Symbolic Separation: Grounding Deep Agents in Knowledge Graphs for Trustworthy Operational Data Analytics
cs.AI
Submitted: 2026-09-15
Updated: 2026-09-15
Code: https://github.com/jlowin/fastmcp
License: http://creativecommons.org/licenses/by/4.0/
The gist: Generative AI promises natural language access to the massive numerical telemetry of data centers and Industry 4.0 installations, yet text-to-query and tool-using agents stay unreliable: even
Terminology
Abstract
Generative AI promises natural language access to the massive numerical telemetry of data centers and Industry 4.0 installations, yet text-to-query and tool-using agents stay unreliable: even frontier models answer little more than half of real-world database questions, and far fewer of the multi-step, operational ones, because the LLM must compose how heterogeneous sources relate and hallucinates the relations, not just the fields. We propose symbolic separation: a deep agent reasons freely but may act on data only through an ontology-constrained Virtual Knowledge Graph with deterministic pre-execution validation. Unlike a tool API's interface contract, this domain-semantic contract turns a complex question into one validated graph traversal instead of LLM-inferred joins. Instantiated as the Neurosymbolic Deep Analyst and evaluated on 49.9 TB of superconputer telemetry against a rigid workflow and a non-symbolic ablation, it raises end-to-end task success from 43% to 86%, prevents silent data-integrity errors that no syntactic check catches, and cuts token cost by 2.4x, letting a smaller on-premise model outperform a larger one.
Sources
- Integrating Large Language Models with Internet of Things Applications
- Managing Schema Evolution in NoSQL Data Stores
- Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph
- Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning
- Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning
- SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directions
- SPINACH: SPARQL-Based Information Navigation for Challenging Real-World Questions
- From Data Center IoT Telemetry to Data Analytics Chatbots -- Virtual Knowledge Graph is All You Need
- A Unified Ontology for Scalable Knowledge Graph-Driven Operational Data Analytics in High-Performance Computing Systems
- Online Job Failure Prediction in an HPC System
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection