{"id":"https://openalex.org/W7221783101","doi":"https://doi.org/10.48550/arxiv.2610.17310","title":"Beyond Successful Play: Diagnosing Opponent Modeling in Large Language Models","display_name":"Beyond Successful Play: Diagnosing Opponent Modeling in Large Language Models","publication_year":2026,"publication_date":"2026-10-12","ids":{"openalex":"https://openalex.org/W7221783101","doi":"https://doi.org/10.48550/arxiv.2610.17310"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.17310","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.17310","pdf_url":"https://arxiv.org/pdf/2610.17310","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.17310","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5158679011","display_name":"Hanbo Xie","orcid":null,"observed_orcids":[]},"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":"Xie, Hanbo","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5158747664","display_name":"Yue Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162608824","display_name":"University of Sussex","ror":"https://ror.org/00ayhx656","country_code":"GB","type":"education","lineage":["https://openalex.org/I162608824"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhao, Yue","raw_affiliation_strings":["University of Sussex"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sussex","institution_ids":["https://openalex.org/I162608824"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033785127","display_name":"Robert C. Wilson","orcid":"https://orcid.org/0000-0002-2963-2971","observed_orcids":["https://orcid.org/0000-0002-2963-2971"]},"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":"Wilson, Robert C.","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"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/T10656","display_name":"Child and Animal Learning Development","score":0.423799991607666,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10656","display_name":"Child and Animal Learning Development","score":0.423799991607666,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.1914999932050705,"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/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.0892999991774559,"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/theory-of-mind","display_name":"theory of mind","score":0.8169999718666077},{"id":"https://openalex.org/keywords/opponent-modeling","display_name":"opponent modeling","score":0.9020000100135803},{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.7490000128746033},{"id":"https://openalex.org/keywords/hide-and-seek","display_name":"hide and seek","score":0.7720000147819519},{"id":"https://openalex.org/keywords/belief-tracking","display_name":"belief tracking","score":0.8019999861717224},{"id":"https://openalex.org/keywords/action-prediction","display_name":"action prediction","score":0.7919999957084656},{"id":"https://openalex.org/keywords/mentalization","display_name":"mentalization","score":0.5040000081062317},{"id":"https://openalex.org/keywords/supervised-fine-tuning","display_name":"supervised fine-tuning","score":0.6679999828338623},{"id":"https://openalex.org/keywords/qwen2-5","display_name":"Qwen2.5","score":0.7699999809265137},{"id":"https://openalex.org/keywords/gpt-5-4","display_name":"GPT-5.4","score":0.9259999990463257}],"concepts":[{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6424999833106995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6065000295639038},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.604200005531311},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.536899983882904},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5235000252723694},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5105999708175659},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4399000108242035},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.3952000141143799},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.364300012588501},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C2779560602","wikidata":"https://www.wikidata.org/wiki/Q639219","display_name":"Theory of mind","level":3,"score":0.3628000020980835},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.34950000047683716},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.34630000591278076},{"id":"https://openalex.org/C2778136018","wikidata":"https://www.wikidata.org/wiki/Q10350689","display_name":"Predictive power","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C18591518","wikidata":"https://www.wikidata.org/wiki/Q1920928","display_name":"Mentalization","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C2778571376","wikidata":"https://www.wikidata.org/wiki/Q1355821","display_name":"Frontier","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.2513999938964844},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.17310","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.17310","pdf_url":"https://arxiv.org/pdf/2610.17310","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:10.48550/arxiv.2610.17310","doi":"https://doi.org/10.48550/arxiv.2610.17310","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.17310","pdf_url":null,"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":"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:2610.17310","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.17310","pdf_url":"https://arxiv.org/pdf/2610.17310","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":[{"id":"https://openalex.org/F4320309321","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7221783101.pdf","grobid_xml":"https://content.openalex.org/works/W7221783101.