CHisAgent: A Multi-Agent Framework for Event Taxonomy Construction in Ancient Chinese Cultural Systems
On the map: LLM agents and tool use → Multimodal and embodied agents
Abstract (arXiv)
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 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 textitInducer that derives an initial hierarchy from raw historical corpora, a top-down textitExpander that introduces missing intermediate concepts using LLM world knowledge, and an evidence-guided textitEnricher that integrates external structured historical resources to ensure faithfulness. Using the textitTwenty-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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use. Builds on 18 of its 38 references that are in the map. First posted on arXiv 9 Jan 2026.
Builds on
18 of 38 references.
References · 18
- 2022BERTopic: Neural topic modeling with a class-based TF-IDF procedurecited by 779
- 2024Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoningcited by 45
- 2019HiExpan: Task-Guided Taxonomy Construction by Hierarchical Tree Expansioncited by 31
- 2022TaxoCom: Topic Taxonomy Completion with Hierarchical Discovery of Novel Topic Clusterscited by 30
- 2019SetExpan: Corpus-Based Set Expansion via Context Feature Selection and Rank Ensemblecited by 25
- 2025TaxoAdapt: Aligning LLM-Based Multidimensional Taxonomy Construction to Evolving Research Corporacited by 23
- 2020Constructing Taxonomies from Pretrained Language Modelscited by 21
- 2023Prompting or Fine-tuning? A Comparative Study of Large Language Models for Taxonomy Constructioncited by 18
- 2025CULEMO: Cultural Lenses on Emotion -- Benchmarking LLMs for Cross-Cultural Emotion Understandingcited by 14
- 2021Time-Aware Ancient Chinese Text Translation and Inferencecited by 10
- 2024CodeTaxo: Enhancing Taxonomy Expansion with Limited Examples via Code Language Promptscited by 10
- 2024Large Language Models for Scholarly Ontology Generation: An Extensive Analysis in the Engineering Fieldcited by 10
6 more
- 2025Time Travel: A Comprehensive Benchmark to Evaluate LMMs on Historical and Cultural Artifactscited by 10
- 2025An Investigation into Value Misalignment in LLM-Generated Texts for Cultural Heritagecited by 8
- 2024A Unified Taxonomy-Guided Instruction Tuning Framework for Entity Set Expansion and Taxonomy Expansioncited by 7
- 2024CHisIEC: An Information Extraction Corpus for Ancient Chinese Historycited by 7
- 2025LLMTaxo: Leveraging Large Language Models for Constructing Taxonomy of Factual Claims from Social Mediacited by 5
- 2023Extending an Event-type Ontology: Adding Verbs and Classes Using Fine-tuned LLMs Suggestionscited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2025On Path to Multimodal Historical Reasoning: HistBench and HistAgent
- 2026Can LLMs Act as Historians? Evaluating Historical Research Capabilities of LLMs via the Chinese Imperial Examination
- 2026SAGE: From Direct Answering to Evidence-Grounded Inference for Chinese Ancient Document Understanding
- 2026Worlds Within Words: Translating Culture in Ancient Chinese Texts with Multi-Agent Coordination
- 2026CulMind: Benchmarking Multimodal Understanding and Reasoning in Chinese Cultural Heritage
- 2025Benchmarking Temporal Reasoning and Alignment Across Chinese Dynasties
- 2025Supervised Fine Tuning of Large Language Models for Domain Specific Knowledge Graph Construction:A Case Study on Hunan's Historical Celebrities
- 2026Beyond Similarity: Grounded Agentic Extraction and Expert-Adjudicated Evaluation of Intertextuality in Classical Chinese Histories