{"id":"https://openalex.org/W7224911649","doi":"https://doi.org/10.48550/arxiv.2610.40227","title":"EpiAgent: Epistemic Self-Play for LLM Agents","display_name":"EpiAgent: Epistemic Self-Play for LLM Agents","publication_year":2026,"publication_date":"2026-10-29","ids":{"openalex":"https://openalex.org/W7224911649","doi":"https://doi.org/10.48550/arxiv.2610.40227"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.40227","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.40227","pdf_url":"https://arxiv.org/pdf/2610.40227","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.40227","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100594817","display_name":"Xuanfa Jin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I9796191","display_name":"University College of Applied Science","ror":"https://ror.org/00f72x493","country_code":"PS","type":"education","lineage":["https://openalex.org/I9796191"]}],"countries":["CN","PS"],"is_corresponding":false,"raw_author_name":"Jin, Xuanfa","raw_affiliation_strings":["Institute of Automation , Chinese Academy of Sciences","School of Artificial Intelligence , UCAS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Artificial Intelligence , UCAS","institution_ids":["https://openalex.org/I4210165038","https://openalex.org/I9796191"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160206127","display_name":"Xinyu Cui","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I9796191","display_name":"University College of Applied Science","ror":"https://ror.org/00f72x493","country_code":"PS","type":"education","lineage":["https://openalex.org/I9796191"]}],"countries":["CN","PS"],"is_corresponding":false,"raw_author_name":"Cui, Xinyu","raw_affiliation_strings":["Institute of Automation , Chinese Academy of Sciences","School of Artificial Intelligence , UCAS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Artificial Intelligence , UCAS","institution_ids":["https://openalex.org/I4210165038","https://openalex.org/I9796191"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124958797","display_name":"Zhijian Ma","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I9796191","display_name":"University College of Applied Science","ror":"https://ror.org/00f72x493","country_code":"PS","type":"education","lineage":["https://openalex.org/I9796191"]}],"countries":["CN","PS"],"is_corresponding":false,"raw_author_name":"Ma, Zhijian","raw_affiliation_strings":["Institute of Automation , Chinese Academy of Sciences","School of Artificial Intelligence , UCAS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Artificial Intelligence , UCAS","institution_ids":["https://openalex.org/I4210165038","https://openalex.org/I9796191"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160164852","display_name":"Xue Yan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I9796191","display_name":"University College of Applied Science","ror":"https://ror.org/00f72x493","country_code":"PS","type":"education","lineage":["https://openalex.org/I9796191"]}],"countries":["CN","PS"],"is_corresponding":false,"raw_author_name":"Yan, Xue","raw_affiliation_strings":["Institute of Automation , Chinese Academy of Sciences","School of Artificial Intelligence , UCAS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Artificial Intelligence , UCAS","institution_ids":["https://openalex.org/I4210165038","https://openalex.org/I9796191"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160185504","display_name":"Jian Zhao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Jian","raw_affiliation_strings":["Zhongguancun Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhongguancun Academy","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160155490","display_name":"Haifeng Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I9796191","display_name":"University College of Applied Science","ror":"https://ror.org/00f72x493","country_code":"PS","type":"education","lineage":["https://openalex.org/I9796191"]}],"countries":["CN","PS"],"is_corresponding":false,"raw_author_name":"Zhang, Haifeng","raw_affiliation_strings":["Institute of Automation , Chinese Academy of Sciences","School of Artificial Intelligence , UCAS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Artificial Intelligence , UCAS","institution_ids":["https://openalex.org/I4210165038","https://openalex.org/I9796191"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160157475","display_name":"Jun Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wang, Jun","raw_affiliation_strings":["AI Centre , Department of Computer Science , UCL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Centre , Department of Computer Science , UCL","institution_ids":["https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"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/T11031","display_name":"Game Theory and Applications","score":0.36399999260902405,"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"}},"topics":[{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.36399999260902405,"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"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.2223999947309494,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.13850000500679016,"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/epistemic-game-theory","display_name":"epistemic game theory","score":0.8700000047683716},{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.8429999947547913},{"id":"https://openalex.org/keywords/self-play","display_name":"self-play","score":0.6840000152587891},{"id":"https://openalex.org/keywords/belief-updating","display_name":"belief updating","score":0.8510000109672546},{"id":"https://openalex.org/keywords/epistemic-states","display_name":"epistemic states","score":0.7730000019073486},{"id":"https://openalex.org/keywords/multi-agent-interaction","display_name":"multi-agent