APPLICATION OF COOPERATIVE MULTI-AGENT SYSTEMS IN TERRITORIAL DEVELOPMENT ANALYSIS AND FORECASTING BASED ON DATA-DRIVEN MANAGEMENT
Svetlana S. Mikhailova, Soelma D. Danilova, Aleksey N. Timofeev
Financial University under the Government of the Russian Federation, Moscow, Russian Federation
Keywords: spatial development, analytical center, large language model, decision-making systems, LLM agents, multiagent approach
Abstract
The article is devoted to reducing the cognitive burden on human development in the field of spatial development of regions in the context of data-driven management. A model of a regional analytical center based on cooperative multiagency with LLM is proposed, including a formal description of the task, a project office of agents, a resource base (data, knowledge graphs, skills, rules) and a simulation model of the region. For transparency, Human in the Loop, LLM as a Judge, and Datalog validation schemes are used. A prototype has been developed for Java 25, Spring Boot 4, Angular 20, PostgreSQL 17. The scenario in the field of transportation in Buryatia shows that mutual verification of agents improves the quality of solutions developed for agricultural production.
|
