Chatty-KG: A Multi-Agent AI System for On-Demand Conversational Question Answering over Knowledge Graphs

Summary: Chatty-KG: modular multi-agent conversational KGQA; task-specialized LLM agents do context tracking, entity/relation linking, and query planning to synthesize SPARQL, preserving KG structure vs serialized-RAG. Supports on-demand, low-latency multi-turn QA over evolving/private KGs, with strong F1/P@1 gains. (summarized by gpt-5.4-mini on Apr 11 2026)

Paper ID: 7649
Venue: SIGMOD
Year: 2026
Pagerank: 5.093636e-05
Overall Rank: 10,437 | 28.40%
DOI: 10.1145/3786632

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

1. Reham Omar (Concordia University)
2. Abdelghny Orogat (Concordia University)
3. Ibrahim Abdelaziz (IBM)
4. Omij Mangukiya (Concordia University)
5. Panos Kalnis (King Abdullah University of Science and Technology)
6. Essam Mansour (Concordia University)

BibTeX Citation

@inproceedings{omar_sigmod26,
        title = {{Chatty-KG: A Multi-Agent AI System for On-Demand Conversational Question Answering over Knowledge Graphs}},
        author = {Omar, Reham and Orogat, Abdelghny and Abdelaziz, Ibrahim and Mangukiya, Omij and Kalnis, Panos and Mansour, Essam},
        series = {{SIGMOD} '26},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3786632},
        url = {https://dl.acm.org/doi/10.1145/3786632},
        year = {2026}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank

Outgoing Citations (Sorted by Pagerank)

Showing 3 of 3 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
3,981	Natural Language Question Answering over RDF — A Graph Data Driven Approach	2014	SIGMOD	6.9746167e-05
10,023	A Universal Question-Answering Platform for Knowledge Graphs	2023	SIGMOD	5.1757914e-05
10,663	Dialogue Benchmark Generation from Knowledge Graphs with Cost-Effective Retrieval-Augmented LLMs	2025	SIGMOD	5.093636e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	5,671	Question Answering Over Knowledge Graphs: Question Understanding Via Template Decomposition	2018	VLDB
2	3,699	KBQA: Learning Question Answering over QA Corpora and Knowledge Bases	2017	VLDB
3	10,916	LEGO-GraphRAG: Modularizing Graph-based Retrieval-Augmented Generation for Design Space Exploration	2025	VLDB
4	10,290	Skyline Retrieval meets Set-Cover Chunk Merging: A Cost-Effective RAG-Sketch for Long-Context LLM QA	2026	SIGMOD
5	4,886	Chat2Data: An Interactive Data Analysis System with RAG, Vector Databases and LLMs	2024	VLDB
6	4,308	AutoTQA: Towards Autonomous Tabular Question Answering through Multi-Agent Large Language Models	2024	VLDB
7	6,254	In-depth Analysis of Graph-based RAG in a Unified Framework	2025	VLDB
8	8,343	An Interactive Multi-modal Query Answering System with Retrieval-Augmented Large Language Models	2024	VLDB
9	10,023	A Universal Question-Answering Platform for Knowledge Graphs	2023	SIGMOD
10	10,663	Dialogue Benchmark Generation from Knowledge Graphs with Cost-Effective Retrieval-Augmented LLMs	2025	SIGMOD