CoE-Ops: Collaboration of LLM-based Experts for AIOps Question-Answering
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915418207158272 |
|---|---|
| author | Zhao, Jinkun Wang, Yuanshuai Zhang, Xingjian Chen, Ruibo Liao, Xingchuang Wang, Junle Huang, Lei Zhang, Kui Wu, Wenjun |
| author_facet | Zhao, Jinkun Wang, Yuanshuai Zhang, Xingjian Chen, Ruibo Liao, Xingchuang Wang, Junle Huang, Lei Zhang, Kui Wu, Wenjun |
| contents | With the rapid evolution of artificial intelligence, AIOps has emerged as a prominent paradigm in DevOps. Lots of work has been proposed to improve the performance of different AIOps phases. However, constrained by domain-specific knowledge, a single model can only handle the operation requirement of a specific task,such as log parser,root cause analysis. Meanwhile, combining multiple models can achieve more efficient results, which have been proved in both previous ensemble learning and the recent LLM training domain. Inspired by these works,to address the similar challenges in AIOPS, this paper first proposes a collaboration-of-expert framework(CoE-Ops) incorporating a general-purpose large language model task classifier. A retrieval-augmented generation mechanism is introduced to improve the framework's capability in handling both Question-Answering tasks with high-level(Code,build,Test,etc.) and low-level(fault analysis,anomaly detection,etc.). Finally, the proposed method is implemented in the AIOps domain, and extensive experiments are conducted on the DevOps-EVAL dataset. Experimental results demonstrate that CoE-Ops achieves a 72% improvement in routing accuracy for high-level AIOps tasks compared to existing CoE methods, delivers up to 8% accuracy enhancement over single AIOps models in DevOps problem resolution, and outperforms larger-scale Mixture-of-Experts (MoE) models by up to 14% in accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_22937 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CoE-Ops: Collaboration of LLM-based Experts for AIOps Question-Answering Zhao, Jinkun Wang, Yuanshuai Zhang, Xingjian Chen, Ruibo Liao, Xingchuang Wang, Junle Huang, Lei Zhang, Kui Wu, Wenjun Computation and Language Artificial Intelligence With the rapid evolution of artificial intelligence, AIOps has emerged as a prominent paradigm in DevOps. Lots of work has been proposed to improve the performance of different AIOps phases. However, constrained by domain-specific knowledge, a single model can only handle the operation requirement of a specific task,such as log parser,root cause analysis. Meanwhile, combining multiple models can achieve more efficient results, which have been proved in both previous ensemble learning and the recent LLM training domain. Inspired by these works,to address the similar challenges in AIOPS, this paper first proposes a collaboration-of-expert framework(CoE-Ops) incorporating a general-purpose large language model task classifier. A retrieval-augmented generation mechanism is introduced to improve the framework's capability in handling both Question-Answering tasks with high-level(Code,build,Test,etc.) and low-level(fault analysis,anomaly detection,etc.). Finally, the proposed method is implemented in the AIOps domain, and extensive experiments are conducted on the DevOps-EVAL dataset. Experimental results demonstrate that CoE-Ops achieves a 72% improvement in routing accuracy for high-level AIOps tasks compared to existing CoE methods, delivers up to 8% accuracy enhancement over single AIOps models in DevOps problem resolution, and outperforms larger-scale Mixture-of-Experts (MoE) models by up to 14% in accuracy. |
| title | CoE-Ops: Collaboration of LLM-based Experts for AIOps Question-Answering |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2507.22937 |