AGENTiGraph: A Multi-Agent Knowledge Graph Framework for Interactive, Domain-Specific LLM Chatbots
Authors:
- Xinjie ZhaoXZXinjie Zhao
- Moritz BlumMBMoritz Blum
- Fan GaoFGFan Gao
- Yingjian ChenYCYingjian Chen
- Boming YangBYBoming Yang
- Luis Marquez-CarpinteroLMLuis Marquez-Carpintero
- Mónica Pina-NavarroMPMónica Pina-Navarro
- Yanran FuYFYanran Fu
- So MorikawaSMSo Morikawa
- Yusuke IwasawaYIYusuke Iwasawa
- Yutaka MatsuoYMYutaka Matsuo
- Chanjun ParkCPChanjun Park
Preprint
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.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- Factuality challenges in the era of large language models and opportunities for fact-checkingNature Machine Intelligence, 2024
- ChatGPT has entered the classroom: how LLMs could transform educationNature, 2023
- Modern Baselines for SPARQL Semantic Parsing2022
- Natural Language Interfaces to DataFoundations and Trends® in Databases, 2022
- Deriving Contextualised Semantic Features from BERT (and Other Transformer Model) Embeddings2021
- Generalizing from a Few ExamplesACM Computing Surveys, 2020
- Natural Questions: A Benchmark for Question Answering ResearchTransactions of the Association for Computational Linguistics, 2019
- Handling scalable approximate queries over NoSQL graph databases: Cypherf and the Fuzzy4S frameworkFuzzy Sets and Systems, 2018
- Cypher2018
- A Review of Relational Machine Learning for Knowledge GraphsProceedings of the IEEE, 2015