{"id":"https://openalex.org/W7127124003","doi":"https://doi.org/10.1145/3793655.3793732","title":"Stalled, Biased, and Confused: Uncovering Reasoning Failures in LLMs for Cloud-Based Root Cause Analysis","display_name":"Stalled, Biased, and Confused: Uncovering Reasoning Failures in LLMs for Cloud-Based Root Cause Analysis","publication_year":2026,"publication_date":"2026-04-12","ids":{"openalex":"https://openalex.org/W7127124003","doi":"https://doi.org/10.1145/3793655.3793732"},"language":null,"primary_location":{"id":"doi:10.1145/3793655.3793732","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3793655.3793732","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 IEEE/ACM Third International Conference on AI Foundation Models and Software Engineering","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3793655.3793732","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116142563","display_name":"Evelien Riddell","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Evelien Riddell","raw_affiliation_strings":["University of Waterloo, Waterloo, Ontario, Canada"],"raw_orcid":"https://orcid.org/0000-0003-0844-8910","affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, Ontario, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124812327","display_name":"James Riddell","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"James Riddell","raw_affiliation_strings":["University of Waterloo, Waterloo, Ontario, Canada"],"raw_orcid":"https://orcid.org/0009-0007-3261-5412","affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, Ontario, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103062194","display_name":"Gengyi Sun","orcid":"https://orcid.org/0009-0009-6143-9862"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Gengyi Sun","raw_affiliation_strings":["University of Waterloo, Waterloo, Ontario, Canada"],"raw_orcid":"https://orcid.org/0009-0009-6143-9862","affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, Ontario, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020880402","display_name":"Micha\u0142 Antkiewicz","orcid":"https://orcid.org/0000-0002-6249-4507"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Micha\u0142 Antkiewicz","raw_affiliation_strings":["University of Waterloo, Waterloo, Ontario, Canada"],"raw_orcid":"https://orcid.org/0000-0003-4947-7136","affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, Ontario, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124803120","display_name":"Krzysztof Czarnecki","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Krzysztof Czarnecki","raw_affiliation_strings":["University of Waterloo, Waterloo, Ontario, Canada"],"raw_orcid":"https://orcid.org/0000-0003-1642-1101","affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, Ontario, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I151746483"],"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":"172","last_page":"183"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9490000009536743,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12127","display_name":"Software System Performance and Reliability","score":0.9490000009536743,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10260","display_name":"Software Engineering Research","score":0.01140000019222498,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.004699999932199717,"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/workflow","display_name":"Workflow","score":0.6883000135421753},{"id":"https://openalex.org/keywords/root-cause-analysis","display_name":"Root cause analysis","score":0.5957000255584717},{"id":"https://openalex.org/keywords/root-cause","display_name":"Root cause","score":0.5841000080108643},{"id":"https://openalex.org/keywords/interdependence","display_name":"Interdependence","score":0.49790000915527344},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.4609000086784363},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.42640000581741333},{"id":"https://openalex.org/keywords/reasoning-system","display_name":"Reasoning system","score":0.4147000014781952},{"id":"https://openalex.org/keywords/automated-reasoning","display_name":"Automated reasoning","score":0.3490999937057495},{"id":"https://openalex.org/keywords/fault-tree-analysis","display_name":"Fault tree analysis","score":0.3434000015258789}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6883000135421753},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5967000126838684},{"id":"https://openalex.org/C130963320","wikidata":"https://www.wikidata.org/wiki/Q1401207","display_name":"Root cause analysis","level":2,"score":0.5957000255584717},{"id":"https://openalex.org/C84945661","wikidata":"https://www.wikidata.org/wiki/Q7366567","display_name":"Root cause","level":2,"score":0.5841000080108643},{"id":"https://openalex.org/C185874996","wikidata":"https://www.wikidata.org/wiki/Q269699","display_name":"Interdependence","level":2,"score":0.49790000915527344},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.4609000086784363},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.42640000581741333},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.4147000014781952},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3598000109195709},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.3490999937057495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3479999899864197},{"id":"https://openalex.org/C107094494","wikidata":"https://www.wikidata.org/wiki/Q428453","display_name":"Fault