# Automating Database-Native Function Code Synthesis with LLMs

arXiv: https://arxiv.org/abs/2604.06231 · HTML: https://mlsanity.com/paper/2604.06231/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 41 references that are in the map.
- First posted on arXiv 2 Apr 2026.

## Builds on (most cited first, 21 of 21)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [WizardCoder: Empowering Code Large Language Models with Evol-Instruct](https://mlsanity.com/paper/2306.08568/) (2023)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [CodeT: Code Generation with Generated Tests](https://mlsanity.com/paper/2207.10397/) (2022)
- [Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling](https://mlsanity.com/paper/2507.23370/) (2025)
- [LongCodeBench: Evaluating Coding LLMs at 1M Context Windows](https://mlsanity.com/paper/2505.07897/) (2025)
- [SWE-Dev: Building Software Engineering Agents with Training and Inference Scaling](https://mlsanity.com/paper/2506.07636/) (2025)
- [Optuna vs Code Llama: Are LLMs a New Paradigm for Hyperparameter Tuning?](https://mlsanity.com/paper/2504.06006/) (2025)
- [Piloting Copilot, Codex, and StarCoder2: Hot Temperature, Cold Prompts, or Black Magic?](https://mlsanity.com/paper/2210.14699/) (2022)
- [LibEvolutionEval: A Benchmark and Study for Version-Specific Code Generation](https://mlsanity.com/paper/2412.04478/) (2024)
- [RustEvo^2: An Evolving Benchmark for API Evolution in LLM-based Rust Code Generation](https://mlsanity.com/paper/2503.16922/) (2025)
- [Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs](https://mlsanity.com/paper/2601.17058/) (2026)
- [DBAIOps: A Reasoning LLM-Enhanced Database Operation and Maintenance System using Knowledge Graphs](https://mlsanity.com/paper/2508.01136/) (2025)
- [Optimization of Imperative Programs in a Relational Database](https://mlsanity.com/paper/1712.00498/) (2017)
- [PARROT: A Benchmark for Evaluating LLMs in Cross-System SQL Translation](https://mlsanity.com/paper/2509.23338/) (2025)
- [OpenMLDB: A Real-Time Relational Data Feature Computation System for Online ML](https://mlsanity.com/paper/2501.08591/) (2025)

## Built on by (most cited first, 2 of 2)

- [Are We Ready For An Agent-Native Memory System?](https://mlsanity.com/paper/2606.24775/) (2026)
- [AgenticDataBench: A Comprehensive Benchmark for Data Agents](https://mlsanity.com/paper/2607.01647/) (2026)

## Abstract (arXiv)

Database systems incorporate an ever-growing number of functions in their kernels (a.k.a., database native functions) for scenarios like new application support and business migration. This growth causes an urgent demand for automatic database native function synthesis. While recent advances in LLM-based code generation (e.g., Claude Code) show promise, they are too generic for database-specific development. They often hallucinate or overlook critical context because database function synthesis is inherently complex and error-prone, where synthesizing a single function may involve registering multiple function units, linking internal references, and implementing logic correctly. To this end, we propose DBCooker, an LLM-based system for automatically synthesizing database native functions. It consists of three components. First, the function characterization module aggregates multi-source declarations, identifies function units that require specialized coding, and traces cross-unit dependencies. Second, we design operations to address the main synthesis challenges: (1) a pseudo-code-based coding plan generator that constructs structured implementation skeletons by identifying key elements such as reusable referenced functions; (2) a hybrid fill-in-the-blank model guided by probabilistic priors and component awareness to integrate core logic with reusable routines; and (3) three-level progressive validation, including syntax checking, standards compliance, and LLM-guided semantic verification. Finally, an adaptive orchestration strategy unifies these operations with existing tools and dynamically sequences them via the orchestration history of similar functions. Results show that DBCooker outperforms other methods on SQLite, PostgreSQL, and DuckDB (34.55% higher accuracy on average), and can synthesize new functions absent in the latest SQLite (v3.50).