用双记忆机制提升软件故障诊断效率，让系统能复用经验、持续进化。
OpsMem: Dual-Memory Reasoning with Cross-Memory Resonance for Failure Diagnosis
- 设计双记忆结构：短期记忆记当前状态，长期记忆存可复用经验。
- 通过跨记忆共振激活相关经验，使诊断准确率提升46.88%。
- 适合需要持续优化的工业级故障诊断系统使用。
现代软件系统的故障诊断依赖于迭代式证据获取与基于操作经验的假设推理。现有基于大模型的方法通过代理推理或知识增强提升诊断能力，但缺乏在迭代过程中协调诊断状态与操作经验的机制。我们提出OpsMem，一种双记忆框架，分别维护当前诊断状态的短期记忆和可复用操作经验的长期记忆。通过跨记忆共振激活与当前状态相关的长期记忆，将多智能体诊断同时基于短期记忆与激活的长期记忆进行条件化，并将已解决故障中的可复用经验回填至长期记忆。在真实世界华为微服务故障诊断数据集上的实验表明，OpsMem优于代表性代理推理与知识增强基线，在匹配度（Match）和相关性（Relevant）上分别比最强基线提升46.88%和18.39%。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。