IDSTune: A Multi-Agent Collaborative Framework for Integrated Database System Tuning

2026-07-24

AI Summary

This work addresses the limitations of traditional database tuning approaches, which optimize parameters, indexes, or materialized views in isolation and fail to account for inter-component dependencies, thereby struggling with dynamic and diverse workloads. To overcome this, the authors propose IDSTune, a novel framework that introduces, for the first time, a large language model–driven multi-agent collaboration mechanism. IDSTune employs a two-stage process—first compressing the workload and then jointly recommending configurations—to enable holistic, coordinated tuning across multiple components. By integrating a centralized coordinator, a feedback loop, and retrieval-augmented knowledge, the framework significantly enhances global consistency and adaptability. Experimental results demonstrate that IDSTune achieves up to a 38% performance improvement and accelerates the tuning process by up to 57% across various scenarios, exhibiting strong generalization capability and efficiency.

Abstract

Database tuning is critical for achieving high performance in modern database management systems (DBMSs). Existing methods typically optimize a single component---knobs, indexes, or materialized views---without accounting for their interdependencies. This limitation arises because these components require different tuning strategies and are difficult to integrate within a unified framework. As a result, directly extending a method to multiple components or simply combining separate methods often fails to capture cross-component collaboration and shared tuning signals. Moreover, existing methods are insufficient for handling diverse workloads, evolving data, and dynamic query patterns. To address these limitations, we propose IDSTune, an integrated tuning framework that jointly optimizes multiple configuration components through LLM-driven multi-agent collaboration. IDSTune operates in two phases: (i) workload compression, which extracts and selects task-relevant features, and (ii) configuration recommendation, where specialized agents collaboratively generate and refine configurations for knobs, indexes, and materialized views under the supervision of a centralized coordinator. By incorporating feedback and external knowledge retrieval, IDSTune achieves efficient and globally consistent tuning. Extensive experiments show that IDSTune achieves up to 38% performance improvement and 57% faster tuning, with strong adaptability across diverse scenarios.

Problem

• database tuning
• multi-component optimization
• cross-component collaboration
• workload adaptability
• dynamic query patterns

Innovation

• multi-agent collaboration
• integrated database tuning
• LLM-driven optimization
• workload compression
• configuration recommendation