interaction","score":0.6610000133514404},{"id":"https://openalex.org/keywords/incomplete-information","display_name":"incomplete information","score":0.8130000233650208},{"id":"https://openalex.org/keywords/bi-level-optimization","display_name":"bi-level optimization","score":0.8939999938011169},{"id":"https://openalex.org/keywords/intrinsic-rewards","display_name":"intrinsic rewards","score":0.675000011920929},{"id":"https://openalex.org/keywords/action-planning","display_name":"action planning","score":0.6840000152587891},{"id":"https://openalex.org/keywords/competitive-games","display_name":"competitive games","score":0.3529999852180481},{"id":"https://openalex.org/keywords/mixed-games","display_name":"mixed games","score":0.492000013589859}],"concepts":[{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.6406999826431274},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5909000039100647},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5382999777793884},{"id":"https://openalex.org/C107247716","wikidata":"https://www.wikidata.org/wiki/Q1347436","display_name":"Epistemic modal logic","level":4,"score":0.48590001463890076},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.4205000102519989},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.4122999906539917},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4106999933719635},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.4068000018596649},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36970001459121704},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.36489999294281006},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.35359999537467957},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.30889999866485596},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3000999987125397},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2558000087738037},{"id":"https://openalex.org/C166052673","wikidata":"https://www.wikidata.org/wiki/Q83021","display_name":"Empirical evidence","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.40227","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.40227","pdf_url":"https://arxiv.org/pdf/2610.40227","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.2610.40227","doi":"https://doi.org/10.48550/arxiv.2610.40227","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.40227","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:2610.40227","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.40227","pdf_url":"https://arxiv.org/pdf/2610.40227","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":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224911649.pdf","grobid_xml":"https://content.openalex.org/works/W7224911649.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7117292883","https://openalex.org/W7166718851","https://openalex.org/W4414630897","https://openalex.org/W7126203083","https://openalex.org/W4415879979","https://openalex.org/W7214303602","https://openalex.org/W2760546516","https://openalex.org/W7164812943","https://openalex.org/W4387914238","https://openalex.org/W29597899"],"abstract_inverted_index":{"Epistemic":[0,98,130],"game":[1],"theory":[2],"explains":[3],"an":[4,31,60,82,132,143,202],"agent's":[5,78,90],"strategic":[6],"behavior":[7],"via":[8],"the":[9,22,77,89,115,137,176,188,199],"beliefs":[10,18,39,67,75,103,152,192],"it":[11],"holds":[12],"about":[13],"others":[14],"and":[15,36,72,107,161,170,187],"how":[16,149],"these":[17,74,102],"are":[19],"updated":[20,116],"as":[21,123],"interactions":[23],"unfold.":[24],"Modern":[25],"LLM-based":[26,57],"agents,":[27],"however,":[28],"often":[29],"lack":[30],"explicit":[32],"mechanism":[33],"for":[34,85,207],"learning":[35],"updating":[37],"such":[38],"to":[40,147,193],"guide":[41],"decisions":[42],"under":[43],"incomplete":[44],"information.":[45],"To":[46],"bridge":[47],"this":[48],"gap,":[49],"we":[50,128],"propose":[51],"EpiAgent,":[52],"a":[53,124],"framework":[54],"that":[55,134,165],"equips":[56],"agents":[58],"with":[59,76],"explicit,":[61,203],"learnable":[62,204],"epistemic":[63,83,117,180,205],"layer,":[64],"which":[65,100,110],"maintains":[66],"over":[68],"others'":[69],"private":[70],"information":[71,80],"combines":[73],"available":[79],"into":[81,94],"state":[84],"action":[86,194],"selection.":[87],"Concretely,":[88],"policy":[91],"is":[92],"decomposed":[93],"two":[95,138],"coupled":[96],"stages:":[97],"Update,":[99],"updates":[101],"from":[104],"interaction":[105],"histories,":[106],"Action":[108],"Planning,":[109],"selects":[111],"actions":[112],"conditioned":[113],"on":[114],"state.":[118],"By":[119],"formulating":[120],"their":[121],"dependency":[122],"bi-level":[125],"optimization":[126],"problem,":[127],"introduce":[129],"Self-Play,":[131],"algorithm":[133],"alternately":[135],"optimizes":[136],"stages":[139],"through":[140],"self-play,":[141],"utilizing":[142],"intrinsic":[144],"prediction":[145],"reward":[146],"evaluate":[148],"well":[150],"inferred":[151],"predict":[153],"subsequent":[154],"observations.":[155],"Empirical":[156],"results":[157,197],"across":[158],"both":[159],"mixed":[160],"competitive":[162],"scenarios":[163],"show":[164],"EpiAgent":[166],"consistently":[167],"outperforms":[168],"prompting-based":[169],"RL-based":[171],"baselines.":[172],"Further":[173],"analyses":[174],"reveal":[175],"benefits":[177],"of":[178,190,201],"dedicated":[179],"training,":[181],"improvements":[182],"in":[183],"belief":[184],"inference":[185],"accuracy,":[186],"contribution":[189],"learned":[191],"planning.":[195],"These":[196],"demonstrate":[198],"value":[200],"layer":[206],"effective":[208],"multi-agent":[209],"interactions.":[210]},"counts_by_year":[],"updated_date":"2026-11-02T09:45:03.842371","created_date":"2026-10-31T00:00:00"}