{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T20:57:02Z","timestamp":1775595422145,"version":"3.50.1"},"reference-count":54,"publisher":"Association for Computing Machinery (ACM)","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. ACM Manag. Data"],"published-print":{"date-parts":[[2026,4,2]]},"abstract":"<jats:p>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 execution by generating SPARQL queries through task-specialized LLM agents. These agents collaborate for contextual interpretation, dialogue tracking, entity and relation linking, and efficient query planning, enabling accurate and low-latency translation of natural questions into executable queries. Experiments on large and diverse KGs show that CHATTY-KG significantly outperforms state-of-the-art baselines in both single-turn and multi-turn settings, achieving higher F1 and P@1 scores. Its modular design preserves dialogue coherence and supports evolving KGs without fine-tuning or preprocessing. Evaluations with commercial (e.g., GPT-4o, Gemini-2.0) and open-weight (e.g., Phi-4, Gemma 3) LLMs confirm broad compatibility and stable performance. Overall, CHATTY-KG unifies conversational flexibility with structured KG grounding, offering a scalable and extensible approach for reliable multi-turn KGQA.<\/jats:p>","DOI":"10.1145\/3786632","type":"journal-article","created":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T17:54:13Z","timestamp":1775584453000},"page":"1-26","source":"Crossref","is-referenced-by-count":0,"title":["Chatty-KG: A Multi-Agent AI System for On-Demand Conversational Question Answering over Knowledge Graphs"],"prefix":"10.1145","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6233-2092","authenticated-orcid":false,"given":"Reham","family":"Omar","sequence":"first","affiliation":[{"name":"Concordia University, Montreal, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2373-5375","authenticated-orcid":false,"given":"Abdelghny","family":"Orogat","sequence":"additional","affiliation":[{"name":"Concordia University, Montreal, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1449-5115","authenticated-orcid":false,"given":"Ibrahim","family":"Abdelaziz","sequence":"additional","affiliation":[{"name":"IBM Research, Yorktown Heights, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2364-3511","authenticated-orcid":false,"given":"Omij","family":"Mangukiya","sequence":"additional","affiliation":[{"name":"Concordia University, Montreal, QC, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5060-1360","authenticated-orcid":false,"given":"Panos","family":"Kalnis","sequence":"additional","affiliation":[{"name":"Kaust, Thuwal, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6851-6351","authenticated-orcid":false,"given":"Essam","family":"Mansour","sequence":"additional","affiliation":[{"name":"Concordia University, Montreal, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,7]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","unstructured":"Marah I Abdin Jyoti Aneja Harkirat S. Behl S\u00e9bastien Bubeck Ronen Eldan and et al. 2024. Phi-4 Technical Report. CoRR Vol. abs\/2412.08905 (2024). arXiv:2412.08905 https:\/\/doi.org\/10.48550\/arXiv.2412.08905","DOI":"10.48550\/arXiv.2412.08905"},{"key":"e_1_2_1_2_1","unstructured":"AI@Meta. 2024. Llama 3.1 Model Card. https:\/\/github.com\/meta-llama\/llama-models\/blob\/main\/models\/llama3_1\/MODEL_CARD.md"},{"key":"e_1_2_1_3_1","volume-title":"Proceedings of the International Semantic Web Conference, Posters & Demonstrations Track (ISWC)","volume":"1272","author":"Ceccarelli Diego","year":"2014","unstructured":"Diego Ceccarelli, Claudio Lucchese, Salvatore Orlando, Raffaele Perego, and Salvatore Trani. 2014. Dexter 2.0 - an Open Source Tool for Semantically Enriching Data. In Proceedings of the International Semantic Web Conference, Posters & Demonstrations Track (ISWC), Vol. 1272. 417-420. http:\/\/ceur-ws.org\/Vol-1272\/paper_127.pdf"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498488"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531815"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591682"},{"key":"e_1_2_1_7_1","unstructured":"DBLP release. 2022. https:\/\/dblp.org\/rdf\/release\/dblp-2022-06-01.nt.gz."