mlsanityData to 14 Oct 2026

Symbolic Separation: Grounding Deep Agents in Knowledge Graphs for Trustworthy Operational Data Analytics

arXiv 2609.17107 ↗First posted 15 Sep 2026cs.AIcited by 0

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 28 of its 72 references that are in the map. First posted on arXiv 15 Sep 2026.

Builds on

28 of 72 references.

Closest ancestors · 1

Same direction, newest first

  1. 2026SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directions7 Mar

Other references · 27

  1. 2025Qwen3 Technical Reportcited by 8,820
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  4. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  5. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  6. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineeringcited by 1,737
  7. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  8. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 688
  9. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 668
  10. 2020A Survey on Knowledge Graphs: Representation, Acquisition and Applicationscited by 643
  11. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoningcited by 328
  12. 2023Grammar-Constrained Decoding for Structured NLP Tasks without Finetuningcited by 197
15 more
  1. 2023Can Knowledge Graphs Reduce Hallucinations in LLMs? : A Surveycited by 92
  2. 2024A Survey on Employing Large Language Models for Text-to-SQL Taskscited by 67
  3. 2017Deep Learning for IoT Big Data and Streaming Analytics: A Surveycited by 59
  4. 2025NL2SQL-BUGs: A Benchmark for Detecting Semantic Errors in NL2SQL Translationcited by 33
  5. 2025Large Language Models Meet Knowledge Graphs for Question Answering: Synthesis and Opportunitiescited by 31
  6. 2024SPINACH: SPARQL-Based Information Navigation for Challenging Real-World Questionscited by 27
  7. 2021Automating Data Science: Prospects and Challengescited by 18
  8. 2024Integrating Large Language Models with Internet of Things Applicationscited by 7
  9. 2022RUAD: unsupervised anomaly detection in HPC systemscited by 4
  10. 2021Operational Data Analytics in Practice: Experiences from Design to Deployment in Production HPC Environmentscited by 2
  11. 2025Rethinking Text-to-SQL: Dynamic Multi-turn SQL Interaction for Real-world Database Explorationcited by 2
  12. 2013Managing Schema Evolution in NoSQL Data Storescited by 1
  13. 2023Online Job Failure Prediction in an HPC Systemcited by 1
  14. 2025From Data Center IoT Telemetry to Data Analytics Chatbots -- Virtual Knowledge Graph is All You Needcited by 1
  15. 2026Generating Expressive and Customizable Evals for Timeseries Data Analysis Agents with AgentFuelcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Towards Trustworthy and Cost-Efficient Data Integration: From Na"ive RAG to Agentic RAG
  2. 2025HyDRA: A Hybrid-Driven Reasoning Architecture for Verifiable Knowledge Graphs
  3. 2026Towards Reliable AI Data Scientists: Data Agents with Workflow Harnesses
  4. 2025DeepAnalyze: Agentic Large Language Models for Autonomous Data Science
  5. 2025Data Agent: A Holistic Architecture for Orchestrating Data+AI Ecosystems
  6. 2026ElephantBroker: A Knowledge-Grounded Cognitive Runtime for Trustworthy AI Agents
  7. 2026Knowledge Graphs as the Missing Data Layer for LLM-Based Industrial Asset Operations
  8. 2025KARMA: Leveraging Multi-Agent LLMs for Automated Knowledge Graph Enrichment