arXiv：cs.AI· Muhammad Bilal Awan, Zubair Hussain, Abdul Shahid·· 4 小时前AI 评分37
AegisFlow：面向脆弱数据生态的多智能体智能体 AI 框架，实现自主修复与自愈
AegisFlow: A Multi-Agent Agentic AI Framework for Autonomous Remediation and Self-Healing in Fragile Data Ecosystems
AI 导读
AegisFlow 是一个基于 LLM 的多智能体框架，通过 Watchdog 采集运行时遥测、Repair 自动生成并部署代码补丁，闭环打通检测与修复。在五类常见故障场景测试中，MTTR 从平均 170 分钟降至 3.2 分钟，改善 98.1%，补丁成功率 92%。
正文
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. 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). 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. 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 . 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. 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.
| Comments: | 43 pages |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.06971 [cs.AI] |
| (or arXiv:2610.06971v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.06971 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Muhammad Bilal Awan Mr. [view email]
[v1]
Sat, 3 Oct 2026 19:12:31 UTC (1,318 KB)
来源：arXiv：cs.AI · arxiv.org