AOI: Turning Failed Trajectories into Training Signals for Autonomous Cloud Diagnosis
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914401773158400 |
|---|---|
| author | Yang, Pei Chen, Wanyi Zheng, Asuka Yuxi Li, Xueqian Li, Xiang Tu, Haoqin Xiao, Jie Pang, Yifan Zhang, Dongdong Li, Fuqiang Long, Alfred Ai, Lynn Yang, Eric Shi, Bill |
| author_facet | Yang, Pei Chen, Wanyi Zheng, Asuka Yuxi Li, Xueqian Li, Xiang Tu, Haoqin Xiao, Jie Pang, Yifan Zhang, Dongdong Li, Fuqiang Long, Alfred Ai, Lynn Yang, Eric Shi, Bill |
| contents | Large language model (LLM) agents offer a promising data-driven approach to automating Site Reliability Engineering (SRE), yet their enterprise deployment is constrained by three challenges: restricted access to proprietary data, unsafe action execution under permission-governed environments, and the inability of closed systems to improve from failures. We present AOI (Autonomous Operations Intelligence), a trainable multi-agent framework formulating automated operations as a structured trajectory learning problem under security constraints. Our approach integrates three key components. First, a trainable diagnostic system applies Group Relative Policy Optimization (GRPO) to distill expert-level knowledge into locally deployed open-source models, enabling preference-based learning without exposing sensitive data. Second, a read-write separated execution architecture decomposes operational trajectories into observation, reasoning, and action phases, allowing safe learning while preventing unauthorized state mutation. Third, a Failure Trajectory Closed-Loop Evolver mines unsuccessful trajectories and converts them into corrective supervision signals, enabling continual data augmentation. Evaluated on the AIOpsLab benchmark, our contributions yield cumulative gains. (1) The AOI runtime alone achieves 66.3% best@5 success on all 86 tasks, outperforming the prior state-of-the-art (41.9%) by 24.4 points. (2) Adding Observer GRPO training, a locally deployed 14B model reaches 42.9% avg@1 on 63 held-out tasks with unseen fault types, surpassing Claude Sonnet 4.5. (3) The Evolver converts 37 failed trajectories into diagnostic guidance, improving end-to-end avg@5 by 4.8 points while reducing variance by 35%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_03378 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AOI: Turning Failed Trajectories into Training Signals for Autonomous Cloud Diagnosis Yang, Pei Chen, Wanyi Zheng, Asuka Yuxi Li, Xueqian Li, Xiang Tu, Haoqin Xiao, Jie Pang, Yifan Zhang, Dongdong Li, Fuqiang Long, Alfred Ai, Lynn Yang, Eric Shi, Bill Machine Learning Artificial Intelligence Large language model (LLM) agents offer a promising data-driven approach to automating Site Reliability Engineering (SRE), yet their enterprise deployment is constrained by three challenges: restricted access to proprietary data, unsafe action execution under permission-governed environments, and the inability of closed systems to improve from failures. We present AOI (Autonomous Operations Intelligence), a trainable multi-agent framework formulating automated operations as a structured trajectory learning problem under security constraints. Our approach integrates three key components. First, a trainable diagnostic system applies Group Relative Policy Optimization (GRPO) to distill expert-level knowledge into locally deployed open-source models, enabling preference-based learning without exposing sensitive data. Second, a read-write separated execution architecture decomposes operational trajectories into observation, reasoning, and action phases, allowing safe learning while preventing unauthorized state mutation. Third, a Failure Trajectory Closed-Loop Evolver mines unsuccessful trajectories and converts them into corrective supervision signals, enabling continual data augmentation. Evaluated on the AIOpsLab benchmark, our contributions yield cumulative gains. (1) The AOI runtime alone achieves 66.3% best@5 success on all 86 tasks, outperforming the prior state-of-the-art (41.9%) by 24.4 points. (2) Adding Observer GRPO training, a locally deployed 14B model reaches 42.9% avg@1 on 63 held-out tasks with unseen fault types, surpassing Claude Sonnet 4.5. (3) The Evolver converts 37 failed trajectories into diagnostic guidance, improving end-to-end avg@5 by 4.8 points while reducing variance by 35%. |
| title | AOI: Turning Failed Trajectories into Training Signals for Autonomous Cloud Diagnosis |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2603.03378 |