{"id":"https://openalex.org/W7204699366","doi":"https://doi.org/10.5281/zenodo.22168492","title":"Compiled Agency: Frontier General-Purpose Coding Agents Build Winning Game Players from Bare Interaction \u2014 from Flappy Bird to StarCraft II and Civilization","display_name":"Compiled Agency: Frontier General-Purpose Coding Agents Build Winning Game Players from Bare Interaction \u2014 from Flappy Bird to StarCraft II and Civilization","publication_year":2026,"publication_date":"2026-07-17","ids":{"openalex":"https://openalex.org/W7204699366","doi":"https://doi.org/10.5281/zenodo.22168492"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.18996","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.18996","pdf_url":"https://arxiv.org/pdf/2609.18996","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/2609.18996","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148704705","display_name":"Joey Xiao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiao, Joey","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129510188","display_name":"Haonan Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huang, Haonan","raw_affiliation_strings":["Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9937000274658203,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9937000274658203,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.002300000051036477,"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/T13904","display_name":"Artificial Intelligence Applications","score":0.0013000000035390258,"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/ai-coding-agents","display_name":"coding agents","score":0.8659999966621399},{"id":"https://openalex.org/keywords/game-agents","display_name":"game-playing agents","score":0.5870000123977661},{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.5690000057220459},{"id":"https://openalex.org/keywords/starcraft-ii","display_name":"StarCraft II","score":0.7509999871253967},{"id":"https://openalex.org/keywords/civilization","display_name":"civilization","score":0.6850000023841858},{"id":"https://openalex.org/keywords/held-out-evaluation","display_name":"held-out evaluation","score":0.5180000066757202},{"id":"https://openalex.org/keywords/flappy-bird","display_name":"Flappy Bird","score":0.41999998688697815}],"concepts":[{"id":"https://openalex.org/C2779182362","wikidata":"https://www.wikidata.org/wiki/Q17126187","display_name":"Session (web analytics)","level":2,"score":0.6165000200271606},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6144999861717224},{"id":"https://openalex.org/C2778024590","wikidata":"https://www.wikidata.org/wiki/Q2357432","display_name":"Cheating","level":2,"score":0.5401999950408936},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5336999893188477},{"id":"https://openalex.org/C2778571376","wikidata":"https://www.wikidata.org/wiki/Q1355821","display_name":"Frontier","level":2,"score":0.49970000982284546},{"id":"https://openalex.org/C2780175911","wikidata":"https://www.wikidata.org/wiki/Q5013404","display_name":"CONQUEST","level":2,"score":0.4494999945163727},{"id":"https://openalex.org/C544833334","wikidata":"https://www.wikidata.org/wiki/Q2005","display_name":"JavaScript","level":2,"score":0.3837999999523163},{"id":"https://openalex.org/C202556891","wikidata":"https://www.wikidata.org/wiki/Q1584646","display_name":"Repeated game","level":3,"score":0.35760000348091125},{"id":"https://openalex.org/C41826821","wikidata":"https://www.wikidata.org/wiki/Q844005","display_name":"Game Developer","level":3,"score":0.3418000042438507},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.34049999713897705},{"id":"https://openalex.org/C503285160","wikidata":"https://www.wikidata.org/wiki/Q858057","display_name":"Game design","level":2,"score":0.334199994802475},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.326200008392334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30820000171661377},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C47350684","wikidata":"https://www.wikidata.org/wiki/Q5157306","display_name":"Computational creativity","level":3,"score":0.3075999915599823},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C47175762","wikidata":"https://www.wikidata.org/wiki/Q13422573","display_name":"Non-cooperative game","level":3,"score":0.2953999936580658},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C47187476","wikidata":"https://www.wikidata.org/wiki/Q12336660","display_name":"Video game design","level":3,"score":0.2766999900341034},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2621000111103058},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2612000107765198},{"id":"https://openalex.org/C106485872","wikidata":"https://www.wikidata.org/wiki/Q5088884","display_name":"Cheap talk","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C54276265","wikidata":"https://www.wikidata.org/wiki/Q1061635","display_name":"Video game development","level":3,"score":0.2574000060558319},{"id":"https://openalex.org/C3017957056","wikidata":"https://www.wikidata.org/wiki/Q1331296","display_name":"Game play","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2609.18996","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.18996","pdf_url":"https://arxiv.org/pdf/2609.18996","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:10.5281/zenodo.22168492","doi":"https://doi.org/10.5281/zenodo.22168492","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22168492","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},{"id":"doi:10.5281/zenodo.22168493","doi":"https://doi.org/10.5281/zenodo.22168493","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22168493","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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:2609.18996","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.18996","pdf_url":"https://arxiv.org/pdf/2609.18996","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204699366.pdf","grobid_xml":"https://content.openalex.org/works/W7204699366.