Demonstration of Pneuma-Seeker: Agentic System for Reifying and Fulfilling Information Needs on Tabular Data

TL;DR

Pneuma-Seeker is a system that helps data analysts refine vague questions into explicit specifications for relational data, using LLMs as transparent collaborators to improve data discovery and provenance tracking.

Contribution

This work introduces Pneuma-Seeker, a novel system that reifies user information needs as explicit relational specifications, enhancing iterative data exploration with LLMs.

Findings

Enabled iterative refinement of data queries.

Demonstrated effective use in procurement use cases.

Leveraged LLMs as transparent analytical collaborators.

Abstract

Data analysts working with relational data often start with vague or underspecified questions and refine them iteratively as they explore the data. To support this iterative process, we demonstrate Pneuma-Seeker, a system that reifies a user's information need as explicit, inspectable relational specifications, enabling iterative refinement of the information need, targeted data discovery, and provenance-aware execution. Through two real-world procurement use cases, we show how Pneuma-Seeker leverages LLMs as transparent, interactive analytical collaborators rather than opaque answer engines.