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

arXiv: https://arxiv.org/abs/2603.02081 · HTML: https://mlsanity.com/paper/2603.02081/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 61 references that are in the map.
- First posted on arXiv 2 Mar 2026.

## Builds on (most cited first, 17 of 17)

- [Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation](https://mlsanity.com/paper/2308.15363/) (2023)
- [SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks](https://mlsanity.com/paper/2602.12670/) (2026)
- [CodeS: Towards Building Open-source Language Models for Text-to-SQL](https://mlsanity.com/paper/2402.16347/) (2024)
- [GPTuner: A Manual-Reading Database Tuning System via GPT-Guided Bayesian Optimization](https://mlsanity.com/paper/2311.03157/) (2023)
- [DB-BERT: a Database Tuning Tool that "Reads the Manual"](https://mlsanity.com/paper/2112.10925/) (2021)
- [λ-Tune: Harnessing Large Language Models for Automated Database System Tuning](https://mlsanity.com/paper/2411.03500/) (2024)
- [Can Large Language Models Be Query Optimizer for Relational Databases?](https://mlsanity.com/paper/2502.05562/) (2025)
- [E2ETune: End-to-End Knob Tuning via Fine-tuned Generative Language Model](https://mlsanity.com/paper/2404.11581/) (2024)
- [Building Efficient Query Engines in a High-Level Language](https://mlsanity.com/paper/1612.05566/) (2016)
- [Are Your LLM-based Text-to-SQL Models Secure? Exploring SQL Injection via Backdoor Attacks](https://mlsanity.com/paper/2503.05445/) (2025)
- [SQLBarber: A System Leveraging Large Language Models to Generate Customized and Realistic SQL Workloads](https://mlsanity.com/paper/2507.06192/) (2025)
- [SEFRQO: A Self-Evolving Fine-Tuned RAG-Based Query Optimizer](https://mlsanity.com/paper/2508.17556/) (2025)
- [Rethinking Analytical Processing in the GPU Era](https://mlsanity.com/paper/2508.04701/) (2025)
- [Are LLMs Ready for TOON? Benchmarking Structural Correctness-Sustainability Trade-offs in Novel Structured Output Formats](https://mlsanity.com/paper/2601.12014/) (2026)
- [Efficient and Provable Multi-Query Optimization](https://mlsanity.com/paper/1512.02568/) (2015)
- [GenJoin: Conditional Generative Plan-to-Plan Query Optimizer that Learns from Subplan Hints](https://mlsanity.com/paper/2411.04525/) (2024)
- [PBench: Workload Synthesizer with Real Statistics for Cloud Analytics Benchmarking](https://mlsanity.com/paper/2506.16379/) (2025)

## Built on by (most cited first, 1 of 1)

- [Demonstrating GenDB: Instance-Optimized and Customized Query Processing Code Generation via LLM Agents](https://mlsanity.com/paper/2607.20630/) (2026)

## Abstract (arXiv)

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.