{"id":"https://openalex.org/W7134893528","doi":"https://doi.org/10.1109/icdmw69685.2025.00294","title":"Spireeval: Transforming Gameplay into Sequential Datasets for LLM Decision-Making Analysis","display_name":"Spireeval: Transforming Gameplay into Sequential Datasets for LLM Decision-Making Analysis","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W7134893528","doi":"https://doi.org/10.1109/icdmw69685.2025.00294"},"language":null,"primary_location":{"id":"doi:10.1109/icdmw69685.2025.00294","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdmw69685.2025.00294","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Data Mining Workshops (ICDMW)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128772943","display_name":"Maxim Suslov","orcid":null},"institutions":[{"id":"https://openalex.org/I4210157288","display_name":"Activated Research Company (United States)","ror":"https://ror.org/04sv8h433","country_code":"US","type":"company","lineage":["https://openalex.org/I4210157288"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maxim Suslov","raw_affiliation_strings":["High School Student, Eden Prairie High School,Eden Prairie,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"High School Student, Eden Prairie High School,Eden Prairie,United States","institution_ids":["https://openalex.org/I4210157288"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128780053","display_name":"Shivashish Khanna","orcid":null},"institutions":[{"id":"https://openalex.org/I4210157288","display_name":"Activated Research Company (United States)","ror":"https://ror.org/04sv8h433","country_code":"US","type":"company","lineage":["https://openalex.org/I4210157288"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shivashish Khanna","raw_affiliation_strings":["High School Student, Eden Prairie High School,Eden Prairie,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"High School Student, Eden Prairie High School,Eden Prairie,United States","institution_ids":["https://openalex.org/I4210157288"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000344989","display_name":"Zirui Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]},{"id":"https://openalex.org/I2800403580","display_name":"University of Minnesota System","ror":"https://ror.org/03grvy078","country_code":"US","type":"education","lineage":["https://openalex.org/I2800403580"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zirui Liu","raw_affiliation_strings":["University of Minnesota,Department of Computer Science,Minneapolis,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Minnesota,Department of Computer Science,Minneapolis,United States","institution_ids":["https://openalex.org/I130238516","https://openalex.org/I2800403580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":"2404","last_page":"2408"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.07779999822378159,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.07779999822378159,"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/T11891","display_name":"Big Data and Business Intelligence","score":0.0575999990105629,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.02590000070631504,"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/field","display_name":"Field (mathematics)","score":0.30489999055862427},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.28949999809265137},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2890999913215637},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.2361000031232834},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.23330000042915344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6499000191688538},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39169999957084656},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26350000500679016},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2361000031232834},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.23330000042915344},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2303999960422516},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.22949999570846558}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdmw69685.2025.00294","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdmw69685.2025.00294","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Data Mining Workshops (ICDMW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.666480541229248}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W4400361424"],"related_works":[],"abstract_inverted_index":{"As":[0],"Artificial":[1],"Intelligence":[2],"(AI)":[3],"systems,":[4],"particularly":[5],"Large":[6],"Language":[7],"Models":[8],"(LLMs),":[9],"become":[10],"more":[11],"capable,":[12],"evaluating":[13],"their":[14,19],"decision-making":[15],"processes,":[16],"not":[17],"just":[18],"outcomes,":[20],"requires":[21],"environments":[22],"that":[23,142],"are":[24],"rich,":[25],"dynamic,":[26],"and":[27,178],"strategically":[28],"deep.":[29],"We":[30],"present":[31,137],"an":[32,138],"open-source":[33],"architecture,":[34],"SpireEval,":[35],"for":[36,59,108,125,152],"instrumenting":[37],"\u201cSlay":[38],"The":[39,85,98,190],"Spire\u201d":[40],"to":[41,46,57,79,83,90,120,165,186,192],"generate":[42],"structured,":[43,187],"finegrained":[44],"datasets":[45],"evaluate":[47],"LLM":[48,109],"strategic":[49],"performance,":[50],"using":[51],"it":[52],"as":[53,87,156],"a":[54,77,88,161],"case":[55],"study":[56],"allow":[58],"the":[60,92,106,113,118,130,176],"development":[61],"of":[62,95,116,132],"strong":[63],"benchmarks":[64],"within":[65],"similar":[66],"procedural":[67],"game":[68,114],"environments.":[69],"Our":[70,169],"primary":[71],"contribution":[72],"in":[73],"this":[74],"paper":[75,99],"is":[76,196],"framework":[78],"connect":[80],"powerful":[81],"chatbots":[82],"Slay":[84,117],"Spire":[86,119],"channel":[89],"measure":[91],"decisionmaking":[93],"capacity":[94],"advanced":[96],"models.":[97],"details":[100],"our":[101,133,194],"opensource":[102],"repository,":[103],"which":[104],"provides":[105],"tools":[107],"agent":[110,167],"interaction":[111],"with":[112],"state":[115],"then":[121,159],"gather":[122],"data":[123],"suitable":[124],"statistical":[126,140],"inspection.":[127],"To":[128],"demonstrate":[129],"feasibility":[131],"approach,":[134],"we":[135,146],"also":[136],"example":[139],"benchmark":[141],"works":[143],"twofold.":[144],"First,":[145],"score":[147],"individual":[148],"combat":[149],"actions,":[150],"adjusting":[151],"contextual":[153],"factors":[154],"such":[155],"enemy":[157],"intent,":[158],"use":[160],"run-level":[162],"Bayesian":[163],"model":[164],"estimate":[166],"skill.":[168],"approach":[170],"enables":[171],"reproducible,":[172],"detailed":[173],"analysis":[174],"at":[175],"run":[177],"action":[179],"level,":[180],"moving":[181],"beyond":[182],"aggregate":[183],"performance":[184],"metrics":[185],"context-rich":[188],"datasets.":[189],"code":[191],"reproduce":[193],"experiment":[195],"available":[197],"here:":[198],"https://github.com/Max-Suslov/game-bench.":[199]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-12T00:00:00"}