},{"key":"e_1_2_1_8_1","unstructured":"DeepSeek-AI Aixin Liu Bei Feng Bing Xue Bingxuan Wang and et al. 2024. DeepSeek-V3 Technical Report. CoRR Vol. abs\/2412.19437 (2024). arXiv:2412.19437 https:\/\/arxiv.org\/abs\/2412.19437"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-1423"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3184558.3191541"},{"key":"e_1_2_1_11_1","unstructured":"YAGO downloads. 2022. https:\/\/yago-knowledge.org\/downloads\/yago-4."},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00671-6_7"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2404.16130"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2017.2766634"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-88361-4_8"},{"key":"e_1_2_1_16_1","unstructured":"IBM Research. 2024. Granite Foundation Models. https:\/\/www.ibm.com\/downloads\/documents\/us-en\/10a99803c92fdb35"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2021.EACL-MAIN.74"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2310.06825"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","unstructured":"Aishwarya Kamath Johan Ferret Shreya Pathak Nino Vieillard Ramona Merhej and et al. 2025. Gemma 3 Technical Report. CoRR Vol. abs\/2503.19786 (2025). arXiv:2503.19786 https:\/\/doi.org\/10.48550\/arXiv.2503.19786","DOI":"10.48550\/arXiv.2503.19786"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.339"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_2_1_22_1","volume-title":"Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa.","author":"Kojima Takeshi","year":"2022","unstructured":"Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. Large Language Models are Zero-Shot Reasoners. In Advances in Neural Information Processing Systems : Annual Conference on Neural Information Processing Systems (NeurIPS). http:\/\/papers.nips.cc\/paper_files\/paper\/2022\/hash\/8bb0d291acd4acf06ef112099c16f326-Abstract-Conference.html"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.3233\/SW-140134"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2020.ACL-MAIN.703"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3650203.3663334"},{"key":"e_1_2_1_27_1","volume-title":"Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90% ChatGPT Quality. https:\/\/lmsys.org\/blog\/2023-03-30-vicuna\/","author":"Org LMSYS","year":"2023","unstructured":"LMSYS Org. 2023. Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90% ChatGPT Quality. https:\/\/lmsys.org\/blog\/2023-03-30-vicuna\/"},{"key":"e_1_2_1_28_1","unstructured":"MAG records. 2022. https:\/\/zenodo.org\/record\/4617285#.YrNszNLMJhH."},{"key":"e_1_2_1_29_1","unstructured":"Yohei Nakajima. 2023. Task-driven autonomous agent. https:\/\/github.com\/yoheinakajima\/babyagi"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588911"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3709681"},{"key":"e_1_2_1_32_1","volume-title":"https:\/\/openai.com\/index\/hello-gpt-4o\/","author":"AI.","year":"2024","unstructured":"OpenAI. 2024. GPT-4o. (2024). https:\/\/openai.com\/index\/hello-gpt-4o\/"},{"key":"e_1_2_1_33_1","article-title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, and et al., 2020. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. Journal of machine learning research, Vol. 21 (2020), 140:1-140:67. https:\/\/jmlr.org\/papers\/v21\/20-074.html","journal-title":"Journal of machine learning research"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2408.00118"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2308.12950"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-1243"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.272"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","unstructured":"Liang Shi Zhengju Tang Nan Zhang Xiaotong Zhang and Zhi Yang. 2025. A Survey on Employing Large Language Models for Text-to-SQL Tasks. ACM Comput. Surv. (2025). doi:10.1145\/3737873","DOI":"10.1145\/3737873"},{"key":"e_1_2_1_39_1","unstructured":"Significant Gravitas. 2023. Auto-GPT: An Autonomous GPT-4 Experiment. https:\/\/github.com\/Significant-Gravitas\/Auto-GPT"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2412.05299"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-49461-2_34"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2403.05530"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68204-4_22"},{"key":"e_1_2_1_44_1","unstructured":"Ricardo Usbeck Ria Gusmita Axel-Cyrille Ngomo and Muhammad Saleem. 