# DBAIOps: A Reasoning LLM-Enhanced Database Operation and Maintenance System using Knowledge Graphs

arXiv: https://arxiv.org/abs/2508.01136 · HTML: https://mlsanity.com/paper/2508.01136/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 9 of its 26 references that are in the map.
- First posted on arXiv 2 Aug 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 9 of 9)

- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [D-Bot: Database Diagnosis System using Large Language Models](https://mlsanity.com/paper/2312.01454/) (2023)
- [Saga: A Platform for Continuous Construction and Serving of Knowledge At Scale](https://mlsanity.com/paper/2204.07309/) (2022)
- [Semantic Sensitive TF-IDF to Determine Word Relevance in Documents](https://mlsanity.com/paper/2001.09896/) (2020)
- [Automatic Database Configuration Debugging using Retrieval-Augmented Language Models](https://mlsanity.com/paper/2412.07548/) (2024)
- [Online Adaptive Machine Learning Based Algorithm for Implied Volatility Surface Modeling](https://mlsanity.com/paper/1706.01833/) (2017)
- [RCRank: Multimodal Ranking of Root Causes of Slow Queries in Cloud Database Systems](https://mlsanity.com/paper/2503.04252/) (2025)
- [OpenMLDB: A Real-Time Relational Data Feature Computation System for Online ML](https://mlsanity.com/paper/2501.08591/) (2025)
- [Analyzing Query Performance and Attributing Blame for Contentions in a Cluster Computing Framework](https://mlsanity.com/paper/1708.08435/) (2017)

## Built on by (most cited first, 7 of 7)

- [A Survey of Data Agents: Emerging Paradigm or Overstated Hype?](https://mlsanity.com/paper/2510.23587/) (2025)
- [Cloud-OpsBench: A Reproducible Benchmark for Agentic Root Cause Analysis in Cloud Systems](https://mlsanity.com/paper/2603.00468/) (2026)
- [Automating Database-Native Function Code Synthesis with LLMs](https://mlsanity.com/paper/2604.06231/) (2026)
- [ProfiLLM: Utility-Aligned Agentic User Profiling for Industrial Ride-Hailing Dispatch](https://mlsanity.com/paper/2606.18803/) (2026)
- [OpsMem: Dual-Memory Reasoning with Cross-Memory Resonance for Failure Diagnosis](https://mlsanity.com/paper/2607.11357/) (2026)
- [DBA-Bench: A Production-Fidelity Benchmark for LLM-Based Database Operations Agents](https://mlsanity.com/paper/2607.22165/) (2026)
- [Dial: A Knowledge-Grounded Dialect-Specific NL2SQL System](https://mlsanity.com/paper/2603.07449/) (2026)

## Abstract (arXiv)

The operation and maintenance (O&M) of database systems is critical to ensuring system availability and performance, typically requiring expert experience (e.g., identifying metric-to-anomaly relations) for effective diagnosis and recovery. However, existing automatic database O&M methods, including commercial products, cannot effectively utilize expert experience. On the one hand, rule-based methods only support basic O&M tasks (e.g., metric-based anomaly detection), which are mostly numerical equations and cannot effectively incorporate literal O&M experience (e.g., troubleshooting guidance in manuals). On the other hand, LLM-based methods, which retrieve fragmented information (e.g., standard documents + RAG), often generate inaccurate or generic results. To address these limitations, we present DBAIOps, a novel hybrid database O&M system that combines reasoning LLMs with knowledge graphs to achieve DBA-style diagnosis. First, DBAIOps introduces a heterogeneous graph model for representing the diagnosis experience, and proposes a semi-automatic graph construction algorithm to build that graph from thousands of documents. Second, DBAIOps develops a collection of (800+) reusable anomaly models that identify both directly alerted metrics and implicitly correlated experience and metrics. Third, for each anomaly, DBAIOps proposes a two-stage graph evolution mechanism to explore relevant diagnosis paths and identify missing relations automatically. It then leverages a reasoning LLM (e.g., DeepSeek-R1) to infer root causes and generate clear diagnosis reports for both DBAs and common users. Our evaluation over four mainstream database systems (Oracle, MySQL, PostgreSQL, and DM8) demonstrates that DBAIOps outperforms state-of-the-art baselines, 34.85% and 47.22% higher in root cause and human evaluation accuracy, respectively.