cs.IRNov 10, 2026

Controlled Knowledge Engineering for Taxonomy Induction with Tool-Grounded LLM Agents and Runtime-Adaptive Policies

Authors: Jonas Limniatis, Bennet Schaarmann, Georg Reuber, Robert Stahlbock

Organizations: Lufthansa Technik, Hamburg 22335, Germany · Lufthansa Industry Solutions, Norderstedt 22848, Germany · University of Hamburg Business School, Hamburg 20145, Germany · Nordakademie, University of Applied Sciences, Elmshorn 25337, Germany · 

Abstract

Taxonomies are structured knowledge representations that support semantic search, recommendation, product catalog organization, and retrieval-augmented generation. Their automated construction from a fixed set of candidate entities requires more than plausible text generation: the resulting hierarchy must be complete, structurally valid, and semantically coherent. Large Language Models (LLMs) are promising for this task, but iterative free-form generation remains vulnerable to omitted or hallucinated entities, invalid hierarchical relations, and inconsistent organizational principles. We introduce TIGA (Taxonomy Induction with Tool-Grounded Agents), a knowledge-engineering architecture that formulates taxonomy induction as an iterative decision process over an explicit state and constrained action space. TIGA combines executable taxonomy-editing tools, an memory that records tool calls, rationales, and outcomes, and a runtime-adaptive organizational policy that the agent revises during inference. An optional global reviewer evaluates the constructed taxonomy against the candidate set and the active policy. We evaluate TIGA on four benchmark taxonomies using two LLM backbones and compare it with single-shot and iterative prompting-based baselines. TIGA achieves the strongest structural-quality results in most evaluated configurations, but does not dominate on every precision measure. The gains are accompanied by substantially higher token consumption, API-call volume, and inference time. Ablation results show consistent benefits from the policy and interaction-memory components, whereas the effect of global review depends on the dataset and the available revision budget. These findings characterize tool grounding and runtime policy adaptation as promising but costly mechanisms for improving the controlled construction of structured knowledge representations.

Figures & tables

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. SPARROW: Scalable Taxonomy Induction via Structure-Preserving Partitioning and Constraint-Guided Merging

    Sep 7, 2026Yirui Zhang, Yixuan Tang, Yandong Sun +2Spectral ClusteringTaxonomy Induction

  2. TaSR-RAG: Taxonomy-guided Structured Reasoning for Retrieval-Augmented Generation

    Mar 10, 2026Jiashuo Sun, Yixuan Xie, Jimeng Shi +2Structured RAGRetrieval-Augmented Generation

  3. ReLTEx: Reliable LLM-based Taxonomy Expansion

    Aug 11, 2026Zeinab Ghamlouch, Mehwish AlamLLM Hallucination MitigationLLM Reliability