2018. 9th Challenge on Question Answering over Linked Data (QALD-9). In Joint proceedings of the Workshop on Semantic Deep Learning (SemDeep-4) and NLIWoD4: Natural Language Interfaces for the Web of Data (NLIWOD-4) and 9th Question Answering over Linked Data challenge (QALD-9) co-located with International Semantic Web Conference (ISWC) Vol. 2241. 58-64. http:\/\/ceur-ws.org\/Vol-2241\/paper-06.pdf"},{"key":"e_1_2_1_45_1","volume-title":"Proceedings of the Advances in neural information processing systems (NeurIPS), 5998-6008","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, and Llion Jones et al., 2017. Attention is All you Need. In Proceedings of the Advances in neural information processing systems (NeurIPS), 5998-6008. https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/2629489"},{"key":"e_1_2_1_47_1","volume-title":"Frontiers of Computer Science","volume":"18","author":"Wang Lei","year":"2024","unstructured":"Lei Wang, Chen Ma, Xueyang Feng, Zeyu Zhang, Hao Yang, Jingsen Zhang, Zhiyuan Chen, Jiakai Tang, Xu Chen, Yankai Lin, et al., 2024b. A survey on large language model based autonomous agents. Frontiers of Computer Science, Vol. 18, 6 (2024)."},{"key":"e_1_2_1_48_1","volume-title":"Forty-first International Conference on Machine Learning.","author":"Wang Xingyao","year":"2024","unstructured":"Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, Hao Peng, and Heng Ji. 2024a. Executable code actions elicit better LLM agents. In Forty-first International Conference on Machine Learning."},{"key":"e_1_2_1_49_1","unstructured":"Jason Wei Xuezhi Wang Dale Schuurmans Maarten Bosma Brian Ichter and et al. 2022. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. In Advances in Neural Information Processing Systems: Annual Conference on Neural Information Processing Systems (NeurIPS). http:\/\/papers.nips.cc\/paper_files\/paper\/2022\/hash\/9d5609613524ecf4f15af0f7b31abca4-Abstract-Conference.html"},{"key":"e_1_2_1_50_1","unstructured":"Tianbao Xie Fan Zhou Zhoujun Cheng Peng Shi Luoxuan Weng and et al. 2023. OpenAgents: An Open Platform for Language Agents in the Wild. CoRR Vol. abs\/2310.10634 (2023). arXiv:2310.10634 https:\/\/arxiv.org\/abs\/2310.10634"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","unstructured":"An Yang Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng and et al. 2024b. Qwen2.5 Technical Report. CoRR Vol. abs\/2412.15115 (2024). arXiv:2412.15115 https:\/\/doi.org\/10.48550\/arXiv.2412.15115","DOI":"10.48550\/arXiv.2412.15115"},{"key":"e_1_2_1_52_1","volume-title":"Agentoccam: A simple yet strong baseline for llm-based web agents. arXiv preprint arXiv:2410.13825","author":"Yang Ke","year":"2024","unstructured":"Ke Yang, Yao Liu, Sapana Chaudhary, Rasool Fakoor, Pratik Chaudhari, George Karypis, and Huzefa Rangwala. 2024a. Agentoccam: A simple yet strong baseline for llm-based web agents. arXiv preprint arXiv:2410.13825 (2024)."},{"key":"e_1_2_1_53_1","volume-title":"ReAct: Synergizing Reasoning and Acting in Language Models. In The International Conference on Learning Representations, ICLR. https:\/\/openreview.net\/forum?id=WE_vluYUL-X","author":"Yao Shunyu","unstructured":"Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, and et al., 2023. ReAct: Synergizing Reasoning and Acting in Language Models. In The International Conference on Learning Representations, ICLR. https:\/\/openreview.net\/forum?id=WE_vluYUL-X"},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2610525"}],"container-title":["Proceedings of the ACM on Management of Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3786632","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T19:57:53Z","timestamp":1775591873000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3786632"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,2]]},"references-count":54,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,4,2]]}},"alternative-id":["10.1145\/3786632"],"URL":"https:\/\/doi.org\/10.1145\/3786632","relation":{},"ISSN":["2836-6573"],"issn-type":[{"value":"2836-6573","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,2]]}}}