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

TL;DR

AGENTiGraph is an interactive, user-friendly system that enables non-technical users to build and manage domain-specific knowledge graphs through natural language, enhancing LLM chatbot capabilities with dynamic, multi-turn reasoning.

Contribution

It introduces a flexible, visual framework for knowledge graph management integrated with LLMs, supporting multi-round dialogues and automatic knowledge updates without specialized query languages.

Findings

Achieved 95.12% classification accuracy on a 3,500-query educational benchmark.

Reached 90.45% success rate in executing multi-step tasks.

Demonstrated scalability to legal and medical domains for complex queries.

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.