{"id":"https://openalex.org/W4414836540","doi":"https://doi.org/10.1145/3748634","title":"LLMs May Not Be Human-Level Players, But They Can Be Testers: Measuring Game Difficulty with LLM Agents","display_name":"LLMs May Not Be Human-Level Players, But They Can Be Testers: Measuring Game Difficulty with LLM Agents","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W4414836540","doi":"https://doi.org/10.1145/3748634"},"language":"en","primary_location":{"id":"doi:10.1145/3748634","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3748634","pdf_url":null,"source":{"id":"https://openalex.org/S4210183893","display_name":"Proceedings of the ACM on Human-Computer Interaction","issn_l":"2573-0142","issn":["2573-0142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Human-Computer Interaction","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3748634","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068853170","display_name":"Chang Xiao","orcid":"https://orcid.org/0009-0008-7143-2771"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chang Xiao","raw_affiliation_strings":["Boston University, Boston, USA"],"affiliations":[{"raw_affiliation_string":"Boston University, Boston, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062911210","display_name":"Zixiaofan Yang","orcid":"https://orcid.org/0000-0003-3224-2154"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zixiaofan Yang","raw_affiliation_strings":["Columbia University, New York, USA"],"affiliations":[{"raw_affiliation_string":"Columbia University, New York, USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5068853170"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33008919,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":"6","first_page":"1097","last_page":"1123"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.9902999997138977,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.9902999997138977,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9775999784469604,"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/T11182","display_name":"Auction Theory and Applications","score":0.9750000238418579,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.43149998784065247},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.3693999946117401},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.3402000069618225},{"id":"https://openalex.org/keywords/serious-game","display_name":"Serious game","score":0.31470000743865967}],"concepts":[{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.43149998784065247},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4302000105381012},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3693999946117401},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.36399999260902405},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.3522999882698059},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.337799996137619},{"id":"https://openalex.org/C3018769082","wikidata":"https://www.wikidata.org/wiki/Q1506693","display_name":"Serious game","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.31310001015663147},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.249099999666214}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3748634","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3748634","pdf_url":null,"source":{"id":"https://openalex.org/S4210183893","display_name":"Proceedings of the ACM on Human-Computer Interaction","issn_l":"2573-0142","issn":["2573-0142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Human-Computer Interaction","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3748634","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3748634","pdf_url":null,"source":{"id":"https://openalex.org/S4210183893","display_name":"Proceedings of the ACM on Human-Computer Interaction","issn_l":"2573-0142","issn":["2573-0142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Human-Computer Interaction","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1565751582","https://openalex.org/W2073282066","https://openalex.org/W2478600331","https://openalex.org/W2623399293","https://openalex.org/W2783539613","https://openalex.org/W2802789500","https://openalex.org/W2902907165","https://openalex.org/W2963729301","https://openalex.org/W2980615522","https://openalex.org/W2982316857","https://openalex.org/W2997998108","https://openalex.org/W3006861906","https://openalex.org/W3015341521","https://openalex.org/W3096726323","https://openalex.org/W4239857641","https://openalex.org/W4244793087","https://openalex.org/W4247936669","https://openalex.org/W4299335686","https://openalex.org/W4307472389","https://openalex.org/W4363624465","https://openalex.org/W4378505261","https://openalex.org/W4388725043","https://openalex.org/W4389636360","https://openalex.org/W4396239104","https://openalex.org/W4400361801","https://openalex.org/W4409683224","https://openalex.org/W4410237593"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,25],"Large":[3],"Language":[4],"Models":[5],"(LLMs)":[6],"have":[7],"demonstrated":[8],"their":[9,90,131],"potential":[10],"as":[11,83,85,119,130],"autonomous":[12],"agents":[13,55,121],"across":[14],"various":[15],"tasks.":[16],"One":[17],"emerging":[18],"application":[19],"is":[20],"the":[21,37,50,69,86,127,156],"use":[22],"of":[23,52,138],"LLMs":[24,41,79,115,154],"playing":[26],"games.":[27],"In":[28],"this":[29],"work,":[30],"we":[31,145],"explore":[32],"a":[33,100],"practical":[34],"problem":[35],"for":[36,122,152],"gaming":[38],"industry:":[39],"Can":[40],"be":[42],"used":[43],"to":[44,56],"measure":[45],"game":[46,58,124,157],"difficulty?":[47],"We":[48],"evaluate":[49],"feasibility":[51],"using":[53],"LLM":[54],"test":[57],"difficulty,":[59],"focusing":[60],"on":[61,142],"two":[62],"widely":[63],"played":[64],"games:":[65],"Wordle":[66],"and":[67,103,150],"Slay":[68],"Spire":[70],".":[71],"Our":[72],"results":[73],"reveal":[74],"an":[75],"interesting":[76],"finding:":[77],"although":[78],"may":[80,133],"not":[81],"perform":[82],"well":[84],"average":[87],"human":[88,110,139],"player,":[89],"performance,":[91],"when":[92],"guided":[93],"by":[94,109],"simple,":[95],"generic":[96],"prompting":[97],"techniques,":[98],"shows":[99],"statistically":[101],"significant":[102],"strong":[104],"correlation":[105],"with":[106,136],"difficulty":[107,125],"indicated":[108],"players.":[111,140],"This":[112],"suggests":[113],"that":[114],"could":[116],"potentially":[117],"serve":[118],"human-like":[120],"measuring":[123],"during":[126],"development":[128],"process,":[129],"assessments":[132],"align":[134],"closely":[135],"those":[137],"Based":[141],"our":[143],"experiments,":[144],"also":[146],"propose":[147],"general":[148],"principles":[149],"guidelines":[151],"integrating":[153],"into":[155],"testing":[158],"workflow.":[159]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}