QueryGym: Step-by-Step Interaction with Relational Databases
This addresses the need for better evaluation frameworks in database querying research, though it appears incremental as it builds on existing interactive environment concepts.
The paper tackles the problem of evaluating LLM-based query planning agents by introducing QueryGym, an interactive environment that requires agents to construct explicit sequences of relational algebra operations, resulting in an engine-agnostic and transparent testbed for research.
We introduce QueryGym, an interactive environment for building, testing, and evaluating LLM-based query planning agents. Existing frameworks often tie agents to specific query language dialects or obscure their reasoning; QueryGym instead requires agents to construct explicit sequences of relational algebra operations, ensuring engine-agnostic evaluation and transparent step-by-step planning. The environment is implemented as a Gymnasium interface that supplies observations -- including schema details, intermediate results, and execution feedback -- and receives actions that represent database exploration (e.g., previewing tables, sampling column values, retrieving unique values) as well as relational algebra operations (e.g., filter, project, join). We detail the motivation and the design of the environment. In the demo, we showcase the utility of the environment by contrasting it with contemporary LLMs that query databases. QueryGym serves as a practical testbed for research in error remediation, transparency, and reinforcement learning for query generation. For the associated demo, see https://ibm.biz/QueryGym.