Agentic Troubleshooting Guide Automation for Incident Management

📅 2025-10-11
📈 Citations: 0
Influential: 0
📄 PDF

career value

180K/year
🤖 AI Summary
Manual execution of Troubleshooting Guides (TSGs) in large-scale IT systems is inefficient and error-prone, while existing LLM-based approaches struggle with poor TSG quality, complex control flow, data-intensive queries, and parallel execution requirements. Method: We propose an end-to-end automation framework comprising: (i) TSG Mentor to enhance guide quality; (ii) an offline phase leveraging LLMs to construct a structured execution DAG and generate domain-specific Query Preparation Plugins (QPPs); and (iii) an online phase employing a DAG-guided, memory-augmented scheduler and executor that ensures correctness and enables task-level parallelism. Results: Evaluated on real-world TSGs and incidents, our framework achieves a 94% success rate with GPT-4.1—significantly outperforming baselines—and reduces execution time for parallelizable TSGs by 32.9%–70.4%, while also improving token efficiency and latency.

Technology Category

Application Category

📝 Abstract
Effective incident management in large-scale IT systems relies on troubleshooting guides (TSGs), but their manual execution is slow and error-prone. While recent advances in LLMs offer promise for automating incident management tasks, existing LLM-based solutions lack specialized support for several key challenges, including managing TSG quality issues, interpreting complex control flow, handling data-intensive queries, and exploiting execution parallelism. We first conducted an empirical study on 92 real-world TSGs, and, guided by our findings, we present StepFly, a novel end-to-end agentic framework for troubleshooting guide automation. Our approach features a three-stage workflow: the first stage provides a comprehensive guide together with a tool, TSG Mentor, to assist SREs in improving TSG quality; the second stage performs offline preprocessing using LLMs to extract structured execution DAGs from unstructured TSGs and to create dedicated Query Preparation Plugins (QPPs); and the third stage executes online using a DAG-guided scheduler-executor framework with a memory system to guarantee correct workflow and support parallel execution of independent steps. Our empirical evaluation on a collection of real-world TSGs and incidents demonstrates that StepFly achieves a ~94% success rate on GPT-4.1, outperforming baselines with less time and token consumption. Furthermore, it achieves a remarkable execution time reduction of 32.9% to 70.4% for parallelizable TSGs.
Problem

Research questions and friction points this paper is trying to address.

Automating troubleshooting guides to reduce manual execution errors and delays
Addressing LLM limitations in handling complex control flow and data queries
Improving parallel execution efficiency for IT incident management workflows
Innovation

Methods, ideas, or system contributions that make the work stand out.

Automated TSG quality improvement with TSG Mentor tool
Offline preprocessing extracts DAGs and creates query plugins
DAG-guided scheduler with memory enables parallel execution
🔎 Similar Papers
No similar papers found.
J
JIAYI MAO
Tsinghua University, China
L
LIQUN LI
Microsoft, China
Y
YANJIE GAO
Microsoft Research, China
Z
ZEGANG PENG
Tsinghua University, China
S
SHILIN HE
Microsoft, China
C
CHAOYUN ZHANG
Microsoft, China
S
SI QIN
Microsoft, China
S
SAMIA KHALID
Microsoft, USA
Q
QINGWEI LIN
Microsoft, China
S
SARAVAN RAJMOHAN
Microsoft, USA
S
SITARAM LANKA
Microsoft, USA
D
DONGMEI ZHANG
Microsoft, China