OpsMem：用于故障诊断的具有跨内存共振的双内存推理
OpsMem: Dual-Memory Reasoning with Cross-Memory Resonance for Failure Diagnosis
浏览论文内容
中文总结 AI 辅助
针对现代软件系统故障诊断中缺乏协调诊断状态与操作经验机制的问题，提出双内存框架OpsMem，通过跨内存共振等进行多智能体诊断，实验表明其在华为微服务故障诊断数据集上优于基线，提升了匹配度和相关性。
中文摘要 AI 辅助
现代软件系统中的故障诊断需要通过操作经验进行迭代证据获取和假设推理。现有的基于大语言模型的方法通过智能体推理或知识增强来改进诊断，但在迭代诊断过程中往往缺乏将不断演变的诊断状态与操作经验相协调的机制。我们提出了OpsMem，一个双内存框架，它为当前诊断状态维护短期内存，为可重复使用的操作经验维护长期内存。OpsMem使用跨内存共振来激活与状态相关的长期内存，基于短期和激活的长期内存进行多智能体诊断，并将已解决事件中的可重复使用经验整合回长期内存。在真实世界的华为微服务故障诊断数据集上的实验表明，OpsMem优于代表性的智能体推理和知识增强基线，分别比最强基线在匹配度和相关性上提高了46.88%和18.39%。
英文摘要
Failure diagnosis in modern software systems requires iterative evidence acquisition and hypothesis reasoning guided by operational experience. Existing LLM-based methods improve diagnosis through agentic reasoning or knowledge augmentation, but they often lack a mechanism to coordinate the evolving diagnostic state with operational experience during iterative diagnosis. We propose OpsMem, a dual-memory framework that maintains a short-term memory for the current diagnostic state and a long-term memory for reusable operational experience. OpsMem uses cross-memory resonance to activate state-relevant long-term memory, conditions multi-agent diagnosis on the short-term and activated long-term memories, and consolidates reusable experience from solved incidents back into long-term memory. Experiments on a real-world Huawei microservice failure diagnosis dataset show that OpsMem outperforms representative agentic-reasoning and knowledge-augmented baselines, improving Match and Relevant by up to 46.88% and 18.39% over the strongest baseline, respectively.
发表机构
- Huawei（华为）
机构由 AI 辅助整理，请以论文原文为准。
