Paper Detail

OpsMem: Dual-Memory Reasoning with Cross-Memory Resonance for Failure Diagnosis

Yongqian Sun, Rongchen Gao, Yu Luo, Wenwei Gu, Shenglin Zhang, Qingyi Guo, Qiuai Fu, Yaoliang Wu, Dan Pei

arxiv Score 13.2

Published 2026-07-13 · First seen 2026-07-14

General AI

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.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{sun2026opsmem,
  title = {OpsMem: Dual-Memory Reasoning with Cross-Memory Resonance for Failure Diagnosis},
  author = {Yongqian Sun and Rongchen Gao and Yu Luo and Wenwei Gu and Shenglin Zhang and Qingyi Guo and Qiuai Fu and Yaoliang Wu and Dan Pei},
  year = {2026},
  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},
  url = {https://arxiv.org/abs/2607.11357},
  keywords = {cs.AI, cs.SE},
  eprint = {2607.11357},
  archiveprefix = {arXiv},
}

Metadata

{}