{"id":"https://openalex.org/W7168044587","doi":"https://doi.org/10.1145/3786583.3786852","title":"When LLMs Listen to Experts: Accurate Failure Diagnosis in Operating Systems","display_name":"When LLMs Listen to Experts: Accurate Failure Diagnosis in Operating Systems","publication_year":2026,"publication_date":"2026-04-12","ids":{"openalex":"https://openalex.org/W7168044587","doi":"https://doi.org/10.1145/3786583.3786852"},"language":null,"primary_location":{"id":"doi:10.1145/3786583.3786852","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786583.3786852","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 IEEE/ACM 48th International Conference on Software Engineering: Software Engineering in Practice","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3786583.3786852","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103286616","display_name":"Y. Zhao","orcid":"https://orcid.org/0009-0005-6603-3539"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongxin Zhao","raw_affiliation_strings":["Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0005-6603-3539","affiliations":[{"raw_affiliation_string":"Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072210083","display_name":"Shenglin Zhang","orcid":"https://orcid.org/0000-0003-0330-0028"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shenglin Zhang","raw_affiliation_strings":["Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0003-0330-0028","affiliations":[{"raw_affiliation_string":"Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140467368","display_name":"Yuxin Sun","orcid":"https://orcid.org/0009-0009-9242-8699"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxin Sun","raw_affiliation_strings":["Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0009-9242-8699","affiliations":[{"raw_affiliation_string":"Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021347584","display_name":"Wenwei Gu","orcid":"https://orcid.org/0000-0003-1096-2732"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenwei Gu","raw_affiliation_strings":["Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0003-1096-2732","affiliations":[{"raw_affiliation_string":"Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027731066","display_name":"Yongqian Sun","orcid":"https://orcid.org/0000-0003-0266-7899"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongqian Sun","raw_affiliation_strings":["Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0003-0266-7899","affiliations":[{"raw_affiliation_string":"Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140466981","display_name":"Luping Wang","orcid":"https://orcid.org/0009-0000-1187-0202"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luping Wang","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-1187-0202","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140470716","display_name":"Li Shi","orcid":"https://orcid.org/0009-0008-0609-6038"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Shi","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0008-0609-6038","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140465605","display_name":"Cheng Huang","orcid":"https://orcid.org/0009-0006-1313-4464"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Huang","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0006-1313-4464","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073989304","display_name":"Guodong Yang","orcid":"https://orcid.org/0000-0003-1908-071X"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guodong Yang","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1908-071X","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100426765","display_name":"Liping Zhang","orcid":"https://orcid.org/0000-0003-2334-3471"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liping Zhang","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2334-3471","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046419834","display_name":"Dan Pei","orcid":"https://orcid.org/0000-0002-5113-838X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Pei","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5113-838X","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"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":"46","last_page":"57"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.7465999722480774,"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":0.7465999722480774,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.0625,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.04050000011920929,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/troubleshooting","display_name":"Troubleshooting","score":0.8992999792098999},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5601000189781189},{"id":"https://openalex.org/keywords/readability","display_name":"Readability","score":0.5418999791145325},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5357999801635742},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.52920001745224},{"id":"https://openalex.org/keywords/failure-mode-and-effects-analysis","display_name":"Failure mode and effects analysis","score":0.46470001339912415},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.3935000002384186},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.38100001215934753}],"concepts":[{"id":"https://openalex.org/C147494362","wikidata":"https://www.wikidata.org/wiki/Q2078905","display_name":"Troubleshooting","level":2,"score":0.8992999792098999},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.67330002784729},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.5662999749183655},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5601000189781189},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.5418999791145325},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5357999801635742},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.52920001745224},{"id":"https://openalex.org/C66283442","wikidata":"https://www.wikidata.org/wiki/Q1389268","display_name":"Failure mode and effects analysis","level":2,"score":0.46470001339912415},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4198000133037567},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.41179999709129333},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3935000002384186},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.38100001215934753},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3668999969959259},{"id":"https://openalex.org/C160713754","wikidata":"https://www.wikidata.org/wiki/Q1389965","display_name":"Maintainability","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.2818000018596649},{"id":"https://openalex.org/C2778974597","wikidata":"https://www.wikidata.org/wiki/Q702761","display_name":"Standard operating procedure","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.27649998664855957},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C163164238","wikidata":"https://www.wikidata.org/wiki/Q2737027","display_name":"Failure rate","level":2,"score":0.2597000002861023}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3786583.3786852","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786583.3786852","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 IEEE/ACM 48th International Conference on Software Engineering: Software Engineering in Practice","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3786583.3786852","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786583.3786852","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 IEEE/ACM 48th International Conference on Software Engineering: Software Engineering in Practice","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.6473423838615417}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W2296719434","https://openalex.org/W2337381441","https://openalex.org/W2401686019","https://openalex.org/W2583874385","https://openalex.org/W2754665629","https://openalex.org/W2793353921","https://openalex.org/W2958754741","https://openalex.org/W2962715466","https://openalex.org/W2966971704","https://openalex.org/W2971315908","https://openalex.org/W3083560262","https://openalex.org/W3086623952","https://openalex.org/W3097305689","https://openalex.org/W3155331679","https://openalex.org/W3155567600","https://openalex.org/W3183619936","https://openalex.org/W3194035167","https://openalex.org/W3195057108","https://openalex.org/W4211023551","https://openalex.org/W4290927880","https://openalex.org/W4382203537","https://openalex.org/W4383890187","https://openalex.org/W4384302784","https://openalex.org/W4384345623","https://openalex.org/W4389158453","https://openalex.org/W4392736029","https://openalex.org/W4394745212","https://openalex.org/W4394769528","https://openalex.org/W4394946189","https://openalex.org/W4398239377","https://openalex.org/W4400484653","https://openalex.org/W4400484740","https://openalex.org/W4400484838","https://openalex.org/W4400531953","https://openalex.org/W4400582623","https://openalex.org/W4402516174","https://openalex.org/W4403537005","https://openalex.org/W4403582420","https://openalex.org/W4404782032","https://openalex.org/W4404953107","https://openalex.org/W4405561262","https://openalex.org/W4405778637","https://openalex.org/W4408355202","https://openalex.org/W4410636386","https://openalex.org/W4411552386","https://openalex.org/W4411552868","https://openalex.org/W4413267905","https://openalex.org/W7133209642","https://openalex.org/W7133222210","https://openalex.org/W7133224126"],"related_works":[],"abstract_inverted_index":{"Efficient":[0],"failure":[1,22,62,102,111,175],"diagnosis":[2,42,63,103,132],"is":[3],"critical":[4],"to":[5,32,77,113,156],"maintaining":[6],"the":[7,33,83,115,131,159,227],"stability":[8],"and":[9,68,81,143,164,193,216],"reliability":[10],"of":[11,36,118,123,187,229,242],"operating":[12,136],"systems":[13],"(OSes)":[14],"in":[15,198,231,248],"modern":[16],"industrial":[17,89],"environments.":[18],"In":[19],"practice,":[20],"manual":[21],"analysis":[23],"by":[24,106,205],"on-call":[25],"engineers":[26,230],"(OCEs)":[27],"faces":[28],"increasing":[29],"challenges":[30],"due":[31],"growing":[34],"complexity":[35],"OS":[37,174],"failures,":[38,233],"while":[39],"recent":[40],"automated":[41,61,244],"methods":[43,192,247],"often":[44],"suffer":[45],"from":[46,178,212],"low":[47],"explainability,":[48],"limiting":[49],"their":[50,65],"practical":[51,94,165,217],"adoption.":[52],"Large":[53],"Language":[54],"Models":[55],"(LLMs)":[56],"hold":[57],"promise":[58],"for":[59,88,161,214],"advancing":[60],"through":[64],"sophisticated":[66],"reasoning":[67],"language":[69],"generation":[70],"capabilities.":[71],"However,":[72],"traditional":[73],"LLM-based":[74],"solutions":[75],"struggle":[76],"integrate":[78],"domain":[79],"knowledge":[80],"lack":[82],"effective":[84],"interaction":[85],"mechanisms":[86],"required":[87],"troubleshooting.":[90],"To":[91],"address":[92],"these":[93],"challenges,":[95],"we":[96],"present":[97],"OScope,":[98],"an":[99,185],"automated,":[100],"explainable":[101],"framework":[104,128],"powered":[105],"LLMs.":[107],"OScope":[108,150,170,183,206,223],"leverages":[109],"historical":[110],"cases":[112],"enhance":[114],"semantic":[116],"understanding":[117],"anomalies,":[119],"enabling":[120],"precise":[121],"retrieval":[122],"relevant":[124],"troubleshooting":[125],"guides.":[126],"The":[127,201],"further":[129],"structures":[130],"process":[133],"using":[134],"standard":[135],"procedure":[137],"(SOP)":[138],"templates,":[139],"supporting":[140],"step-by-step":[141],"verification":[142],"correction":[144],"with":[145,158],"corresponding":[146],"SOP":[147],"documents.":[148],"Importantly,":[149],"facilitates":[151],"human-in-the-loop":[152],"collaboration,":[153],"allowing":[154],"OCEs":[155,213],"interact":[157],"system":[160],"report":[162],"refinement":[163],"feedback.":[166],"We":[167],"have":[168,207],"evaluated":[169],"on":[171],"a":[172,239],"real-world":[173],"dataset":[176],"collected":[177],"Alibaba.":[179],"Results":[180],"show":[181],"that":[182],"achieves":[184],"AC@5":[186],"90%,":[188],"significantly":[189],"outperforming":[190],"baseline":[191],"demonstrating":[194],"high":[195],"diagnostic":[196,202],"value":[197],"production":[199],"settings.":[200],"reports":[203],"generated":[204],"also":[208],"received":[209],"positive":[210],"feedback":[211],"readability":[215],"usefulness.":[218],"Since":[219],"deployment":[220],"at":[221],"Alibaba,":[222],"has":[224],"substantially":[225],"improved":[226],"efficiency":[228],"resolving":[232],"highlighting":[234],"its":[235],"tangible":[236],"impact":[237],"as":[238],"successful":[240],"case":[241],"applying":[243],"software":[245],"engineering":[246],"industry.":[249]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-07-12T00:00:00"}