GenDB: The Next Generation of Query Processing -- Synthesized, Not Engineered

2026-03-02

AI Summary

Traditional query engines struggle to adapt to evolving requirements and technological advances due to their rigid architectures and complex maintenance overhead. This work proposes a novel query processing paradigm grounded in large language models (LLMs), leveraging a multi-agent system—centered on the Claude Code Agent—to dynamically synthesize high-performance, query-specific execution code. By enabling on-demand code generation and instance-level optimization, the approach eliminates reliance on fixed query engine architectures. Empirical evaluation on the TPC-H benchmark and a newly designed data-leakage-resistant benchmark demonstrates that the proposed method significantly outperforms established systems, including DuckDB, Umbra, MonetDB, ClickHouse, and PostgreSQL.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Data Mining & Knowledge Management: Intelligent Query Processing
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Traditional query processing relies on engines that are carefully optimized and engineered by many experts. However, new techniques and user requirements evolve rapidly, and existing systems often cannot keep pace. At the same time, these systems are difficult to extend due to their internal complexity, and developing new systems requires substantial engineering effort and cost. In this paper, we argue that recent advances in Large Language Models (LLMs) are starting to shape the next generation of query processing systems. We propose using LLMs to synthesize execution code for each incoming query, instead of continuously building, extending, and maintaining complex query processing engines. As a proof of concept, we present GenDB, an LLM-powered agentic system that generates instance-optimized and customized query execution code tailored to specific data, workloads, and hardware resources. We implemented an early prototype of GenDB that uses Claude Code Agent as the underlying component in the multi-agent system, and we evaluate it on OLAP workloads. We use queries from the well-known TPC-H benchmark and also construct a new benchmark designed to reduce potential data leakage from LLM training data. We compare GenDB with state-of-the-art query engines, including DuckDB, Umbra, MonetDB, ClickHouse, and PostgreSQL. GenDB achieves significantly better performance than these systems. Finally, we discuss the current limitations of GenDB and outline future extensions and related research challenges.

Problem

• query processing
• extensibility
• engineering cost
• system evolution
• database engines

Innovation

• Large Language Models
• Query Processing
• Code Synthesis
• GenDB
• Instance-Optimized Execution