AegisFlow: A Multi-Agent Agentic AI Framework for Autonomous Remediation and Self-Healing in Fragile Data Ecosystems

Computer Science > Artificial Intelligence arXiv:2610.06971 (cs) [Submitted on 3 Oct 2026] Title: AegisFlow: A Multi-Agent Agentic AI Framework for Autonomous Remediation and Self-Healing in Fragile Data Ecosystems Authors: Muhammad Bilal Awan, Zubair Hussain, Abdul Shahid.

计算机科学 > 人工智能 arXiv:2610.06971 (cs) [提交于 2026 年 10 月 3 日] 标题：AegisFlow：一种用于脆弱数据生态系统中自主修复和自我愈合的多智能体代理 AI 框架。作者：Muhammad Bilal Awan, Zubair Hussain, Abdul Shahid。

Abstract: Traditional data pipelines are notoriously brittle, often failing due to upstream schema drift, API contract changes, or website DOM modifications. Present observability tools only raise alerts but for human engineers, resulting in a high Mean Time to Repair (MTTR) and operational fatigue.

摘要：传统的数据流水线以脆弱著称，常因上游模式漂移、API 契约变更或网站 DOM 修改而失效。目前的观测工具仅能向人类工程师发出警报，导致平均修复时间（MTTR）过长并产生运维疲劳。

In this paper we propose AegisFlow (Agentic Engine for Intelligent Self-healing and Graph-driven Operations for Workload remediation), a novel agentic framework that closes the loop between detection and resolution. AegisFlow uses a Watchdog agent to collect runtime telemetry and has a Repair agent to automatically create, test and deploy code patches based on Large Language Models (LLMs).

在本文中，我们提出了 AegisFlow（用于智能自我愈合和工作负载修复的图驱动操作代理引擎），这是一种闭合检测与解决环节的新型代理框架。AegisFlow 使用一个“看门狗”代理来收集运行时遥测数据，并配备一个“修复”代理，基于大语言模型（LLMs）自动创建、测试和部署代码补丁。

The framework presents the non-intrusive execution model called Parallel Shadow Patching, a non-intrusive execution model based on the Monitor, Analyze, Plan, Execute, Knowledge (MAPE-K) loop to generate and verify patches in digital twin environments.

该框架提出了一种名为“并行影子补丁”的非侵入式执行模型，这是一种基于监控、分析、计划、执行、知识（MAPE-K）循环的非侵入式执行模型，用于在数字孪生环境中生成并验证补丁。

Through experimental testing, we have evaluated AegisFlow across five common failure scenarios, and see 98.1 percent improvement in MTTR (from an average of 170 minutes per patch to 3.2 minutes) and a patch success rate of 92 percent.

通过实验测试，我们在五种常见故障场景中评估了 AegisFlow，结果显示 MTTR 提升了 98.1%（从每个补丁平均 170 分钟缩短至 3.2 分钟），补丁成功率为 92%。

In particular, the system is successful in dealing with changes in the JSON schema (96 percent) and punctuation drift (98 percent), and is least successful in Shadow DOM cases (85 percent). AegisFlow frees up about 98 percent of data engineering on-call time from firefighting and reallocates it towards innovation.

特别地，该系统在处理 JSON 模式变更（96%）和标点符号漂移（98%）方面表现成功，而在 Shadow DOM 情况下的表现相对较弱（85%）。AegisFlow 将数据工程约 98% 的待命时间从“救火”式工作中解放出来，并将其重新分配到创新工作中。

The framework is deployment agnostic consisting of a system that can be deployed in a plugin fashion into an existing pipeline orchestration system with minimal uplift to the existing system.

该框架与部署环境无关，其系统可以插件方式部署到现有的流水线编排系统中，且对现有系统的改动极小。