一句话：提出 ChaosEater，用 LLM 智能体工作流全自动执行 Kubernetes 系统混沌工程全周期，低成本构建弹性系统。
混沌工程（CE）通过向分布式系统故意注入故障来检验弹性、暴露弱点并在生产故障发生前加以修复。现有 CE 工具只能自动执行预定义的实验，而实验规划与基于结果改进系统仍需人工完成，既费时又依赖多领域专家。为让任何人都能低成本构建弹性系统，本文提出 ChaosEater：它按照系统化的 CE 周期预定义一个智能体工作流，并把工作流中细分的子过程交给大语言模型（LLM）完成。ChaosEater 面向构建在 Kubernetes 上的软件系统，其中的 LLM 通过需求定义、代码生成、测试与调试等软件工程任务走完整个 CE 周期。作者在小规模与大规模 Kubernetes 系统上开展案例研究，结果表明它能以显著低的时间与金钱成本稳定完成合理的 CE 周期，其周期质量还经人类工程师与 LLM 定性验证。
Chaos Engineering (CE) is an engineering technique aimed at improving the resilience of distributed systems. It involves intentionally injecting faults into a system to test its resilience, uncover weaknesses, and address them before they cause failures in production. Recent CE tools automate the execution of predefined CE experiments. However, planning such experiments and improving the system based on the experimental results still remain manual. These processes are labor-intensive and require multi-domain expertise. To address these challenges and enable anyone to build resilient systems at low cost, this paper proposes ChaosEater, a system that automates the entire CE cycle with Large Language Models (LLMs). It predefines an agentic workflow according to a systematic CE cycle and assigns subdivided processes within the workflow to LLMs. ChaosEater targets CE for software systems built on Kubernetes. Therefore, the LLMs in ChaosEater complete CE cycles through software engineering tasks, including requirement definition, code generation, testing, and debugging. We evaluate ChaosEater through case studies on small- and large-scale Kubernetes systems. The results demonstrate that it consistently completes reasonable CE cycles with significantly low time and monetary costs. Its cycles are also qualitatively validated by human engineers and LLMs.
@inproceedings{paperbot9422,
title = {LLM-Powered Fully Automated Chaos Engineering: Towards Enabling Anyone to Build Resilient Software Systems at Low Cost},
author = {Daisuke Kikuta and Hiroki Ikeuchi and Kengo Tajiri},
booktitle = {ASE},
year = {2025},
doi = {10.1109/ase63991.2025.00331}
}