{"id":"https://openalex.org/W7225465280","doi":"https://doi.org/10.5281/zenodo.24035633","title":"Beyond Idle Compliance: The Claim\u2013State Gap in Long-Horizon LLM Agents","display_name":"Beyond Idle Compliance: The Claim\u2013State Gap in Long-Horizon LLM Agents","publication_year":2026,"publication_date":"2026-11-07","ids":{"openalex":"https://openalex.org/W7225465280","doi":"https://doi.org/10.5281/zenodo.24035633"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24035633","doi":"https://doi.org/10.5281/zenodo.24035633","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24035633","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.24035633","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133610272","display_name":"Rog\u00e9rio Figurelli","orcid":"https://orcid.org/0009-0002-5726-1765","observed_orcids":["https://orcid.org/0009-0002-5726-1765"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Figurelli, Rog\u00e9rio","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0002-5726-1765","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5133610272"],"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.45089998841285706,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.45089998841285706,"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/T13904","display_name":"Artificial Intelligence Applications","score":0.10999999940395355,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.09730000048875809,"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/llm-based-agents","display_name":"LLM agents","score":0.8230000138282776},{"id":"https://openalex.org/keywords/long-horizon-agents","display_name":"long-horizon agents","score":0.7540000081062317},{"id":"https://openalex.org/keywords/agent-failure-modes","display_name":"agent failure modes","score":0.6859999895095825},{"id":"https://openalex.org/keywords/negative-control","display_name":"negative control","score":0.4440000057220459},{"id":"https://openalex.org/keywords/axiomatic-framework","display_name":"axiomatic framework","score":0.3930000066757202}],"concepts":[{"id":"https://openalex.org/C116222747","wikidata":"https://www.wikidata.org/wiki/Q220888","display_name":"Falsifiability","level":2,"score":0.704800009727478},{"id":"https://openalex.org/C2777179996","wikidata":"https://www.wikidata.org/wiki/Q911222","display_name":"Mistake","level":2,"score":0.5972999930381775},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5785999894142151},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.529699981212616},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.5069000124931335},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4839000105857849},{"id":"https://openalex.org/C167729594","wikidata":"https://www.wikidata.org/wiki/Q17736","display_name":"Axiom","level":2,"score":0.48159998655319214},{"id":"https://openalex.org/C144446859","wikidata":"https://www.wikidata.org/wiki/Q219164","display_name":"Zombie","level":2,"score":0.47920000553131104},{"id":"https://openalex.org/C146834321","wikidata":"https://www.wikidata.org/wiki/Q2979672","display_name":"Closure (psychology)","level":2,"score":0.4781000018119812},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.4269999861717224},{"id":"https://openalex.org/C2779043874","wikidata":"https://www.wikidata.org/wiki/Q189643","display_name":"Delusion","level":2,"score":0.4007999897003174},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.37959998846054077},{"id":"https://openalex.org/C71889745","wikidata":"https://www.wikidata.org/wiki/Q1783264","display_name":"Counterfactual conditional","level":3,"score":0.36309999227523804},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.35749998688697815},{"id":"https://openalex.org/C166052673","wikidata":"https://www.wikidata.org/wiki/Q83021","display_name":"Empirical evidence","level":2,"score":0.3537999987602234},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.3490000069141388},{"id":"https://openalex.org/C2776141515","wikidata":"https://www.wikidata.org/wiki/Q1274479","display_name":"Repetition (rhetorical device)","level":2,"score":0.34200000762939453},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.3393999934196472},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.334199994802475},{"id":"https://openalex.org/C190253527","wikidata":"https://www.wikidata.org/wiki/Q295354","display_name":"Law and economics","level":1,"score":0.3107999861240387},{"id":"https://openalex.org/C2777366796","wikidata":"https://www.wikidata.org/wiki/Q6017758","display_name":"Indeterminacy (philosophy)","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C2776127325","wikidata":"https://www.wikidata.org/wiki/Q1424662","display_name":"Omniscience","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2946999967098236},{"id":"https://openalex.org/C79897977","wikidata":"https://www.wikidata.org/wiki/Q5054568","display_name":"Causal