CHisAgent: A Multi-Agent Framework for Event Taxonomy Construction in Ancient Chinese Cultural Systems

2026-01-09

arXiv.org

AI Summary

This work addresses the limited performance of existing large language models on Chinese historical and cultural reasoning tasks and the high cost and poor scalability of manually constructing taxonomies of ancient Chinese events. To overcome these challenges, the authors propose CHisAgent, a multi-agent framework that introduces collaborative multi-agent mechanisms into the construction of knowledge systems for ancient Chinese history and culture. Through a three-stage pipeline—comprising an Inducer, an Expander, and an Enhancer—the framework enables bottom-up hierarchical event induction, top-down structural completion, and integration of external evidence. Leveraging large language models and combining structured historical records with domain knowledge, CHisAgent automatically constructs a comprehensive taxonomy of ancient Chinese events spanning political, military, diplomatic, and socio-cultural domains. The resulting taxonomy significantly outperforms baseline approaches in structural coherence and coverage and facilitates cross-cultural alignment analysis.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent/AI Theories and Architectures
• Knowledge Representation and Reasoning: Action, Change, and Causality

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• Web Mining and Content Analysis: Bridging structured and unstructured data

Abstract

Despite strong performance on many tasks, large language models (LLMs) show limited ability in historical and cultural reasoning, particularly in non-English contexts such as Chinese history. Taxonomic structures offer an effective mechanism to organize historical knowledge and improve understanding. However, manual taxonomy construction is costly and difficult to scale. Therefore, we propose \textbf{CHisAgent}, a multi-agent LLM framework for historical taxonomy construction in ancient Chinese contexts. CHisAgent decomposes taxonomy construction into three role-specialized stages: a bottom-up \textit{Inducer} that derives an initial hierarchy from raw historical corpora, a top-down \textit{Expander} that introduces missing intermediate concepts using LLM world knowledge, and an evidence-guided \textit{Enricher} that integrates external structured historical resources to ensure faithfulness. Using the \textit{Twenty-Four Histories}, we construct a large-scale, domain-aware event taxonomy covering politics, military, diplomacy, and social life in ancient China. Extensive reference-free and reference-based evaluations demonstrate improved structural coherence and coverage, while further analysis shows that the resulting taxonomy supports cross-cultural alignment.

Problem

• event taxonomy
• ancient Chinese history
• cultural reasoning
• large language models
• knowledge organization

Innovation

• multi-agent LLM framework
• event taxonomy construction
• historical reasoning
• Chinese cultural systems
• structured knowledge integration