Chatty-KG: A Multi-Agent AI System for On-Demand Conversational Question Answering over Knowledge Graphs
Reham Omar, Abdelghny Orogat, Ibrahim Abdelaziz, Omij Mangukiya, Panos Kalnis, and Essam Mansour

TL;DR
Chatty-KG is a multi-agent system that enhances conversational question answering over knowledge graphs by combining retrieval, dialogue understanding, and structured query generation, outperforming existing methods in accuracy and efficiency.
Contribution
It introduces a modular multi-agent framework that integrates retrieval and structured execution for multi-turn KGQA without fine-tuning or pre-processing.
Findings
Outperforms state-of-the-art baselines in F1 and P@1 scores
Supports both single-turn and multi-turn conversations effectively
Compatible with various large language models, including commercial and open-weight ones
Abstract
Conversational Question Answering over Knowledge Graphs (KGs) combines the factual grounding of KG-based QA with the interactive nature of dialogue systems. KGs are widely used in enterprise and domain applications to provide structured, evolving, and reliable knowledge. Large language models (LLMs) enable natural and context-aware conversations, but lack direct access to private and dynamic KGs. Retrieval-augmented generation (RAG) systems can retrieve graph content but often serialize structure, struggle with multi-turn context, and require heavy indexing. Traditional KGQA systems preserve structure but typically support only single-turn QA, incur high latency, and struggle with coreference and context tracking. To address these limitations, we propose Chatty-KG, a modular multi-agent system for conversational QA over KGs. Chatty-KG combines RAG-style retrieval with structured…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Advanced Graph Neural Networks · Multimodal Machine Learning Applications
