{"id":"https://openalex.org/W7214729686","doi":"https://doi.org/10.48550/arxiv.2609.31874","title":"COUNTERMEM: World-Model Verified Counter-Factual Memory for Language Agents","display_name":"COUNTERMEM: World-Model Verified Counter-Factual Memory for Language Agents","publication_year":2026,"publication_date":"2026-09-25","ids":{"openalex":"https://openalex.org/W7214729686","doi":"https://doi.org/10.48550/arxiv.2609.31874"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.31874","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.31874","pdf_url":"https://arxiv.org/pdf/2609.31874","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/2609.31874","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135247611","display_name":"Hongji Pu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pu, Hongji","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101660252","display_name":"Ruixiang Tang","orcid":"https://orcid.org/0000-0002-5112-8771","observed_orcids":["https://orcid.org/0000-0002-5112-8771"]},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tang, Ruixiang","raw_affiliation_strings":["Department of Computer Science , Rutgers University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Rutgers University","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153410284","display_name":"Yongfeng Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Yongfeng","raw_affiliation_strings":["Department of Computer Science , Rutgers University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Rutgers University","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":1,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.8955000042915344,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.8955000042915344,"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":0.07699999958276749,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.004900000058114529,"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/agent-memory","display_name":"agent memory","score":0.6140000224113464},{"id":"https://openalex.org/keywords/world-models","display_name":"world models","score":0.6290000081062317},{"id":"https://openalex.org/keywords/language-agents","display_name":"language agents","score":0.6079999804496765},{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.6420000195503235},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.4909999966621399},{"id":"https://openalex.org/keywords/proof-verification","display_name":"proof verification","score":0.5609999895095825},{"id":"https://openalex.org/keywords/react","display_name":"React","score":0.5899999737739563},{"id":"https://openalex.org/keywords/reflexion","display_name":"reflexion","score":0.8209999799728394},{"id":"https://openalex.org/keywords/memory-reuse","display_name":"memory reuse","score":0.3149999976158142}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8058000206947327},{"id":"https://openalex.org/C2779795794","wikidata":"https://www.wikidata.org/wiki/Q7315343","display_name":"Reset (finance)","level":2,"score":0.75},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.667900025844574},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6373000144958496},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.6122999787330627},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.6022999882698059},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4952000081539154},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.421099990606308},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4104999899864197},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.40450000762939453},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3488999903202057},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.33559998869895935},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.301800012588501},{"id":"https://openalex.org/C159023740","wikidata":"https://www.wikidata.org/wiki/Q623276","display_name":"Deadlock","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C98184364","wikidata":"https://www.wikidata.org/wiki/Q1780131","display_name":"Argument (complex analysis)","level":2,"score":0.2621000111103058}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.31874","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.31874","pdf_url":"https://arxiv.org/pdf/2609.31874","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.2609.31874","doi":"https://doi.org/10.48550/arxiv.2609.31874","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.31874","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.31874","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.31874","pdf_url":"https://arxiv.org/pdf/2609.31874","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214729686.pdf","grobid_xml":"https://content.openalex.org/works/W7214729686.