{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T05:20:05Z","timestamp":1783574405982,"version":"3.55.0"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T00:00:00Z","timestamp":1782086400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T00:00:00Z","timestamp":1782086400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,6,22]]},"DOI":"10.1109\/dsn69566.2026.00018","type":"proceedings-article","created":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T19:41:43Z","timestamp":1783539703000},"page":"15-23","source":"Crossref","is-referenced-by-count":0,"title":["LLMGuard: Multi-Agent Fault Diagnosis for Reliable Language-Model-as-a-Service"],"prefix":"10.1109","author":[{"given":"Yuedong","family":"Zhong","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangba","family":"Yu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujie","family":"Huang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"QunChao","family":"Fu","sequence":"additional","affiliation":[{"name":"Huawei Cloud Computing Technology Co., Ltd"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Ren","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cong","family":"Feng","sequence":"additional","affiliation":[{"name":"Huawei Cloud Computing Technology Co., Ltd"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongqiang","family":"Yang","sequence":"additional","affiliation":[{"name":"Huawei Cloud Computing Technology Co., Ltd"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Lyu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i27.35133"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3418881"},{"key":"ref3","first-page":"505","article-title":"Minder: Faulty machine detection for large-scale distributed model training","volume-title":"NSDI 2025","author":"Deng"},{"key":"ref4","first-page":"745","article-title":"Megascale: Scaling large language model training to more than 10, 000 gpus","volume-title":"NSDI 2024","author":"Jiang"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/hpca61900.2025.00096"},{"key":"ref6","first-page":"709","article-title":"Characterization of large language model development in the datacenter","volume-title":"NSDI 2024","author":"Hu"},{"key":"ref7","article-title":"Azure machine learning studio","year":"2025"},{"key":"ref8","article-title":"Amazon sagemaker","year":"2025"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3696630.3728531"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/DSN-S65789.2025.00034"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3629553"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639081"},{"key":"ref13","article-title":"Cloud atlas: Efficient fault localization for cloud systems using language models and causal insight","author":"Xie","year":"2024"},{"key":"ref14","article-title":"Aidai: Automated incident diagnosis for AI workloads in the cloud","volume-title":"CoRR","author":"Yang","year":"2025"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3732777"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/issre55969.2022.00022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3542929.3563482"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3616249"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3643728"},{"key":"ref20","article-title":"Ascend npu exporter","year":"2025"},{"key":"ref21","article-title":"Nvidia data center gpu manager","year":"2025"},{"key":"ref22","first-page":"865","article-title":"Evolution of aegis: Fault diagnosis for AI model training service in production","volume-title":"NSDI 2025","author":"Dong"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/icse48619.2023.00149"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/icse55347.2025.00234"},{"key":"ref25","article-title":"earco: Efficient automated root cause analysis with prompt optimization","volume-title":"CoRR","author":"Goel","year":"2025"},{"key":"ref26","first-page":"266","article-title":"Automated root causing of cloud incidents using incontext learning with gpt-4","volume-title":"FSE 2024 Companion","author":"Zhang","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3691620.3695475"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3613891"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3663529.3663861"},{"key":"ref30","article-title":"Enhancing cluster resilience: Llm-agent based autonomous intelligent cluster diagnosis system and evaluation framework","author":"Shi","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3680016"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3701716.3715225"},{"key":"ref33","first-page":"4017","article-title":"mABC: Multi-agent blockchain-inspired collaboration for root cause analysis in micro-services architecture","volume-title":"EMNLP 2024 Findings","author":"Zhang","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.14778\/3675034.3675043"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3663529.3663841"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3696630.3728492"}],"event":{"name":"2026 56th Annual IEEE International Conference on Dependable Systems and Networks (DSN)","location":"Charlotte, NC, USA","start":{"date-parts":[[2026,6,22]]},"end":{"date-parts":[[2026,6,25]]}},"container-title":["2026 56th Annual IEEE International Conference on Dependable Systems and Networks (DSN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11593123\/11593173\/11593258.pdf?arnumber=11593258","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T05:12:36Z","timestamp":1783573956000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11593258\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,22]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/dsn69566.2026.00018","relation":{},"subject":[],"published":{"date-parts":[[2026,6,22]]}}}