# An Agentic Hybrid Top-Down and Bottom-Up Approach to Knowledge Graph Generation

arXiv: https://arxiv.org/abs/2608.07023 · HTML: https://mlsanity.com/paper/2608.07023/

## 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 18 of its 27 references that are in the map.
- First posted on arXiv 7 Aug 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 18 of 18)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://mlsanity.com/paper/2305.03495/) (2023)
- [Goal-Driven Explainable Clustering via Language Descriptions](https://mlsanity.com/paper/2305.13749/) (2023)
- [TaxoGen: Unsupervised Topic Taxonomy Construction by Adaptive Term Embedding and Clustering](https://mlsanity.com/paper/1812.09551/) (2018)
- [HiExpan: Task-Guided Taxonomy Construction by Hierarchical Tree Expansion](https://mlsanity.com/paper/1910.08194/) (2019)
- [TaxoCom: Topic Taxonomy Completion with Hierarchical Discovery of Novel Topic Clusters](https://mlsanity.com/paper/2201.06771/) (2022)
- [JobBERT: Understanding Job Titles through Skills](https://mlsanity.com/paper/2109.09605/) (2021)
- [Making Large Language Models Better Data Creators](https://mlsanity.com/paper/2310.20111/) (2023)
- [TnT-LLM: Text Mining at Scale with Large Language Models](https://mlsanity.com/paper/2403.12173/) (2024)
- [Chain-of-Layer: Iteratively Prompting Large Language Models for Taxonomy Induction from Limited Examples](https://mlsanity.com/paper/2402.07386/) (2024)
- [TaxoAdapt: Aligning LLM-Based Multidimensional Taxonomy Construction to Evolving Research Corpora](https://mlsanity.com/paper/2506.10737/) (2025)
- [From Papers to Panoramas: Building Hierarchies of Scientific Literature at Scale](https://mlsanity.com/paper/2504.13834/) (2025)
- [Automatic Bottom-Up Taxonomy Construction: A Software Application Domain Study](https://mlsanity.com/paper/2409.15881/) (2024)
- [Efficient Text Encoders for Labor Market Analysis](https://mlsanity.com/paper/2505.24640/) (2025)
- [Creating a Fine Grained Entity Type Taxonomy Using LLMs](https://mlsanity.com/paper/2402.12557/) (2024)
- [Building Data-Driven Occupation Taxonomies: A Bottom-Up Multi-Stage Approach via Semantic Clustering and Multi-Agent Collaboration](https://mlsanity.com/paper/2509.15786/) (2025)

## Abstract (arXiv)

Organizing thousands of unstandardized, multilingual expertise declarations is a persistent challenge for Human Resources (HR) platforms, directly impacting downstream tasks like accurate talent matching. To address this, we propose a hybrid knowledge graph generation pipeline that grounds a Large Language Model (LLM) in the Wikidata multilingual Knowledge Graph (KG) while employing an agentic reflexion pattern to synthesize emerging concepts and their associated metadata. Unlike rigid top-down methods or fragmented bottom-up approaches, our system anchors recognized concepts to stable Knowledge Graph entities while dynamically creating new nodes and relational metadata for unrecognized skills. Executed across five stages, entity reconciliation, multilingual canonicalization, active curation, deduplication, and the iterative recovery of unmapped concepts, the system autonomously adapts to rapidly evolving, noisy skill mentions across five European languages. Ultimately, this pipeline provides a highly scalable, explicable, and self-healing framework for generating a comprehensive skills knowledge graph, from which a structured taxonomy is derived, using unstructured, noisy text.