tree analysis","level":2,"score":0.3434000015258789},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3346000015735626},{"id":"https://openalex.org/C171078966","wikidata":"https://www.wikidata.org/wiki/Q111029","display_name":"Root (linguistics)","level":2,"score":0.33000001311302185},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.325300008058548},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.32120001316070557},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3109999895095825},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.2989000082015991},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2928999960422516},{"id":"https://openalex.org/C2776088982","wikidata":"https://www.wikidata.org/wiki/Q841402","display_name":"Silver bullet","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.2678000032901764},{"id":"https://openalex.org/C166052673","wikidata":"https://www.wikidata.org/wiki/Q83021","display_name":"Empirical evidence","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C106436119","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assurance","level":3,"score":0.25839999318122864},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2547999918460846},{"id":"https://openalex.org/C175551986","wikidata":"https://www.wikidata.org/wiki/Q47089","display_name":"Fault (geology)","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3793655.3793732","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3793655.3793732","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 IEEE/ACM Third International Conference on AI Foundation Models and Software Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2601.22208","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.22208","pdf_url":"https://arxiv.org/pdf/2601.22208","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3793655.3793732","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3793655.3793732","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 IEEE/ACM Third International Conference on AI Foundation Models and Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7296364903450012}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Root":[0],"cause":[1],"analysis":[2],"(RCA)":[3],"is":[4],"essential":[5],"for":[6,32,62,202],"diagnosing":[7],"failures":[8,100,197,226],"within":[9],"complex":[10,92],"software":[11],"systems":[12,26],"to":[13,54,219,244],"ensure":[14],"system":[15,250],"reliability.":[16],"The":[17],"highly":[18],"distributed":[19],"and":[20,70,147,149,159,180,198,212,223,236,240],"interdependent":[21],"nature":[22],"of":[23,68,172,183,192],"modern":[24],"cloud-based":[25],"often":[27],"complicates":[28],"RCA":[29,63,195],"efforts,":[30],"particularly":[31],"multi-hop":[33,215],"fault":[34],"propagation,":[35],"where":[36,207],"symptoms":[37],"appear":[38],"far":[39],"from":[40,102,106],"their":[41,59],"true":[42],"causes.":[43],"Recent":[44],"advancements":[45],"in":[46,214],"Large":[47],"Language":[48],"Models":[49],"(LLMs)":[50],"present":[51,111],"new":[52],"opportunities":[53],"enhance":[55],"automated":[56],"RCA.":[57],"However,":[58],"practical":[60],"value":[61],"depends":[64],"on":[65,75,81,153,248],"the":[66,130,181],"fidelity":[67],"reasoning":[69,90,103,120,185,196,225],"decision-making.":[71],"Existing":[72],"work":[73,247],"relies":[74],"historical":[76],"incident":[77],"corpora,":[78],"operates":[79],"directly":[80],"high-volume":[82],"telemetry":[83],"beyond":[84],"current":[85,208],"LLM":[86,131],"capacity,":[87],"or":[88,105],"embeds":[89],"inside":[91],"multi-agent":[93],"pipelines":[94],"--":[95],"conditions":[96],"that":[97,116,128,227],"obscure":[98],"whether":[99],"arise":[101],"itself":[104],"peripheral":[107],"design":[108,123],"choices.":[109],"We":[110,122,138,175,187],"a":[112,124,134,150,189,241],"focused":[113],"empirical":[114,238],"evaluation":[115],"isolates":[117],"an":[118,200],"LLM's":[119],"behavior.":[121],"controlled":[125],"experimental":[126,136],"framework":[127],"foregrounds":[129],"by":[132],"using":[133],"simplified":[135],"setting.":[137],"evaluate":[139],"six":[140],"LLMs":[141,210],"under":[142],"two":[143,154],"agentic":[144],"workflows":[145],"(ReAct":[146],"Plan-and-Execute)":[148],"non-agentic":[151],"baseline":[152],"real-world":[155],"case":[156],"studies":[157],"(GAIA":[158],"OpenRCA).":[160],"In":[161],"total,":[162],"we":[163],"executed":[164],"48,000":[165],"simulated":[166],"failure":[167,242],"scenarios,":[168],"totaling":[169],"228":[170],"days":[171],"execution":[173],"time.":[174],"measure":[176],"both":[177],"root-cause":[178],"accuracy":[179],"quality":[182],"intermediate":[184],"traces.":[186],"produce":[188],"labeled":[190],"taxonomy":[191,243],"16":[193],"common":[194],"use":[199],"LLM-as-a-Judge":[201],"annotation.":[203],"Our":[204],"results":[205,239],"clarify":[206],"open-source":[209],"succeed":[211],"fail":[213],"RCA,":[216],"quantify":[217],"sensitivity":[218],"input":[220],"data":[221],"modalities,":[222],"identify":[224],"predict":[228],"final":[229],"correctness.":[230],"Together,":[231],"these":[232],"contributions":[233],"provide":[234],"transparent":[235],"reproducible":[237],"guide":[245],"future":[246],"reasoning-driven":[249],"diagnosis.":[251]},"counts_by_year":[],"updated_date":"2026-07-22T06:00:27.337203","created_date":"2026-02-03T00:00:00"}