Search papers, labs, and topics across Lattice.
This paper introduces Git4Data, a novel version-control layer designed specifically for relational databases, enabling AI agents to manage candidate states of data with Git-style operations like branching and merging directly through SQL. By leveraging immutable object storage and Multi-Version Concurrency Control (MVCC), Git4Data ensures that versioning costs are proportional to the size of changes rather than the entire dataset, significantly enhancing efficiency. The implementation in MatrixOne demonstrates up to tenfold performance improvements over existing solutions like DoltDB, highlighting the potential for better support of AI workflows in relational databases.
Git4Data achieves up to 10x faster version control for AI agents in relational databases, transforming how we manage data states.
Large Language Model (LLM) agents increasingly explore many candidate states of relational data in parallel, each of which should remain isolated, reproducible, and auditable, preferably through the same SQL interface used for ordinary data work. Existing tools support this requirement only partially: source-code version control does not scale to large datasets, whereas relational databases manage large data efficiently but rarely expose native branching, comparison, and merging. We present Git4Data, a database-native version-control layer for agentic workflows. Git4Data treats a database as a repository and a table as a versioned object, exposing Git-style operations (snapshot/tag, branch, diff, and merge with explicit conflict-resolution policies) through SQL extensions. Implemented in MatrixOne, a cloud-native relational database, Git4Data leverages immutable object storage and MVCC to make the cost of these operations proportional to the size of the change rather than the size of the data. On the BranchBench agentic branching workloads, Git4Data outperforms DoltDB by up to an order of magnitude. Overall, we believe this work sheds light on how relational databases can better support AI agents through efficient versioning.
