AGENTiGraph: A Multi-Agent Knowledge Graph Framework for Interactive, Domain-Specific LLM Chatbots
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.
Cite
@article{arxiv.2508.02999,
title = {AGENTiGraph: A Multi-Agent Knowledge Graph Framework for Interactive, Domain-Specific LLM Chatbots},
author = {Xinjie Zhao and Moritz Blum and Fan Gao and Yingjian Chen and Boming Yang and Luis Marquez-Carpintero and Mónica Pina-Navarro and Yanran Fu and So Morikawa and Yusuke Iwasawa and Yutaka Matsuo and Chanjun Park and Irene Li},
journal= {arXiv preprint arXiv:2508.02999},
year = {2025}
}
Comments
CIKM 2025, Demo Track