{"id":"https://openalex.org/W4415336491","doi":"https://doi.org/10.48550/arxiv.2509.24239","title":"ChessArena: A Chess Testbed for Evaluating Strategic Reasoning Capabilities of Large Language Models","display_name":"ChessArena: A Chess Testbed for Evaluating Strategic Reasoning Capabilities of Large Language Models","publication_year":2025,"publication_date":"2025-09-29","ids":{"openalex":"https://openalex.org/W4415336491","doi":"https://doi.org/10.48550/arxiv.2509.24239"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2509.24239","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2509.24239","pdf_url":"https://arxiv.org/pdf/2509.24239","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.24239","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100608993","display_name":"Jincheng Liu","orcid":"https://orcid.org/0009-0008-6576-4294"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Liu, Jincheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058280379","display_name":"Sijun He","orcid":"https://orcid.org/0000-0002-8809-2733"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Sijun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113163199","display_name":"Jingjing Wu","orcid":"https://orcid.org/0009-0006-1285-3504"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Jingjing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064807299","display_name":"Xiangsen Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xiangsen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101223339","display_name":"Yang Chen","orcid":"https://orcid.org/0000-0002-4584-857X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Kuang, Zhaoqi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kuang, Zhaoqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003409838","display_name":"Siqi Bao","orcid":"https://orcid.org/0000-0003-3885-125X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bao, Siqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100337338","display_name":"Yuan Yao","orcid":"https://orcid.org/0000-0002-2705-6245"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Yuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100608993"],"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9023000001907349,"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":0.9023000001907349,"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/testbed","display_name":"Testbed","score":0.7353000044822693},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.487199991941452},{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.4156000018119812},{"id":"https://openalex.org/keywords/automated-reasoning","display_name":"Automated reasoning","score":0.40059998631477356},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.37389999628067017},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.3619000017642975},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.3569999933242798},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.3443000018596649}],"concepts":[{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.7353000044822693},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6798999905586243},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.487199991941452},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4790000021457672},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.4156000018119812},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.40059998631477356},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.37389999628067017},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.3619000017642975},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.3569999933242798},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3443000018596649},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33959999680519104},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C36964233","wikidata":"https://www.wikidata.org/wiki/Q7920942","display_name":"Verbal reasoning","level":3,"score":0.2978000044822693},{"id":"https://openalex.org/C2993724205","wikidata":"https://www.wikidata.org/wiki/Q315","display_name":"Human language","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C9616225","wikidata":"https://www.wikidata.org/wiki/Q3929429","display_name":"Semantic reasoner","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C103057564","wikidata":"https://www.wikidata.org/wiki/Q4751139","display_name":"Analytic reasoning","level":3,"score":0.2874000072479248},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.2768999934196472},{"id":"https://openalex.org/C152563557","wikidata":"https://www.wikidata.org/wiki/Q7621861","display_name":"Strategic thinking","level":3,"score":0.27410000562667847},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C43971567","wikidata":"https://www.wikidata.org/wiki/Q3142865","display_name":"Logical reasoning","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C2778044066","wikidata":"https://www.wikidata.org/wiki/Q455595","display_name":"Amateur","level":2,"score":0.25949999690055847}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2509.24239","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2509.24239","pdf_url":"https://arxiv.org/pdf/2509.24239","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2509.24239","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.24239","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.24239","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2509.24239","pdf_url":"https://arxiv.org/pdf/2509.24239","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"large":[1],"language":[2],"models":[3,17],"(LLMs)":[4],"have":[5],"shown":[6],"strong":[7,109],"reasoning":[8,121],"capabilities.":[9],"However,":[10],"a":[11,36,59,108],"critical":[12],"question":[13],"remains:":[14],"do":[15,23],"these":[16],"possess":[18],"genuine":[19],"strategic":[20,44],"reasoning,":[21,45],"or":[22],"they":[24],"primarily":[25],"excel":[26],"at":[27],"pattern":[28],"recognition?":[29],"To":[30],"address":[31],"this,":[32],"we":[33],"present":[34,107],"ChessArena,":[35],"chess-based":[37],"testbed":[38],"for":[39],"evaluating":[40],"LLMs.":[41],"Chess":[42],"demands":[43],"precise":[46],"rule":[47],"adherence,":[48],"and":[49,85,99],"the":[50],"ability":[51],"to":[52,102],"track":[53],"complex":[54],"game":[55],"states.":[56],"ChessArena":[57],"is":[58],"competitive":[60],"framework":[61],"where":[62],"LLMs":[63,75],"play":[64,70],"against":[65],"each":[66],"other":[67],"under":[68],"four":[69],"modes.":[71],"We":[72,105],"evaluate":[73],"13":[74],"across":[76],"over":[77],"800":[78],"games,":[79],"testing":[80],"basic":[81],"understanding,":[82],"move":[83],"selection,":[84],"puzzle":[86],"solving.":[87],"Results":[88],"reveal":[89],"significant":[90],"shortcomings:":[91],"no":[92],"model":[93],"beats":[94],"Maia-1100":[95],"(human":[96],"amateur":[97],"level),":[98],"some":[100],"lose":[101],"random":[103],"play.":[104],"also":[106],"baseline:":[110],"our":[111],"fine-tuned":[112],"Qwen3-8B":[113],"substantially":[114],"improves":[115],"performance,":[116],"approaching":[117],"much":[118],"larger":[119],"state-of-the-art":[120],"models.":[122]},"counts_by_year":[],"updated_date":"2026-04-27T08:22:11.395708","created_date":"2025-10-19T00:00:00"}