An LLM-Based Approach for Creating Multi-agent Systems

P. 81–91.

Rezunik L., Alexandrov D., Mikhail Prozorskiy

Multi-Agent Systems (MAS) can benefit from Large Language Models (LLMs), but hallucinations pose risks to decision-making. This paper introduces an approach for creating MAS based on LLMs and proposes a generalized architecture for such systems. We ensure that reasoning is conducted through predicate logic to minimize errors, and LLMs are exclusively utilized to translate natural language into Prolog, supported by our algorithm for generated code correction. In addition, a safety reasoning agent is introduced to validate facts and prevent rule violations. We evaluate this approach in a sample MAS, demonstrating accurate logical transformations. Results confirm that LLMs add value to MAS when combined with structured knowledge representation, offering opportunities for further exploration focused on scalability enhancement, optimizing efficiency and dynamic refining of ontologies.

Keywords: decision-making, принятие решений, логика предикатов, мультиагентные системы, ontology, онтологии, smart home, умный дом, LLM, predicate logic, Multi-agent, большие языковые модели

Publication based on the results of: Methods and algorithms for the use of intelligent agents in the development and refactoring of distributed software systems (2026)

In book

Intelligent Decision Technologies. Proceedings of the 17th KES-IDT 2025 Conference

Vol. 450. , Cham: Springer, 2026.