AGENTiGraph: A Multi-Agent Knowledge Graph Framework for Interactive, Domain-Specific LLM Chatbots

2025-08-04

AI Summary

To address the challenge of enabling non-technical users to construct and dynamically update domain-specific knowledge bases via natural language interaction, this paper proposes a multi-agent knowledge graph framework. The framework synergistically integrates large language models (LLMs) with structured knowledge graphs, supporting progressive graph construction and real-time updates without requiring expertise in formal query languages—achieved through intent classification, task planning, and automated knowledge fusion. It innovatively enables multi-turn dialogue-driven reasoning for complex tasks while ensuring controllability and explainability in compliance-sensitive scenarios. Evaluated on a 3,500-query educational-domain benchmark, the framework achieves 95.12% intent classification accuracy and 90.45% task execution success rate, substantially outperforming zero-shot baselines. The approach is particularly suited for high-reliability domains such as education, law, and healthcare.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Knowledge Representation and Reasoning: Knowledge Representation Languages
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

AGENTiGraph is a user-friendly, agent-driven system that enables intuitive interaction and management of domain-specific data through the manipulation of knowledge graphs in natural language. It gives non-technical users a complete, visual solution to incrementally build and refine their knowledge bases, allowing multi-round dialogues and dynamic updates without specialized query languages. The flexible design of AGENTiGraph, including intent classification, task planning, and automatic knowledge integration, ensures seamless reasoning between diverse tasks. Evaluated on a 3,500-query benchmark within an educational scenario, the system outperforms strong zero-shot baselines (achieving 95.12% classification accuracy, 90.45% execution success), indicating potential scalability to compliance-critical or multi-step queries in legal and medical domains, e.g., incorporating new statutes or research on the fly. Our open-source demo offers a powerful new paradigm for multi-turn enterprise knowledge management that bridges LLMs and structured graphs.

Problem

• Enables intuitive interaction with domain-specific data via knowledge graphs
• Allows non-technical users to build and refine knowledge bases visually
• Facilitates multi-round dialogues and dynamic updates without query languages

Innovation

• Agent-driven knowledge graph for domain-specific chatbots
• Visual interface for non-technical knowledge management
• Intent classification and dynamic knowledge integration