Pneuma-Seeker: A Relational Reification Mechanism to Align AI Agents with Human Work over Relational Data

TL;DR

Pneuma-Seeker introduces a relational reification approach that iteratively refines user data needs into schemas, enabling more accurate and trustworthy AI-assisted data retrieval and analysis over relational data.

Contribution

It presents Pneuma-Seeker, a novel system that uses relational reification and an LLM-powered agentic architecture to improve alignment between AI agents and human data needs.

Findings

Achieves higher answer accuracy than state-of-the-art baselines.

Demonstrates effective operation over heterogeneous relational data.

Highlights importance of trust and inspectability in real-world deployment.

Abstract

When faced with data problems, many data workers cannot articulate their information need precisely enough for software to help. Although LLMs interpret natural-language requests, they behave brittly when intent is under-specified, e.g., hallucinating fields, assuming join paths, or producing ungrounded answers. We present Pneuma-Seeker, a system built around a central idea: relational reification. Pneuma-Seeker represents a user's evolving information need as a relational schema: a concrete, analysis-ready data model shared between user and system. Rather than answering prompts directly, Pneuma-Seeker iteratively refines this schema, then discovers and prepares relevant sources to construct a relation and executable program that compute the answer. Pneuma-Seeker employs an LLM-powered agentic architecture with conductor-style planning and macro- and micro-level context management to operate effectively over heterogeneous relational corpora. We evaluate Pneuma-Seeker across multiple domains against state-of-the-art academic and industrial baselines, demonstrating higher answer accuracy. Deployment in a real organization highlights trust and inspectability as essential requirements for LLM-mediated data systems.