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

2026-03-11

AI Summary

This work addresses the tendency of existing systems to generate hallucinations or erroneous responses when user intent is ambiguous. The authors propose a relational reification mechanism that iteratively transforms dynamic, vague information needs into shared relational schemas, enabling the discovery and integration of heterogeneous data sources to synthesize executable programs that accurately answer queries. By integrating a large language model agent architecture with imperative planning, the approach co-evolves analysis-ready data models under coordinated macro- and micro-context management, substantially enhancing human-system alignment and system verifiability. Experimental results demonstrate that the proposed system outperforms state-of-the-art academic and industrial baselines across multiple domains, with real-world deployments confirming its advantages in accuracy, trustworthiness, and inspectability.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Planning, Routing, and Scheduling: Planning with Language Models
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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.

Problem

• relational data
• information need
• natural-language requests
• LLM hallucination
• data workers

Innovation

• relational reification
• LLM-powered agentic architecture
• iterative schema refinement
• conductor-style planning
• heterogeneous relational data