AGENTiGraph: A Multi-Agent Knowledge Graph Framework for Interactive, Domain-Specific LLM Chatbots
This provides a user-friendly solution for enterprise knowledge management in domains like legal and medical, though it appears incremental as it builds on existing LLM and knowledge graph techniques.
The researchers tackled the problem of enabling non-technical users to interact with and manage domain-specific data through natural language by developing AGENTiGraph, a multi-agent knowledge graph framework for LLM chatbots, which achieved 95.12% classification accuracy and 90.45% execution success on a 3,500-query benchmark in an educational scenario.
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.