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7213528786","https://openalex.org/W7204193705","https://openalex.org/W7155049400","https://openalex.org/W7212249075","https://openalex.org/W7133750645","https://openalex.org/W7170085180","https://openalex.org/W2923208287","https://openalex.org/W7220946974","https://openalex.org/W7078428596","https://openalex.org/W7213411742"],"abstract_inverted_index":{"LLM":[0],"agents":[1,35,244],"have":[2],"repeatedly":[3],"struggled":[4],"to":[5,75,246],"convert":[6],"knowledge":[7],"of":[8,166,174,202,229,283],"a":[9,62,86,95,98,113,126,159,181,219,238,301],"game":[10,96,123],"into":[11,300],"competent":[12],"play,":[13],"even":[14],"when":[15],"researchers":[16],"build":[17],"the":[18,21,55,117,121,131,171,214,281,288,310,313],"agent":[19,118,304],"around":[20],"model---supplying":[22],"perception,":[23],"memory,":[24],"skill":[25],"libraries,":[26],"planners,":[27],"or":[28],"executable-policy":[29],"scaffolds.":[30],"Rapid":[31],"progress":[32],"in":[33],"coding":[34,88,243],"raises":[36],"two":[37,193],"sharper":[38],"questions:":[39],"can":[40],"frontier":[41],"models":[42],"now":[43],"win":[44,51,199],"games":[45,201,228],"at":[46],"all,":[47],"and---more":[48],"fundamentally---can":[49],"they":[50],"them":[52],"unaided,":[53],"building":[54],"entire":[56],"player":[57],"themselves?":[58],"We":[59,291],"introduce":[60],"Gauntlet,":[61],"develop--freeze--evaluate":[63],"framework":[64],"that":[65],"ports":[66],"games,":[67],"private":[68],"and":[69,82,102,124,133,157,192,196,237,267,270],"public,":[70],"from":[71],"small":[72],"JavaScript":[73],"arcades":[74],"full":[76,227],"commercial-scale":[77],"titles,":[78],"behind":[79],"one":[80,167],"uniform":[81],"deliberately":[83],"bare":[84],"contract:":[85],"general-purpose":[87],"agent,":[89],"used":[90],"exactly":[91],"as":[92],"shipped,":[93],"receives":[94],"description,":[97],"raw":[99],"observation/action":[100],"interface,":[101],"an":[103,146],"empty":[104],"policy":[105],"file---no":[106],"strategy,":[107],"no":[108,110,221],"algorithm,":[109],"architecture.":[111],"In":[112],"single":[114],"autonomous":[115],"session":[116,165,173],"experiments":[119],"with":[120,139],"live":[122,261],"engineers":[125],"standalone":[127],"controller;":[128],"we":[129],"freeze":[130],"result":[132],"score":[134],"it":[135],"on":[136,208],"held-out":[137,150,209],"instances":[138],"zero":[140],"model":[141,235],"calls":[142,236],"during":[143],"play.":[144],"On":[145],"unpublished":[147],"procedural":[148],"roguelike,":[149],"success":[151],"spans":[152],"0--86%":[153],"across":[154],"deployed":[155],"systems":[156],"exposes":[158],"sharp":[160],"generational":[161],"threshold:":[162],"every":[163,186],"observed":[164],"newest-generation":[168],"system":[169,224],"outperforms":[170],"best":[172],"its":[175],"immediate":[176],"predecessor.":[177],"At":[178],"full-game":[179],"scale,":[180],"compiled":[182,295,299],"raw-API":[183],"controller":[184],"defeats":[185],"fair":[187],"StarCraft":[188],"II":[189],"built-in":[190,215],"AI":[191],"cheating":[194],"variants,":[195],"single-session":[197],"programs":[198,256],"complete":[200],"Civilization":[203],"(Freeciv)":[204],"by":[205,309],"total":[206],"conquest":[207],"seeds---at":[210],"modest":[211],"rates,":[212],"against":[213],"novice":[216],"AI,":[217],"yet":[218,250],"first:":[220],"prior":[222],"language-agent":[223],"had":[225],"won":[226],"this":[230,293],"genre":[231],"standalone,":[232],"without":[233],"per-turn":[234],"hand-crafted":[239],"tactical":[240],"layer.":[241],"Frontier":[242],"begin":[245],"track,":[247],"though":[248],"not":[249,285,312],"master,":[251],"long-horizon":[252],"strategy.":[253],"The":[254],"frozen":[255],"are":[257],"inspectable:":[258],"winners":[259],"contain":[260],"simulation,":[262],"persistent":[263,302],"state,":[264],"calibrated":[265],"doctrine,":[266],"finishing":[268],"logic,":[269],"generalize":[271],"through":[272],"observation":[273],"rather":[274],"than":[275],"seed":[276],"lookup;":[277],"fresh-session":[278],"variance":[279],"makes":[280],"distribution":[282],"artifacts,":[284],"any":[286],"champion,":[287],"measured":[289],"object.":[290],"call":[292],"capability":[294],"agency:":[296],"development":[297],"experience":[298],"executable":[303],"whose":[305],"architecture":[306],"is":[307],"built":[308],"model,":[311],"researcher.":[314]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-31T00:00:00"}
