{"id":"https://openalex.org/W7225197182","doi":"https://doi.org/10.48550/arxiv.2611.03227","title":"What Structurally Breaks an Agent? Auditing Difficulty in Stateful Tool-Use Workflows","display_name":"What Structurally Breaks an Agent? Auditing Difficulty in Stateful Tool-Use Workflows","publication_year":2026,"publication_date":"2026-11-02","ids":{"openalex":"https://openalex.org/W7225197182","doi":"https://doi.org/10.48550/arxiv.2611.03227"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2611.03227","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.03227","pdf_url":"https://arxiv.org/pdf/2611.03227","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/2611.03227","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160346221","display_name":"Shereen Anand","orcid":"https://orcid.org/0009-0007-3496-1407","observed_orcids":["https://orcid.org/0009-0007-3496-1407"]},"institutions":[{"id":"https://openalex.org/I196608512","display_name":"PES University","ror":"https://ror.org/05m169e78","country_code":"IN","type":"education","lineage":["https://openalex.org/I196608512"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anand, Shereen","raw_affiliation_strings":["PES University India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PES University India","institution_ids":["https://openalex.org/I196608512"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160526059","display_name":"Ju 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, Ju","raw_affiliation_strings":["University College London United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London United Kingdom","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160459481","display_name":"Yali Du","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Du, Yali","raw_affiliation_strings":["King's College London United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King's College London United Kingdom","institution_ids":["https://openalex.org/I183935753"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":0.8169000148773193,"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":0.8169000148773193,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.040800001472234726,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/T13904","display_name":"Artificial Intelligence Applications","score":0.01889999955892563,"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-failure-modes","display_name":"agent failure modes","score":0.4000000059604645},{"id":"https://openalex.org/keywords/state-retention","display_name":"state retention","score":0.6439999938011169},{"id":"https://openalex.org/keywords/candidate-selection","display_name":"candidate selection","score":0.7099999785423279},{"id":"https://openalex.org/keywords/diagnostic-tools","display_name":"diagnostic tools","score":0.367000013589859},{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.5920000076293945}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7979000210762024},{"id":"https://openalex.org/C22927095","wikidata":"https://www.wikidata.org/wiki/Q1784206","display_name":"Stateful firewall","level":3,"score":0.6643999814987183},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.5206999778747559},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5151000022888184},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.4828000068664551},{"id":"https://openalex.org/C55282118","wikidata":"https://www.wikidata.org/wiki/Q252683","display_name":"Snapshot (computer storage)","level":2,"score":0.4634999930858612},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.42890000343322754},{"id":"https://openalex.org/C204495577","wikidata":"https://www.wikidata.org/wiki/Q1205349","display_name":"Callback","level":2,"score":0.42809998989105225},{"id":"https://openalex.org/C37279795","wikidata":"https://www.wikidata.org/wiki/Q2492305","display_name":"Consistency model","level":3,"score":0.3765000104904175},{"id":"https://openalex.org/C52723943","wikidata":"https://www.wikidata.org/wiki/Q1127410","display_name":"Serialization","level":2,"score":0.36149999499320984},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34630000591278076},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.33649998903274536},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3253999948501587},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28380000591278076},{"id":"https://openalex.org/C16311509","wikidata":"https://www.wikidata.org/wiki/Q4148050","display_name":"Dependency graph","level":3,"score":0.2822999954223633},{"id":"https://openalex.org/C2777489069","wikidata":"https://www.wikidata.org/wiki/Q1589822","display_name":"Ceiling (cloud)","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.26989999413490295},{"id":"https://openalex.org/C2777168461","wikidata":"https://www.wikidata.org/wiki/Q42196253","display_name":"Set operations","level":3,"score":0.26910001039505005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2621000111103058},{"id":"https://openalex.org/C150202949","wikidata":"https://www.wikidata.org/wiki/Q107602","display_name":"Pointer (user interface)","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.2538999915122986},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.25290000438690186}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2611.03227","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.03227","pdf_url":"https://arxiv.org/pdf/2611.03227","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.2611.03227","doi":"https://doi.org/10.48550/arxiv.2611.03227","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.03227","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:2611.03227","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.03227","pdf_url":"https://arxiv.org/pdf/2611.03227","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/W7225197182.pdf","grobid_xml":"https://content.openalex.org/works/W7225197182.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7203928100","https://openalex.org/W7156951040","https://openalex.org/W7223245266","https://openalex.org/W7204961840","https://openalex.org/W7222458645","https://openalex.org/W7128958835","https://openalex.org/W7214738365","https://openalex.org/W7161251449","https://openalex.org/W7224450232","https://openalex.org/W7214102314"],"abstract_inverted_index":{"An":[0],"aggregate":[1],"task":[2],"score":[3],"does":[4],"not":[5],"distinguish":[6],"failures":[7],"of":[8,39,60,153],"scheduling,":[9],"state":[10,28,99,137],"retention,":[11],"and":[12,30,57,69,81,106,110,120,150,168],"candidate":[13,25,104],"selection.":[14],"We":[15],"develop":[16],"a":[17,162,169],"small":[18,157],"executable":[19,145],"instrument":[20],"that":[21,47,115,135],"varies":[22],"dependency":[23],"depth,":[24],"count,":[26],"active":[27],"width,":[29],"access":[31],"to":[32],"current-state":[33],"snapshots":[34],"while":[35],"holding":[36],"the":[37,58,72,124],"number":[38,59],"required":[40],"operations":[41],"fixed.":[42],"Two":[43],"dependency-graph":[44],"families":[45],"show":[46],"increasing":[48],"depth":[49],"at":[50],"fixed":[51],"work":[52],"changes":[53],"both":[54],"scheduling":[55],"freedom":[56],"reachable":[61],"completion":[62],"states,":[63],"so":[64],"these":[65],"controls":[66],"are":[67],"coupled,":[68],"we":[70],"quantify":[71],"coupling.":[73],"The":[74,141],"primary":[75],"study":[76,160],"contains":[77],"49,152":[78],"generated":[79],"tasks":[80,114],"393,216":[82],"reference-controller":[83],"rollouts.":[84],"A":[85,156],"separately":[86],"frozen":[87],"follow-on":[88],"design":[89],"adds":[90],"295,936":[91],"rollouts":[92],"covering":[93],"retention":[94],"strategy,":[95],"snapshot":[96],"cadence,":[97],"hidden":[98],"resampling,":[100],"recovery,":[101],"query":[102],"locality,":[103],"indexing,":[105],"relabeling.":[107],"Residue":[108],"caches":[109],"precomputed":[111],"plans":[112],"solve":[113],"defeat":[116],"limited":[117],"raw-value":[118],"caches,":[119],"indexed":[121],"selection":[122],"removes":[123],"serial-scan":[125],"branching":[126],"deficit.":[127],"Hidden":[128],"resampling":[129],"imposes":[130],"an":[131,144,151],"exact":[132],"success":[133],"ceiling":[134],"additional":[136],"tracking":[138],"cannot":[139],"overcome.":[140],"contribution":[142],"is":[143,174],"diagnostic":[146],"instrument,":[147],"analytic":[148],"calibration,":[149],"audit":[152],"its":[154],"assumptions.":[155],"local":[158],"CPU":[159],"with":[161],"0.5B":[163],"model":[164],"completed":[165],"no":[166],"workflows,":[167],"16-episode":[170],"Copilot-routed":[171],"fractional":[172],"factorial":[173],"descriptive":[175],"only.":[176],"Neither":[177],"supports":[178],"general":[179],"capability":[180],"claims.":[181]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-11-04T00:00:00"}