{"id":"https://openalex.org/W7169609590","doi":"https://doi.org/10.1145/3803437.3805245","title":"Reflex: Event-Driven Automated Fault Localization for Large-Scale LLM Training","display_name":"Reflex: Event-Driven Automated Fault Localization for Large-Scale LLM Training","publication_year":2026,"publication_date":"2026-07-05","ids":{"openalex":"https://openalex.org/W7169609590","doi":"https://doi.org/10.1145/3803437.3805245"},"language":null,"primary_location":{"id":"doi:10.1145/3803437.3805245","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3803437.3805245","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 34th ACM International Conference on the Foundations of Software Engineering","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3803437.3805245","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020974859","display_name":"Hua Ding","orcid":"https://orcid.org/0009-0006-7845-4995"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hua Ding","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-7845-4995","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141096155","display_name":"Yun Zhang","orcid":"https://orcid.org/0009-0009-9159-3107"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yun Zhang","raw_affiliation_strings":["ByteDance Seed, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-9159-3107","affiliations":[{"raw_affiliation_string":"ByteDance Seed, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100358766","display_name":"Bo Zhang","orcid":"https://orcid.org/0000-0002-6975-9184"},"institutions":[{"id":"https://openalex.org/I153473198","display_name":"North China Electric Power University","ror":"https://ror.org/04qr5t414","country_code":"CN","type":"education","lineage":["https://openalex.org/I153473198"]},{"id":"https://openalex.org/I4392738113","display_name":"China Electric Power Research Institute","ror":"https://ror.org/05ehpzy81","country_code":null,"type":"facility","lineage":["https://openalex.org/I17442442","https://openalex.org/I4392738113"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Zhang","raw_affiliation_strings":["China Electric Power Research Institute, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6975-9184","affiliations":[{"raw_affiliation_string":"China Electric Power Research Institute, Beijing, China","institution_ids":["https://openalex.org/I153473198","https://openalex.org/I4392738113"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141086143","display_name":"Wenxiao Wang","orcid":"https://orcid.org/0009-0007-4482-2566"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenxiao Wang","raw_affiliation_strings":["ByteDance Seed, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0007-4482-2566","affiliations":[{"raw_affiliation_string":"ByteDance Seed, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100621400","display_name":"Libo Chen","orcid":"https://orcid.org/0000-0003-3236-4805"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Libo Chen","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3236-4805","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141049756","display_name":"Huan Yu","orcid":"https://orcid.org/0009-0000-8102-5055"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huan Yu","raw_affiliation_strings":["ByteDance Seed, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-8102-5055","affiliations":[{"raw_affiliation_string":"ByteDance Seed, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141082744","display_name":"Zhe Nan","orcid":"https://orcid.org/0009-0001-6311-0018"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhe Nan","raw_affiliation_strings":["ByteDance Seed, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0001-6311-0018","affiliations":[{"raw_affiliation_string":"ByteDance Seed, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141068611","display_name":"Zuquan Song","orcid":"https://orcid.org/0009-0008-7576-6162"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zuquan Song","raw_affiliation_strings":["ByteDance Seed, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-7576-6162","affiliations":[{"raw_affiliation_string":"ByteDance Seed, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112332166","display_name":"W. Z. Lou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128111","display_name":"Clover Seed (China)","ror":"https://ror.org/037jwt041","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128111"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiqiang Lou","raw_affiliation_strings":["ByteDance Seed, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-7390-0581","affiliations":[{"raw_affiliation_string":"ByteDance Seed, Shanghai, China","institution_ids":["https://openalex.org/I4210128111"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141065561","display_name":"Gaohong Liu","orcid":"https://orcid.org/0009-0005-2551-7879"},"institutions":[{"id":"https://openalex.org/I4210128111","display_name":"Clover Seed (China)","ror":"https://ror.org/037jwt041","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128111"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaohong Liu","raw_affiliation_strings":["ByteDance Seed, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-2551-7879","affiliations":[{"raw_affiliation_string":"ByteDance Seed, Shanghai, China","institution_ids":["https://openalex.org/I4210128111"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141094375","display_name":"Xi Yang","orcid":"https://orcid.org/0009-0006-2195-8834"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xi Yang","raw_affiliation_strings":["ByteDance Seed, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-2195-8834","affiliations":[{"raw_affiliation_string":"ByteDance Seed, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141101592","display_name":"Yuhan Li","orcid":"https://orcid.org/0009-0001-5310-9523"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuhan Li","raw_affiliation_strings":["ByteDance Seed, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-5310-9523","affiliations":[{"raw_affiliation_string":"ByteDance Seed, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141096642","display_name":"Qinlong