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W2018800929","https://openalex.org/W2029771517","https://openalex.org/W2044171341","https://openalex.org/W2141538250","https://openalex.org/W2161308639","https://openalex.org/W3168867926","https://openalex.org/W4291001103","https://openalex.org/W4321277158","https://openalex.org/W4389520279","https://openalex.org/W4389521014","https://openalex.org/W4391631327","https://openalex.org/W4403863303","https://openalex.org/W4410251374","https://openalex.org/W4412889608","https://openalex.org/W4416036808","https://openalex.org/W6948407666","https://openalex.org/W7163997117","https://openalex.org/W7164396085","https://openalex.org/W7166797545","https://openalex.org/W7166865324","https://openalex.org/W7170091318","https://openalex.org/W7204584626"],"related_works":["https://openalex.org/W4411119625","https://openalex.org/W4414959212","https://openalex.org/W7204584626","https://openalex.org/W4414413469","https://openalex.org/W7160912755","https://openalex.org/W2529006407","https://openalex.org/W39387144","https://openalex.org/W1689555256","https://openalex.org/W7095766150","https://openalex.org/W7172426534"],"abstract_inverted_index":{"Language-model":[0],"agents":[1],"are":[2],"expected":[3],"to":[4,6,29,170],"adapt":[5],"others":[7],"whose":[8],"behavior":[9],"changes":[10],"through":[11,73],"interaction.":[12],"Yet":[13],"adaptation":[14],"may":[15],"rely":[16],"on":[17,151],"learned":[18],"behavioral":[19,86],"patterns":[20],"rather":[21],"than":[22,223],"theory":[23],"of":[24],"mind":[25],"(ToM):":[26],"the":[27,125,129,143,159],"ability":[28],"infer":[30,142],"others'":[31],"mental":[32],"states,":[33],"including":[34],"beliefs":[35,59],"and":[36,42,60,70,78,85,105,132,195,202,238,251],"intentions.":[37],"We":[38,108],"introduce":[39],"a":[40,180,229,246],"benchmark":[41],"diagnostic":[43],"framework":[44,247],"for":[45,228,248],"repeated":[46],"hide-and-seek":[47],"against":[48],"algorithmic":[49],"opponents":[50],"with":[51],"explicitly":[52],"defined":[53],"recursive":[54],"belief":[55,71,106,200,219,243],"updates.":[56],"Their":[57],"ground-truth":[58],"action":[61,68,113,239],"probabilities":[62,114],"let":[63],"us":[64],"distinguish":[65,235],"adaptive":[66],"play,":[67],"prediction,":[69],"tracking":[72],"live":[74],"interaction,":[75],"fixed-history":[76],"evaluation,":[77],"controlled":[79],"information":[80,220],"interventions.":[81],"With":[82],"structured":[83],"elicitation":[84],"supervised":[87],"fine-tuning":[88],"(SFT),":[89],"we":[90],"find":[91],"improved":[92,236],"play":[93,237],"in":[94,102,120,179],"several":[95],"tested":[96],"settings,":[97,134],"but":[98,135],"diagnostics":[99],"reveal":[100],"limitations":[101],"opponent":[103,112,144,188],"prediction":[104,240],"tracking.":[107],"test":[109],"whether":[110],"supervising":[111],"can":[115],"address":[116],"this":[117,148,167],"predictive":[118],"deficit":[119],"Qwen2.5-7B-Instruct.":[121],"Predictions":[122],"improve":[123,208],"when":[124,139],"model":[126],"is":[127,221],"told":[128],"opponent's":[130],"type":[131],"parameter":[133],"become":[136],"less":[137],"accurate":[138],"it":[140,176,225],"must":[141],"from":[145,186,210,241],"history":[146],"without":[147],"information.":[149],"Training":[150],"examples":[152],"that":[153,216],"also":[154,177,184],"omit":[155],"these":[156],"details":[157],"reduces":[158],"gap,":[160],"although":[161],"improvements":[162],"vary":[163],"across":[164],"opponents.":[165],"Is":[166],"limitation":[168],"specific":[169],"smaller":[171],"open-weight":[172],"models,":[173],"or":[174],"does":[175],"appear":[178],"frontier":[181,230],"model?":[182],"GPT-5.4":[183],"benefits":[185],"correct":[187],"beliefs:":[189],"supplying":[190],"them":[191],"improves":[192],"its":[193],"predictions":[194],"choices,":[196],"whereas":[197],"deeper":[198],"explicit":[199],"reports":[201],"self-generated":[203],"memory":[204],"do":[205],"not":[206],"consistently":[207],"forecasting":[209],"interaction":[211],"history.":[212],"This":[213],"contrast":[214],"suggests":[215],"using":[217],"useful":[218],"easier":[222],"inferring":[224],"autonomously,":[226],"even":[227],"model.":[231],"Together,":[232],"our":[233],"findings":[234],"reliable":[242],"tracking,":[244],"providing":[245],"evaluating":[249],"mentalizing":[250],"testing":[252],"targeted":[253],"improvements.":[254]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-15T00:00:00"}