{"ID":6537585,"CreatedAt":"2026-07-14T02:54:43.516908796Z","UpdatedAt":"2026-07-15T03:28:55.185153975Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.11357","arxiv_id":"2607.11357","title":"OpsMem: Dual-Memory Reasoning with Cross-Memory Resonance for Failure Diagnosis","abstract":"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.","short_abstract":"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 wi...","url_abs":"https://arxiv.org/abs/2607.11357","url_pdf":"https://arxiv.org/pdf/2607.11357v1","authors":"[\"Yongqian Sun\",\"Rongchen Gao\",\"Yu Luo\",\"Wenwei Gu\",\"Shenglin Zhang\",\"Qingyi Guo\",\"Qiuai Fu\",\"Yaoliang Wu\",\"Dan Pei\"]","published":"2026-07-13T10:22:44Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.SE\"]","methods":"[\"Large Language Model\"]","has_code":false}