mlsanityData to 14 Oct 2026

EvoOntology: A Self-Evolving Ontology Layer for Data Agents

arXiv 2609.15779 ↗First posted 14 Sep 2026cs.AI cs.CL cs.DBcited by 2

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

also in 1 more
Abstract (arXiv)

Data agents aim to fulfill natural-language instructions over heterogeneous data, including tables, files, and databases. However, data agents face a challenging agent-data gap: heterogeneous data resides outside the agent, while the agent can access it (e.g., column names and file paths) only through generic tools. Existing approaches either let agents directly explore raw data sources or inject manually constructed semantic layers into prompts. However, neither scales well to large heterogeneous data sources nor adapts to different agent behaviors. In this paper, we introduce EvoOntology, a self-evolving ontology layer for data agents. EvoOntology encapsulates the ontology as an MCP server comprising a schema layer, a content layer, and a tool layer, enabling agents to actively query and interact with the ontology at runtime. To this end, we introduce a builder agent for autonomous ontology construction and a self-evolution loop that continuously refines the ontology through attribution-guided typed edits that are accepted only after a backbone-conditional paired evaluation. Experiments on three well-adopted data-agent benchmarks with four LLM backbones demonstrate that EvoOntology consistently outperforms strong baselines and existing semantic-layer approaches, effectively bridging the agent-data gap and enabling more effective interaction with heterogeneous data. Code: https://github.com/ruc-datalab/EvoOntology

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 25 of its 34 references that are in the map. First posted on arXiv 14 Sep 2026.

Builds on

25 of 34 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight Generation8 Jul
  2. 2024Data Interpreter: An LLM Agent For Data Science28 Feb
  3. 2023MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL18 Dec

Other references · 22

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  3. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  4. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  5. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,332
  6. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,139
  7. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,045
  8. 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 832
  9. 2015Compositional Semantic Parsing on Semi-Structured Tablescited by 515
  10. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 477
  11. 2024Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflowscited by 232
  12. 2024CodeS: Towards Building Open-source Language Models for Text-to-SQLcited by 187
10 more
  1. 2024CHESS: Contextual Harnessing for Efficient SQL Synthesiscited by 169
  2. 2023Data-Copilot: Bridging Billions of Data and Humans with Autonomous Workflowcited by 76
  3. 2023How to Prompt LLMs for Text-to-SQL: A Study in Zero-shot, Single-domain, and Cross-domain Settingscited by 58
  4. 2024RSL-SQL: Robust Schema Linking in Text-to-SQL Generationcited by 52
  5. 2023Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Modelscited by 46
  6. 2024E-SQL: Direct Schema Linking via Question Enrichment in Text-to-SQLcited by 35
  7. 2024PET-SQL: A Prompt-Enhanced Two-Round Refinement of Text-to-SQL with Cross-consistencycited by 27
  8. 2026Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agentscited by 27
  9. 2026CausalDetox: Causal Head Selection and Intervention for Language Model Detoxificationcited by 3
  10. 2024Schema-Aware Multi-Task Learning for Complex Text-to-SQLcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026From Existing Methods to New Research Ideas: Two Perspectives on Recursive Self-Improvementcited by 0
  2. 2026ECG-RSI: Recursive Self-Improvement through Targeted Electrocardiogram Waveform Evolutioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Towards Automated Ontology Generation from Unstructured Text: A Multi-Agent LLM Approach
  2. 2026SciToolAgent-Evo: An Ontology-Aware Self-Evolving Agent for Open-World Scientific Tool Acquisition
  3. 2025FDABench: A Benchmark for Data Agents on Analytical Queries over Heterogeneous Data
  4. 2026Data Agents: Agentic Data Systems
  5. 2025A Survey of Data Agents: Emerging Paradigm or Overstated Hype?
  6. 2025Data Agent: A Holistic Architecture for Orchestrating Data+AI Ecosystems
  7. 2026Do Data Agents Need Semantic Metadata? A Comparative Study in Agentic Data Retrieval
  8. 2025Evo-DKD: Dual-Knowledge Decoding for Autonomous Ontology Evolution in Large Language Models