Wang","orcid":"https://orcid.org/0009-0007-5406-6354"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qinlong Wang","raw_affiliation_strings":["ByteDance Seed, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0007-5406-6354","affiliations":[{"raw_affiliation_string":"ByteDance Seed, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141063742","display_name":"Shuguang Wang","orcid":"https://orcid.org/0009-0008-4249-4092"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuguang Wang","raw_affiliation_strings":["ByteDance Seed, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-4249-4092","affiliations":[{"raw_affiliation_string":"ByteDance Seed, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086945155","display_name":"Wencong Xiao","orcid":"https://orcid.org/0000-0002-3043-522X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wencong Xiao","raw_affiliation_strings":["ByteDance Seed, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3043-522X","affiliations":[{"raw_affiliation_string":"ByteDance Seed, Hangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100673372","display_name":"Shenghong Li","orcid":"https://orcid.org/0000-0002-0767-2307"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shenghong Li","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0767-2307","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":"731","last_page":"742"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5703999996185303},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5376999974250793},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.5159000158309937},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4715999960899353},{"id":"https://openalex.org/keywords/visibility","display_name":"Visibility","score":0.4065999984741211},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.3986000120639801},{"id":"https://openalex.org/keywords/fault","display_name":"Fault (geology)","score":0.37209999561309814}],"concepts":[{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5703999996185303},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5687000155448914},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5376999974250793},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.5220999717712402},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.5159000158309937},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4715999960899353},{"id":"https://openalex.org/C123403432","wikidata":"https://www.wikidata.org/wiki/Q654068","display_name":"Visibility","level":2,"score":0.4065999984741211},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3986000120639801},{"id":"https://openalex.org/C175551986","wikidata":"https://www.wikidata.org/wiki/Q47089","display_name":"Fault (geology)","level":2,"score":0.37209999561309814},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37119999527931213},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C152745839","wikidata":"https://www.wikidata.org/wiki/Q5438153","display_name":"Fault detection and isolation","level":3,"score":0.31459999084472656},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31380000710487366},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2930000126361847},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2831999957561493},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2777999937534332},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C23725684","wikidata":"https://www.wikidata.org/wiki/Q616377","display_name":"Maintenance engineering","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3803437.3805245","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3803437.3805245","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 34th ACM International Conference on the Foundations of Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3803437.3805245","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3803437.3805245","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 34th ACM International Conference on the Foundations of Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4278055530","display_name":null,"funder_award_id":"2023YFB3107100","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G97583977","display_name":null,"funder_award_id":"62372297","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2057332538","https://openalex.org/W3083560262","https://openalex.org/W3086105743","https://openalex.org/W4386768656","https://openalex.org/W4404181190","https://openalex.org/W4405079333","https://openalex.org/W4412130287"],"related_works":[],"abstract_inverted_index":{"Training":[0],"Large":[1],"Language":[2],"Models":[3],"(LLMs)":[4],"at":[5],"scale":[6],"presents":[7],"formidable":[8],"reliability":[9],"challenges,":[10],"where":[11],"frequent":[12],"infrastructure":[13],"failures":[14,45,77],"incur":[15],"prohibitive":[16],"financial":[17],"costs.":[18],"Current":[19],"fault":[20],"localization":[21],"(i.e.,":[22],"pinpointing":[23],"faulty":[24],"nodes)":[25],"remains":[26],"predominantly":[27],"reactive":[28],"and":[29,87],"manual,":[30],"severely":[31],"constraining":[32],"training":[33,44],"throughput.":[34],"We":[35],"conduct":[36],"a":[37,51],"comprehensive":[38],"empirical":[39],"study":[40],"of":[41,83],"2,943":[42],"LLM":[43],"collected":[46],"over":[47],"six":[48],"months":[49],"from":[50],"production":[52],"environment.":[53],"The":[54],"analysis":[55],"yields":[56],"three":[57],"critical":[58],"insights:":[59],"(1)":[60],"effective":[61],"diagnosis":[62],"necessitates":[63],"fusing":[64],"full-stack":[65],"visibility":[66],"with":[67],"longitudinal":[68],"profiling":[69],"to":[70,95],"establish":[71],"spatio-temporal":[72],"context;":[73],"(2)":[74],"diagnosing":[75],"implicit":[76],"requires":[78],"modeling":[79],"the":[80],"compound":[81],"impact":[82],"pervasive":[84],"benign":[85],"anomalies;":[86],"(3)":[88],"robust":[89],"detection":[90],"demands":[91],"hardware-aware":[92],"strategies":[93],"adaptable":[94],"heterogeneous":[96],"infrastructure.":[97]},"counts_by_year":[],"updated_date":"2026-07-18T05:58:53.570196","created_date":"2026-07-18T00:00:00"}