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2890431379","https://openalex.org/W3105943882","https://openalex.org/W3206707647","https://openalex.org/W4322616316","https://openalex.org/W4362661194","https://openalex.org/W4376562731","https://openalex.org/W4387636003","https://openalex.org/W4387835442","https://openalex.org/W4393160747","https://openalex.org/W4407759090","https://openalex.org/W7083815470","https://openalex.org/W7127444689"],"related_works":["https://openalex.org/W7215089407","https://openalex.org/W7215084445","https://openalex.org/W7163039299","https://openalex.org/W7214759132","https://openalex.org/W7172492227","https://openalex.org/W7126039966","https://openalex.org/W7221772872","https://openalex.org/W4415135147","https://openalex.org/W4387830586","https://openalex.org/W7213393592"],"abstract_inverted_index":{"Existing":[0],"agent":[1],"memory":[2,6,37,94,150,165],"frameworks":[3,29],"mainly":[4],"create":[5],"through":[7],"an":[8,65],"agent's":[9],"interaction":[10,156],"with":[11,128],"the":[12,32,48,74,111,129,159,210,235],"factual":[13],"world,":[14],"e.g.,":[15],"remembering":[16],"feedback":[17,49,56,62],"from":[18,105],"actions":[19],"taken":[20],"to":[21,151,241],"improve":[22],"performance":[23],"on":[24,176,191],"future":[25],"tasks.":[26,96],"However,":[27],"these":[28],"seldom":[30],"ask":[31],"\"what":[33],"if\"":[34],"question":[35],"during":[36,170],"construction:":[38],"what":[39],"if":[40],"a":[41,85,98,106,145,199],"different":[42],"action":[43],"had":[44],"been":[45],"taken,":[46],"would":[47],"have":[50],"changed,":[51],"and":[52,71,90,123,131,136,155,166,189],"how":[53],"could":[54],"this":[55,80],"become":[57],"useful":[58],"memory?":[59],"Obtaining":[60],"such":[61,118],"directly":[63],"in":[64],"active":[66],"environment":[67],"can":[68,72,244],"be":[69,249],"expensive":[70],"alter":[73],"state":[75,113],"needed":[76],"for":[77,88,138],"comparison.":[78],"In":[79,209],"work,":[81],"we":[82],"introduce":[83],"COUNTERMEM,":[84],"reinforcement-learning":[86],"framework":[87],"constructing":[89],"using":[91,114],"verified":[92,239],"counterfactual":[93],"across":[95,180,195,213],"After":[97],"failed":[99],"action,":[100],"COUNTERMEM":[101,175,185],"evaluates":[102],"local":[103],"alternatives":[104],"copy":[107],"or":[108,148,231],"reset":[109],"of":[110,201],"original":[112,130],"executable":[115],"world":[116],"models,":[117],"as":[119],"tests,":[120],"proof":[121],"checkers,":[122],"solvers.":[124],"It":[125],"stores":[126],"improvements":[127],"corrected":[132],"actions,":[133],"checked":[134],"outcomes,":[135],"conditions":[137],"reuse.":[139],"A":[140],"learned":[141],"memory-use":[142],"policy":[143,167],"selects":[144],"retrieved":[146],"record":[147],"skips":[149],"balance":[152],"task":[153],"success":[154],"cost,":[157],"while":[158,237],"base":[160],"LLM":[161],"remains":[162],"fixed.":[163],"Both":[164],"are":[168],"frozen":[169],"held-out":[171],"evaluation.":[172],"We":[173],"evaluate":[174],"12":[177,193],"benchmark":[178],"settings":[179],"six":[181,196],"domains.":[182],"With":[183],"gpt-oss-120b,":[184],"improves":[186],"both":[187],"ReAct":[188],"Reflexion":[190],"all":[192],"benchmarks":[194],"domains,":[197],"averaging":[198],"gain":[200],"12.6":[202],"percentage":[203],"points":[204],"over":[205],"their":[206],"unaugmented":[207],"versions.":[208],"four-domain":[211],"comparison":[212],"two":[214],"backbones,":[215],"task-run":[216],"tokens":[217],"decrease":[218],"by":[219],"7.7-42.0%,":[220],"excluding":[221],"offline":[222],"selector-training":[223],"costs.":[224],"Further":[225],"analyses":[226],"show":[227],"that":[228],"removing":[229],"verification":[230],"persistent":[232],"storage":[233],"weakens":[234],"gains,":[236],"applying":[238],"corrections":[240],"unsuitable":[242],"decisions":[243],"reverse":[245],"them.":[246],"Code":[247],"will":[248],"released":[250],"upon":[251],"acceptance.":[252]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-30T00:00:00"}