcid.org/0000-0003-3422-2085"},"institutions":[{"id":"https://openalex.org/I26437253","display_name":"\u00d6rebro University","ror":"https://ror.org/05kytsw45","country_code":"SE","type":"education","lineage":["https://openalex.org/I26437253"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Rishi Hazra","raw_affiliation_strings":["\u00d6rebro University"],"affiliations":[{"raw_affiliation_string":"\u00d6rebro University","institution_ids":["https://openalex.org/I26437253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":14,"corresponding_author_ids":["https://openalex.org/A5062949033"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1383139,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10999","last_page":"11003"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9621999859809875,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9621999859809875,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9526000022888184,"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":0.9520999789237976,"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/oracle","display_name":"Oracle","score":0.738099992275238},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6593999862670898},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6502000093460083},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5543000102043152},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.47350001335144043},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.46369999647140503},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.43160000443458557},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.39480000734329224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.796500027179718},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.738099992275238},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6593999862670898},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6502000093460083},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5543000102043152},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.47350001335144043},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.46369999647140503},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.43160000443458557},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.413100004196167},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.39480000734329224},{"id":"https://openalex.org/C32407928","wikidata":"https://www.wikidata.org/wiki/Q2733833","display_name":"Best response","level":3,"score":0.37770000100135803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36039999127388},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34439998865127563},{"id":"https://openalex.org/C2778583558","wikidata":"https://www.wikidata.org/wiki/Q771245","display_name":"Code reuse","level":3,"score":0.31940001249313354},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.28380000591278076},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C202556891","wikidata":"https://www.wikidata.org/wiki/Q1584646","display_name":"Repeated game","level":3,"score":0.2653000056743622},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.24963/ijcai.2025/1249","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/1249","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:DiVA.org:oru-125558","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:oru:diva-125558","pdf_url":"https://oru.diva-portal.org/smash/get/diva2:2020923/FULLTEXT01","source":{"id":"https://openalex.org/S4306400154","display_name":"\u00d6rebro University Library (\u00d6rebro University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I26437253","host_organization_name":"\u00d6rebro University","host_organization_lineage":["https://openalex.org/I26437253"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:DiVA.org:oru-125558","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:oru:diva-125558","pdf_url":"https://oru.diva-portal.org/smash/get/diva2:2020923/FULLTEXT01","source":{"id":"https://openalex.org/S4306400154","display_name":"\u00d6rebro University Library (\u00d6rebro University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I26437253","host_organization_name":"\u00d6rebro University","host_organization_lineage":["https://openalex.org/I26437253"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414359190.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,20,43,57,75,153],"propose":[1],"a":[2,68,99,114,130],"self-play":[3],"approach":[4],"to":[5,26,31,39,52,101,108,135,156],"generating":[6],"strategies":[7,14],"for":[8,89,111,139,148],"playing":[9,112,140],"in":[10,33,49,62,87,160],"multi-player":[11],"games,":[12],"where":[13],"are":[15,133],"represented":[16],"as":[17,40],"computer":[18],"code.":[19],"use":[21,67],"large":[22],"language":[23],"models":[24],"(LLMs)":[25],"generate":[27,53],"pieces":[28],"of":[29,81,151],"code":[30,110],"play":[32,174],"the":[34,45,94,102,106,117,122,141,146,149,161,164,168,176],"game,":[35],"which":[36],"we":[37],"refer":[38],"generated":[41,47,83,177],"bots.":[42,178],"engage":[44],"LLM":[46,82,107],"bots":[48,92,138,159,169],"competitions,":[50],"designed":[51],"increasingly":[54],"stronger":[55],"strategies.":[56],"follow":[58],"game":[59,150],"theoretic":[60],"principles":[61],"organizing":[63],"these":[64],"tournaments,":[65],"and":[66,85,173],"Policy":[69],"Space":[70],"Response":[71],"Oracle":[72],"(PSRO)":[73],"approach.":[74],"start":[76],"with":[77],"an":[78],"initial":[79,158],"set":[80],"bots,":[84],"continue":[86],"rounds":[88,132],"adding":[90],"new":[91],"into":[93],"population.":[95,124],"Each":[96],"round":[97],"adds":[98],"bot":[100,115],"population":[103],"by":[104],"asking":[105],"produce":[109],"against":[113,175],"representing":[116],"Nash":[118],"equilibrium":[119],"mixture":[120],"over":[121,171],"current":[123],"Our":[125,143],"analysis":[126],"shows":[127,145],"that":[128],"even":[129],"few":[131],"sufficient":[134],"produces":[136],"strong":[137],"game.":[142],"demo":[144],"process":[147],"Checkers.":[152],"allow":[154],"users":[155],"select":[157],"population,":[162],"run":[163],"process,":[165],"inspect":[166],"how":[167],"evolve":[170],"time,":[172]},"counts_by_year":[],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}