{"id":"https://openalex.org/W7163225337","doi":"https://doi.org/10.48550/arxiv.2606.00240","title":"MindZero: Learning Online Mental Reasoning With Zero Annotations","display_name":"MindZero: Learning Online Mental Reasoning With Zero Annotations","publication_year":2026,"publication_date":"2026-05-29","ids":{"openalex":"https://openalex.org/W7163225337","doi":"https://doi.org/10.48550/arxiv.2606.00240"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.00240","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00240","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.00240","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102606486","display_name":"Shunchi Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Shunchi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137626032","display_name":"Jin Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Jin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137687255","display_name":"Chuanyang Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Chuanyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137687199","display_name":"Yichao Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Yichao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101685928","display_name":"Zhining Zhang","orcid":"https://orcid.org/0000-0001-6357-1546"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zhining","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137629990","display_name":"Tianmin Shu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shu, Tianmin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.38769999146461487,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.38769999146461487,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.1273999959230423,"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":0.07280000299215317,"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/inference","display_name":"Inference","score":0.7160999774932861},{"id":"https://openalex.org/keywords/mental-model","display_name":"Mental model","score":0.6536999940872192},{"id":"https://openalex.org/keywords/mental-state","display_name":"Mental state","score":0.6392999887466431},{"id":"https://openalex.org/keywords/psychology-of-reasoning","display_name":"Psychology of reasoning","score":0.5938000082969666},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5527999997138977},{"id":"https://openalex.org/keywords/theory-of-mind","display_name":"Theory of mind","score":0.48570001125335693},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.46459999680519104},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4185999929904938},{"id":"https://openalex.org/keywords/model-based-reasoning","display_name":"Model-based reasoning","score":0.3504999876022339}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7160999774932861},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6970000267028809},{"id":"https://openalex.org/C2982912361","wikidata":"https://www.wikidata.org/wiki/Q1851867","display_name":"Mental model","level":2,"score":0.6536999940872192},{"id":"https://openalex.org/C2779429828","wikidata":"https://www.wikidata.org/wiki/Q3968640","display_name":"Mental state","level":2,"score":0.6392999887466431},{"id":"https://openalex.org/C183521366","wikidata":"https://www.wikidata.org/wiki/Q7256422","display_name":"Psychology of reasoning","level":4,"score":0.5938000082969666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5934000015258789},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5527999997138977},{"id":"https://openalex.org/C2779560602","wikidata":"https://www.wikidata.org/wiki/Q639219","display_name":"Theory of mind","level":3,"score":0.48570001125335693},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.46459999680519104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4320000112056732},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4185999929904938},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.3504999876022339},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3199999928474426},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.2994000017642975},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C4051589","wikidata":"https://www.wikidata.org/wiki/Q860959","display_name":"Mental image","level":3,"score":0.2784999907016754},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2732999920845032},{"id":"https://openalex.org/C2777500436","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Mental process","level":3,"score":0.26809999346733093},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.26350000500679016},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.2556999921798706},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C3746660","wikidata":"https://www.wikidata.org/wiki/Q1068763","display_name":"Rule of inference","level":2,"score":0.25270000100135803},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.00240","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00240","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.00240","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00240","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":false,"raw_source_name":null,"raw_type":"Preprint"},"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":{"Effective":[0],"real-world":[1,54],"assistance":[2,141],"requires":[3],"AI":[4,140],"agents":[5],"with":[6,30],"robust":[7,31,78],"Theory":[8],"of":[9,48,97],"Mind":[10],"(ToM):":[11],"inferring":[12],"human":[13],"mental":[14,50,80,90,117,137,189],"states":[15],"from":[16],"their":[17],"behavior.":[18],"Despite":[19],"recent":[20],"advances,":[21],"several":[22],"key":[23],"challenges":[24,59],"remain,":[25],"including":[26],"(1)":[27],"online":[28,79],"inference":[29],"uncertainty":[32],"updates":[33],"over":[34],"multiple":[35],"hypotheses;":[36],"(2)":[37],"efficient":[38,76],"reasoning":[39,125,138,190],"suitable":[40],"for":[41,75,88,115],"real-time":[42],"assistance;":[43],"and":[44,77,139,145,163,177,185],"(3)":[45],"the":[46,84,95,113],"lack":[47],"ground-truth":[49],"state":[51,91,118],"annotations":[52],"in":[53,143,182],"domains.":[55,147],"We":[56,130,148],"address":[57],"these":[58],"by":[60,101,165],"introducing":[61],"MindZero,":[62],"a":[63,102,196],"self-supervised":[64,197],"reinforcement":[65],"learning":[66],"framework":[67],"that":[68,93,150,188],"trains":[69],"multimodal":[70],"large":[71],"language":[72],"models":[73],"(MLLMs)":[74],"reasoning.":[81,108],"During":[82],"training,":[83,121],"model":[85],"is":[86],"rewarded":[87],"generating":[89],"hypotheses":[92],"maximize":[94],"likelihood":[96],"observed":[98],"actions":[99],"estimated":[100],"planner,":[103],"similar":[104],"to":[105],"model-based":[106,124,155,180],"ToM":[107,175],"This":[109],"method":[110],"thus":[111],"eliminates":[112],"need":[114],"explicit":[116],"annotations.":[119],"After":[120],"MindZero":[122,132,171],"internalizes":[123],"into":[126],"fast":[127],"single-pass":[128],"inference.":[129],"evaluate":[131],"against":[133],"baselines":[134],"across":[135],"challenging":[136],"tasks":[142],"gridworld":[144],"household":[146],"found":[149],"LLMs":[151],"alone":[152],"are":[153,160],"insufficient;":[154],"methods":[156,181],"improve":[157],"accuracy":[158,184],"but":[159],"slow,":[161],"costly,":[162],"limited":[164],"backbone":[166],"MLLM":[167],"capacity.":[168],"In":[169],"contrast,":[170],"enhances":[172],"MLLMs'":[173],"intrinsic":[174],"ability":[176],"significantly":[178],"outperforms":[179],"both":[183],"efficiency,":[186],"showing":[187],"can":[191],"be":[192],"effectively":[193],"learned":[194],"as":[195],"skill.":[198]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-03T00:00:00"}