{"id":"https://openalex.org/W4415004580","doi":"https://doi.org/10.1145/3725783.3764388","title":"Between Promise and Pain: The Reality of Automating Failure Analysis in Microservices with LLMs","display_name":"Between Promise and Pain: The Reality of Automating Failure Analysis in Microservices with LLMs","publication_year":2025,"publication_date":"2025-10-09","ids":{"openalex":"https://openalex.org/W4415004580","doi":"https://doi.org/10.1145/3725783.3764388"},"language":"en","primary_location":{"id":"doi:10.1145/3725783.3764388","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725783.3764388","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 16th ACM SIGOPS Asia-Pacific Workshop on Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3725783.3764388","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044396470","display_name":"Alessandro Cornacchia","orcid":"https://orcid.org/0000-0002-4734-3321"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":true,"raw_author_name":"Alessandro Cornacchia","raw_affiliation_strings":["KAUST, Thuwal, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"KAUST, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119925350","display_name":"Iliyas Alabdulaal","orcid":null},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Iliyas Alabdulaal","raw_affiliation_strings":["KAUST, Thuwal, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"KAUST, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119925351","display_name":"Ibraheem Saghier","orcid":null},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Ibraheem Saghier","raw_affiliation_strings":["KAUST, Thuwal, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"KAUST, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119925352","display_name":"Albaraa Mirdad","orcid":null},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Albaraa Mirdad","raw_affiliation_strings":["KAUST, Thuwal, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"KAUST, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119925353","display_name":"Omar Fayoumi","orcid":null},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Omar Fayoumi","raw_affiliation_strings":["KAUST, Thuwal, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"KAUST, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042255975","display_name":"Marco Canini","orcid":"https://orcid.org/0000-0002-5051-4283"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Marco Canini","raw_affiliation_strings":["KAUST, Thuwal, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"KAUST, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5044396470"],"corresponding_institution_ids":["https://openalex.org/I71920554"],"apc_list":null,"apc_paid":null,"fwci":1.4888,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87625822,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"155","last_page":"167"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":1.0,"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":1.0,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9940000176429749,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9932000041007996,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hallucinating","display_name":"Hallucinating","score":0.6474999785423279},{"id":"https://openalex.org/keywords/microservices","display_name":"Microservices","score":0.5212000012397766},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.4763000011444092},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.46810001134872437},{"id":"https://openalex.org/keywords/root-cause-analysis","display_name":"Root cause analysis","score":0.45399999618530273},{"id":"https://openalex.org/keywords/root-cause","display_name":"Root cause","score":0.4260999858379364},{"id":"https://openalex.org/keywords/root","display_name":"Root (linguistics)","score":0.3962000012397766}],"concepts":[{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.6474999785423279},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5390999913215637},{"id":"https://openalex.org/C2778505942","wikidata":"https://www.wikidata.org/wiki/Q18344624","display_name":"Microservices","level":3,"score":0.5212000012397766},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.4832000136375427},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.4763000011444092},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.46810001134872437},{"id":"https://openalex.org/C130963320","wikidata":"https://www.wikidata.org/wiki/Q1401207","display_name":"Root cause analysis","level":2,"score":0.45399999618530273},{"id":"https://openalex.org/C84945661","wikidata":"https://www.wikidata.org/wiki/Q7366567","display_name":"Root cause","level":2,"score":0.4260999858379364},{"id":"https://openalex.org/C171078966","wikidata":"https://www.wikidata.org/wiki/Q111029","display_name":"Root (linguistics)","level":2,"score":0.3962000012397766},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.39419999718666077},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3878999948501587},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.35989999771118164},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.30390000343322754},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.29409998655319214},{"id":"https://openalex.org/C165136773","wikidata":"https://www.wikidata.org/wiki/Q1363179","display_name":"Single point of failure","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.25519999861717224},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3725783.3764388","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725783.3764388","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 16th ACM SIGOPS Asia-Pacific Workshop on Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3725783.3764388","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725783.3764388","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 16th ACM SIGOPS Asia-Pacific Workshop on Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1537198022","https://openalex.org/W1982786553","https://openalex.org/W2178225550","https://openalex.org/W2930500175","https://openalex.org/W2966971704","https://openalex.org/W2999561215","https://openalex.org/W3198081460","https://openalex.org/W3217305727","https://openalex.org/W4225080085","https://openalex.org/W4284688717","https://openalex.org/W4385621806","https://openalex.org/W4387321636","https://openalex.org/W4389158500","https://openalex.org/W4394745158","https://openalex.org/W4394946189","https://openalex.org/W4400484653","https://openalex.org/W4400484838","https://openalex.org/W4401560363","https://openalex.org/W4403724173","https://openalex.org/W4410553099","https://openalex.org/W4413943474"],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"are":[4],"increasingly":[5],"explored":[6],"as":[7],"general-purpose":[8],"assistants":[9],"for":[10,131],"infrastructure":[11],"operations,":[12],"helping":[13],"automate":[14],"tasks":[15],"like":[16],"querying":[17],"data,":[18],"analyzing":[19],"logs,":[20],"and":[21,32,53,61,69,98,109,120,126,134],"suggesting":[22],"fixes.":[23],"In":[24],"this":[25,140],"paper,":[26],"we":[27],"consider":[28],"the":[29,56,73,118,121],"more":[30,132],"general":[31],"ambitious":[33],"problem":[34],"of":[35,88,112,123,137],"fully":[36],"automating":[37],"root":[38],"cause":[39],"analysis":[40],"(RCA)":[41],"in":[42,139],"microservice":[43],"systems,":[44],"where":[45],"LLMs":[46,138],"must":[47],"collect":[48],"information,":[49],"reason":[50],"about":[51],"it,":[52],"interact":[54],"with":[55],"environment":[57],"to":[58,128],"detect,":[59],"localize":[60],"resolve":[62],"issues.":[63],"Anecdotal":[64],"evidence":[65],"offers":[66],"useful":[67],"insights":[68],"partial":[70],"solutions,":[71],"but":[72],"broader":[74],"challenge":[75],"remains":[76],"unresolved.":[77],"We":[78,91],"systematically":[79],"evaluate":[80],"multiple":[81],"LLM":[82],"agent":[83],"architectures":[84],"across":[85],"a":[86],"range":[87],"incident":[89],"scenarios.":[90],"study":[92],"how":[93],"different":[94],"tool-augmented":[95],"agents":[96],"perform,":[97],"shed":[99],"light":[100],"on":[101],"common":[102],"failure":[103],"modes,":[104],"including":[105],"hallucinated":[106],"reasoning":[107],"paths":[108],"inefficient":[110],"use":[111,136],"context.":[113],"Our":[114],"findings":[115],"reveal":[116],"both":[117],"promise":[119],"limitations":[122],"current":[124],"approaches,":[125],"point":[127],"concrete":[129],"directions":[130],"robust":[133],"effective":[135],"domain.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