chain","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C91317487","wikidata":"https://www.wikidata.org/wiki/Q1530412","display_name":"Simultaneity","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C174839445","wikidata":"https://www.wikidata.org/wiki/Q1134386","display_name":"Lock (firearm)","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C2776889888","wikidata":"https://www.wikidata.org/wiki/Q1135789","display_name":"Unintended consequences","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2842999994754791},{"id":"https://openalex.org/C7991579","wikidata":"https://www.wikidata.org/wiki/Q17955","display_name":"Criticism","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2702000141143799},{"id":"https://openalex.org/C49848784","wikidata":"https://www.wikidata.org/wiki/Q131714","display_name":"Archetype","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C162118730","wikidata":"https://www.wikidata.org/wiki/Q1128453","display_name":"Actuarial science","level":1,"score":0.26649999618530273},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25839999318122864}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24035633","doi":"https://doi.org/10.5281/zenodo.24035633","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24035633","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},{"id":"doi:10.5281/zenodo.24035634","doi":"https://doi.org/10.5281/zenodo.24035634","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24035634","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"doi:10.5281/zenodo.24035633","doi":"https://doi.org/10.5281/zenodo.24035633","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24035633","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7128493354","https://openalex.org/W7164201941","https://openalex.org/W7171633409","https://openalex.org/W7225452118","https://openalex.org/W7225017352","https://openalex.org/W7204079846","https://openalex.org/W7167691546","https://openalex.org/W7221772011","https://openalex.org/W7154478830","https://openalex.org/W7212074403"],"abstract_inverted_index":{"An":[0],"LLM":[1,155],"agent":[2,191],"may":[3],"continue":[4],"acting":[5],"without":[6,10],"progress,":[7],"announce":[8],"completion":[9,87],"a":[11,15,30,83,112,120,175],"verified":[12],"effect,":[13,73],"produce":[14],"technically":[16],"successful":[17,52,182],"but":[18],"unauthorized":[19],"outcome,":[20],"mistake":[21],"locally":[22],"completed":[23],"subtasks":[24],"for":[25,180],"global":[26],"closure,":[27],"or":[28,165],"preserve":[29],"success":[31],"report":[32],"after":[33],"its":[34],"evidentiary":[35],"basis":[36],"expires.":[37],"These":[38],"are":[39],"distinct":[40,168],"failure":[41,121],"conditions":[42],"even":[43],"when":[44],"fluent":[45],"narrative,":[46],"legitimate":[47,187],"tool":[48],"responses,":[49],"and":[50,79,92,95,109,127,144,157,186],"apparently":[51],"component":[53],"actions":[54],"coexist.":[55],"This":[56],"conceptual":[57],"paper":[58],"develops":[59],"an":[60,166],"axiomatic":[61],"claim\u2013state":[62],"account":[63],"derived":[64],"from":[65],"the":[66],"separation":[67],"of":[68,86,100,103,147],"operational":[69],"regimes:":[70],"intention,":[71],"invocation,":[72],"independent":[74,134],"observation,":[75],"admissibility,":[76],"authority,":[77],"composition,":[78],"time.":[80],"It":[81],"formalizes":[82],"three-valued":[84],"judgment":[85],"claims,":[88],"proves":[89],"bounded":[90],"non-entailment":[91],"indistinguishability":[93],"propositions,":[94],"derives":[96],"five":[97],"central":[98],"archetypes\u2014Loop":[99],"Death,":[101],"Delusion":[102],"Done,":[104,108],"Forbidden":[105],"Success,":[106],"Fractured":[107],"Zombie":[110],"Success\u2014within":[111],"broader":[113],"candidate":[114],"taxonomy.":[115],"Each":[116],"archetype":[117],"is":[118,174],"assigned":[119],"condition,":[122],"evidence":[123],"discriminator,":[124],"negative":[125],"control,":[126],"defeater.":[128],"A":[129],"prospective":[130,148],"research":[131,178],"protocol":[132],"specifies":[133],"state":[135],"oracles,":[136],"evidence-matched":[137],"conventional":[138],"baselines,":[139],"explicit":[140],"abstention,":[141],"temporal":[142],"adjudication,":[143],"preregistered":[145],"tests":[146],"prediction.":[149],"The":[150],"manuscript":[151],"reports":[152],"no":[153],"new":[154],"experiment":[156],"does":[158],"not":[159],"claim":[160],"empirical":[161],"prevalence,":[162],"causal":[163],"superiority,":[164],"ontologically":[167],"Large":[169],"Language":[170],"Field.":[171],"Its":[172],"contribution":[173],"falsifiable":[176],"boundary-based":[177],"program":[179],"separating":[181],"execution,":[183],"warranted":[184],"reporting,":[185],"closure":[188],"across":[189],"long-horizon":[190],"trajectories.":[192]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-11-08T00:00:00"}
