一句话：提出 AgentFM，用 LLM 驱动的多智能体按系统、数据与任务角色协同实现分布式数据库故障管理。
分布式数据库是当今大规模软件系统的关键基础设施，有效的故障管理对保障软件可用性至关重要。然而现有方法往往忽略分布式数据库内部不同角色之间的差异，并依赖泛化能力有限的小规模模型。本文首先开展初步实证研究，说明不同角色在故障管理中的独特重要性；在此基础上提出 AgentFM，一个由 LLM 驱动多智能体实现的角色感知故障管理框架。AgentFM 从系统角色、数据角色与任务角色三个维度刻画故障管理，并引入一个元智能体（meta-agent）统一编排这些组件。基于 Apache IoTDB 的初步评估验证了 AgentFM 的有效性，并为后续研究开辟了新方向。
Distributed databases are critical infrastructures for today's large-scale software systems, making effective failure management essential to ensure software availability. However, existing approaches often overlook the role distinctions within distributed databases and rely on small-scale models with limited generalization capabilities. In this paper, we conduct a preliminary empirical study to emphasize the unique significance of different roles. Building on this insight, we propose AgentFM, a role-aware failure management framework for distributed databases powered by LLM-driven multi-agents. AgentFM addresses failure management by considering system roles, data roles, and task roles, with a meta-agent orchestrating these components. Preliminary evaluations using Apache IoTDB demonstrate the effectiveness of AgentFM and open new directions for further research.
@inproceedings{paperbot8944,
title = {AgentFM: Role-Aware Failure Management for Distributed Databases with LLM-Driven Multi-Agents},
author = {Lingzhe Zhang and Yunpeng Zhai and Tong Jia and Xiaosong Huang and Chiming Duan and Ying Li},
booktitle = {FSE},
year = {2025},
doi = {10.1145/3696630.3728492}
}