J

Jacopo Tagliabue

Total Citations
447
h-index
11
Papers
2

Publications

#1 2602.10387v1 Feb 11, 2026

Making Databases Faster with LLM Evolutionary Sampling

Traditional query optimization relies on cost-based optimizers that estimate execution cost (e.g., runtime, memory, and I/O) using predefined heuristics and statistical models. Improving these heuristics requires substantial engineering effort, and even when implemented, these heuristics often cannot take into account semantic correlations in queries and schemas that could enable better physical plans. Using our DBPlanBench harness for the DataFusion engine, we expose the physical plan through a compact serialized representation and let the LLM propose localized edits that can be applied and executed. We then apply an evolutionary search over these edits to refine candidates across iterations. Our key insight is that LLMs can leverage semantic knowledge to identify and apply non-obvious optimizations, such as join orderings that minimize intermediate cardinalities. We obtain up to 4.78$\times$ speedups on some queries and we demonstrate a small-to-large workflow in which optimizations found on small databases transfer effectively to larger databases.

Federico Bianchi James Zou Mehmet Hamza Erol C. Greco Jacopo Tagliabue +1
0 Citations
#2 2602.02335v2 Feb 02, 2026

Building a Correct-by-Design Lakehouse. Data Contracts, Versioning, and Transactional Pipelines for Humans and Agents

Lakehouses are the default cloud platform for analytics and AI, but they become unsafe when untrusted actors concurrently operate on production data: upstream-downstream mismatches surface only at runtime, and multi-table pipelines can leak partial effects. Inspired by software engineering, we design Bauplan, a code-first lakehouse that aims to make (most) illegal states unrepresentable using familiar abstractions. Bauplan acts along three axes: typed table contracts to make pipeline boundaries checkable, Git-like data versioning for review and reproducibility, and transactional runs that guarantee pipeline-level atomicity. We report early results from a lightweight formal transaction model and discuss future work motivated by counterexamples.

Jacopo Tagliabue Weiming Sheng Jinlang Wang M. Barros Luca Bigon +1
0 Citations