{"id":"https://openalex.org/W4414923175","doi":"https://doi.org/10.1145/3771095","title":"Pok\u00e9LLMon: A Grounding and Reasoning Benchmark for Large Language Models in Pok\u00e9mon Battles","display_name":"Pok\u00e9LLMon: A Grounding and Reasoning Benchmark for Large Language Models in Pok\u00e9mon Battles","publication_year":2025,"publication_date":"2025-10-07","ids":{"openalex":"https://openalex.org/W4414923175","doi":"https://doi.org/10.1145/3771095"},"language":"en","primary_location":{"id":"doi:10.1145/3771095","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3771095","pdf_url":null,"source":{"id":"https://openalex.org/S97833917","display_name":"ACM Transactions on Internet Technology","issn_l":"1533-5399","issn":["1533-5399","1557-6051"],"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":"ACM Transactions on Internet Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3771095","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071522360","display_name":"Sihao Hu","orcid":"https://orcid.org/0000-0003-3297-6991"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sihao Hu","raw_affiliation_strings":["School of Computer Science, Georgia Institute of Technology","School of Computer Science, Georgia Institute of Technology, Atlanta, United States"],"raw_orcid":"https://orcid.org/0000-0003-3297-6991","affiliations":[{"raw_affiliation_string":"School of Computer Science, Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"School of Computer Science, Georgia Institute of Technology, Atlanta, United States","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020135180","display_name":"Tiansheng Huang","orcid":"https://orcid.org/0000-0002-4557-1865"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tiansheng Huang","raw_affiliation_strings":["Georgia Institute of Technology School of Computer Science","Georgia Institute of Technology School of Computer Science, Atlanta, United States"],"raw_orcid":"https://orcid.org/0000-0002-4557-1865","affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology School of Computer Science","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology School of Computer Science, Atlanta, United States","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112670911","display_name":"Gaowen Liu","orcid":"https://orcid.org/0009-0007-9048-9274"},"institutions":[{"id":"https://openalex.org/I135428043","display_name":"Cisco Systems (United States)","ror":"https://ror.org/03yt1ez60","country_code":"US","type":"company","lineage":["https://openalex.org/I135428043"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gaowen Liu","raw_affiliation_strings":["Cisco Systems Inc","Cisco Systems Inc, San Jose, United States"],"raw_orcid":"https://orcid.org/0009-0007-9048-9274","affiliations":[{"raw_affiliation_string":"Cisco Systems Inc","institution_ids":["https://openalex.org/I135428043"]},{"raw_affiliation_string":"Cisco Systems Inc, San Jose, United States","institution_ids":["https://openalex.org/I135428043"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071146373","display_name":"Ramana Rao Kompella","orcid":"https://orcid.org/0000-0002-7559-8997"},"institutions":[{"id":"https://openalex.org/I135428043","display_name":"Cisco Systems (United States)","ror":"https://ror.org/03yt1ez60","country_code":"US","type":"company","lineage":["https://openalex.org/I135428043"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ramana Kompella","raw_affiliation_strings":["Cisco Systems Inc","Cisco Systems Inc, San Jose, United States"],"raw_orcid":"https://orcid.org/0000-0002-7559-8997","affiliations":[{"raw_affiliation_string":"Cisco Systems Inc","institution_ids":["https://openalex.org/I135428043"]},{"raw_affiliation_string":"Cisco Systems Inc, San Jose, United States","institution_ids":["https://openalex.org/I135428043"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100343991","display_name":"Ling Liu","orcid":"https://orcid.org/0000-0002-4138-3082"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ling Liu","raw_affiliation_strings":["School of Computer Science, Georgia Institute of Technology","School of Computer Science, Georgia Institute of Technology, Atlanta, United States"],"raw_orcid":"https://orcid.org/0000-0002-4138-3082","affiliations":[{"raw_affiliation_string":"School of Computer Science, Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"School of Computer Science, Georgia Institute of Technology, Atlanta, United States","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13882414,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"26","issue":"1","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9890999794006348,"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":0.9890999794006348,"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":0.9811999797821045,"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":0.9631999731063843,"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/leverage","display_name":"Leverage (statistics)","score":0.6990000009536743},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6462000012397766},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5485000014305115},{"id":"https://openalex.org/keywords/conflation","display_name":"Conflation","score":0.5033000111579895},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.39340001344680786},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.3917999863624573},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.3894999921321869}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.807200014591217},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6990000009536743},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6462000012397766},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5485000014305115},{"id":"https://openalex.org/C130440534","wikidata":"https://www.wikidata.org/wiki/Q14946528","display_name":"Conflation","level":2,"score":0.5033000111579895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43560001254081726},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.39340001344680786},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.3917999863624573},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3894999921321869},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3529999852180481},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.3467999994754791},{"id":"https://openalex.org/C2777877512","wikidata":"https://www.wikidata.org/wiki/Q1116097","display_name":"Common ground","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3052000105381012},{"id":"https://openalex.org/C2776372474","wikidata":"https://www.wikidata.org/wiki/Q508291","display_name":"Simplicity","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.28049999475479126},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.2759999930858612},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.2648000121116638},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2590999901294708},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3771095","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3771095","pdf_url":null,"source":{"id":"https://openalex.org/S97833917","display_name":"ACM Transactions on Internet Technology","issn_l":"1533-5399","issn":["1533-5399","1557-6051"],"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":"ACM Transactions on Internet Technology","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3771095","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3771095","pdf_url":null,"source":{"id":"https://openalex.org/S97833917","display_name":"ACM Transactions on Internet Technology","issn_l":"1533-5399","issn":["1533-5399","1557-6051"],"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":"ACM Transactions on Internet Technology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2799002257","https://openalex.org/W4221143046","https://openalex.org/W4226278401","https://openalex.org/W4362514950","https://openalex.org/W4392935324","https://openalex.org/W4401042748"],"related_works":[],"abstract_inverted_index":{"Developing":[0],"grounding":[1,89,112],"techniques":[2,92,113],"for":[3,8,54,85],"LLMs":[4,23,53,101],"poses":[5],"two":[6],"requirements":[7,40],"interactive":[9,94],"environments,":[10],"i.e.,":[11],"(i)":[12],"the":[13,19,26,73,86],"presence":[14],"of":[15,21,28,79,88,125,132,148],"rich":[16],"knowledge":[17,49,69,104],"beyond":[18],"scope":[20],"existing":[22,100],"and":[24,70,76,90,105,117,120],"(ii)":[25],"complexity":[27],"tasks":[29],"that":[30,99,114],"require":[31],"strategic":[32],"reasoning.":[33],"Existing":[34],"environments":[35],"fail":[36],"to":[37,42],"meet":[38],"both":[39],"due":[41],"their":[43],"simplicity":[44],"or":[45],"reliance":[46],"on":[47],"commonsense":[48],"already":[50],"encoded":[51],"in":[52,93,107],"interaction.":[55],"In":[56],"this":[57],"article,":[58],"we":[59,136],"present":[60],"Pok\u00e9LLMon,":[61],"a":[62,122,129],"new":[63,83,130],"benchmark":[64,150],"enriched":[65],"with":[66],"fictional":[67],"game":[68,103,118],"characterized":[71],"by":[72],"intense,":[74],"dynamic,":[75],"adversarial":[77],"gameplay":[78],"Pok\u00e9mon":[80,108],"battles,":[81],"setting":[82],"challenges":[84,140],"development":[87],"reasoning":[91,126,139],"environments.":[95],"Empirical":[96],"evaluations":[97],"demonstrate":[98],"lack":[102],"struggle":[106],"battles.":[109],"We":[110],"investigate":[111],"leverage":[115],"feedback":[116],"knowledge,":[119],"provide":[121],"thorough":[123],"analysis":[124],"methods":[127],"from":[128],"perspective":[131],"action":[133],"consistency.":[134],"Additionally,":[135],"introduce":[137],"higher-level":[138],"when":[141],"playing":[142],"against":[143],"human":[144],"players.":[145],"The":[146],"implementation":[147],"our":[149],"is":[151],"released":[152],"at:":[153],"https://github.com/git-disl/PokeLLMon":[154],".":[155]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
