Combining Logical Reasoning and LLMs Toward Creating Multi-Agent Smart Home Systems
https://doi.org/10.15514/ISPRAS-2025-37(4)-28
Abstract
The rapid advancement of AI technologies, particularly Large Language Models (LLMs), has sparked interest in their integration into Multi-Agent Systems (MAS). This holds substantial promise for applications such as smart homes, where it can significantly enhance user experience by optimizing comfort, energy efficiency, and security. Despite the potential benefits, the implementation of MAS based on LLMs faces several challenges, including the risks of hallucinations, scalability issues, and concerns about the reliability of these systems in real-world applications. This study explores the development of MAS incorporating LLMs, with a focus on mitigating hallucinations through the integration of formal logical models for knowledge representation and decision-making, along with other machine learning methods. To demonstrate the efficacy of this approach, we conducted experiments with a plant care module within a smart home system. The results show that our approach can significantly reduce hallucinations and enhance the overall reliability of the system. Further research will focus on refining these methods to enhance adaptability and scalability to ensure system’s functionality in real-world environments.
Supporting agencies: This work is an output of a research project implemented as part of the Basic Research Program at the National Research University Higher School of Economics (HSE University).
About the Authors
Lyudmila Aleksandrovna REZUNIK
NRU Higher School of Economics
Russian Federation
Russian Federation
Master of Software Engineering, HSE. Research interests: mobile application development, multi-agent systems, LLM, software architecture.
Mikhail Aleekseevich PROZORSKIY
NRU Higher School of Economics
Russian Federation
Russian Federation
Student at HSE, researcher at the Educational and Research Laboratory of Cloud and Mobile Technologies, HSE. Research interests: mobile application development, smart home systems, software architecture.
Dmitry Vladimirovich ALEXANDROV –
NRU Higher School of Economics
Russian Federation
Russian Federation
Dr. Sci. (Tech.), Professor, Head at the Educational and Research Laboratory of Cloud and Mobile Technologies, HSE. Research interests: methods and techniques of artificial intelligence, mobile application development, software development, knowledge engineering.
References
1. Janbi N., Katib I., Mehmood R. Distributed artificial intelligence: Taxonomy, review, framework, and reference architecture. Intelligent Systems with Applications, vol. 18, 2023, p. 200231. DOI: 10.1016/j.iswa.2023.200231.
2. Guo T., Chen X., Wang Y., Chang R., Pei S., Chawla N.V., Wiest O., Zhang X.N. Large language model based multi-agents: A survey of progress and challenges. arXiv preprint, 2024. DOI: 10.24963/ijcai.2024/890.
3. Christman J., Mele A.R. Autonomous agents: From self-control to autonomy. The Journal of Philosophy, vol. 96, no. 2, 1999, pp. 95–100. DOI: 10.2307/2564674.
4. Wei J., Wang X., Schuurmans D., Bosma M., Ichter B., Xia F., Chi E., Le Q.V., Zhou D. Chain-of-thought prompting elicits reasoning in large language models. arXiv preprint, vol. arXiv:2201.11903, 2023. Available at: https://arxiv.org/abs/2201.11903.
5. Wang H., Du X., Yu W., Chen Q., Zhu K., Chu Z., Yan L., Guan Y. Learning to break: Knowledge-enhanced reasoning in multi-agent debate system. Neurocomputing, vol. 618, 2025, p. 129063. Available at: https://www.sciencedirect.com/science/article/pii/S0925231224018344.
6. Jiang Y.-H., Li R., Zhou Y., Qi C., Hu H., Wei et al. AI agent for education: von Neumann multi-agent system framework. In Proc. of the 28th Global Chinese Conference on Computers in Education, 2024.
7. Nezhurina M., Cipolina-Kun L., Cherti M., Jitsev J. Alice in Wonderland: Simple tasks showing complete reasoning breakdown in state-of-the-art large language models. arXiv preprint, vol. arXiv:2406.02061, 2024. Available at: https://arxiv.org/abs/2406.02061.
8. Zeng Y., Rajasekharan A., Basu K., Wang H., Arias J., Gupta G. A reliable common-sense reasoning socialbot built using LLMs and goal-directed ASP. Theory and Practice of Logic Programming, vol. 24, no. 4, 2024. DOI: 10.1017/S147106842400022X.
9. OpenAI. GPT-4 Technical Report. arXiv preprint, vol. arXiv:2303.08774, 2024. Available at: https://arxiv.org/abs/2303.08774.
10. Wang Z., Liu J., Bao Q., Rong H., Zhang J. ChatLogic: Integrating logic programming with large language models for multi-step reasoning. arXiv preprint, vol. arXiv:2407.10162, 2024. Available at: https://arxiv.org/abs/2407.10162.
11. Lewis P.S.H., Perez E., Piktus A., Petroni F., Karpukhin V., Goyal N., Kuttler H., Lewis M., Yih W.-T., Rocktäschel T., Riedel S., Kiela D. Retrieval-augmented generation for knowledge-intensive NLP tasks. arXiv preprint, vol. arXiv:2005.11401, 2020. Available at: https://arxiv.org/abs/2005.11401.
12. Chen J., Hu P., Jiménez-Ruiz E., Holter O.M., Antonyrajah D., Horrocks I. OWL2Vec*: Embedding of OWL ontologies. arXiv preprint, vol. arXiv:2009.14654, 2020. Available at: https://arxiv.org/abs/2009.14654.
13. Modgil S., Fox J. A guardian agent approach to safety in medical multi-agent systems. In Safety and Security in Multiagent Systems, 2009.
14. Nimis J., Lockemann P.C. Robust multi-agent systems: The transactional conversation approach? 2004.
15. Cabalar P., Fabiano F., Gebser M., Gupta G., Swift T. Proceedings of the 40th International Conference on Logic Programming (ICLP 2024). In Electronic Proceedings in Theoretical Computer Science (EPTCS), University of Texas at Dallas, Dallas, TX, USA, Oct. 2024, pp. 69–77.
16. Lifschitz V. What is Answer Set Programming? In Proceedings of the National Conference on Artificial Intelligence, vol. 3, 2008, pp. 1594–1597.
17. Lin X., Wu Y.-C., Yang H., Zhang Y., Zhang Y., Ji J. CLMASP: Coupling large language models with answer set programming for robotic task planning. arXiv preprint, vol. arXiv:2406.03367, 2024. Available at: https://arxiv.org/abs/2406.03367.
18. Yang Z., Ishay A., Lee J. Coupling large language models with logic programming for robust and general reasoning from text. arXiv preprint, vol. arXiv:2307.07696, 2023. Available at: https://arxiv.org/abs/2307.07696.
Review
For citations:
REZUNIK L.A., PROZORSKIY M.A., ALEXANDROV – D.V. Combining Logical Reasoning and LLMs Toward Creating Multi-Agent Smart Home Systems. Proceedings of the Institute for System Programming of the RAS (Proceedings of ISP RAS). 2025;37(4):219-234. https://doi.org/10.15514/ISPRAS-2025-37(4)-28
Email this article 