Living organisms are assumed to produce same-species offspring^1,2. Here, we report a shift from this norm in Messor ibericus, an ant that lays individuals from two distinct species. In this life cycle, females must clone males of another species because they require their sperm to produce the worker caste. As a result, males from the same mother exhibit distinct genomes and morphologies, as they belong to species that diverged over 5 million years ago. The evolutionary history of this system appears as sexual parasitism³ that evolved into a natural case of cross-species cloning^4,5, resulting in the maintenance of a male-only lineage cloned through distinct species’ ova. We term females exhibiting this reproductive mode as xenoparous, meaning they give birth to other species as part of their life cycle.

Plovdiv faces significant air pollution challenges due to geographic, climatic, and industrial factors, making accurate air quality assessment critical. This study presents a hybrid multi-agent platform that integrates symbolic and sub-symbolic artificial intelligence to improve the reliability of air quality monitoring. The platform features a BDI agent, developed using JaCaMo, for processing real-time sensor measurements and a ReAct agent, implemented with LangChain, to incorporate external data sources and perform advanced analytics. By combining these AI approaches, the platform enhances data integration, detects anomalies, and resolves discrepancies between conflicting air quality reports. Furthermore, its scalable and adaptable architecture lays the foundation for future advancements in environmental monitoring. This research represents the first stage in developing an AI-powered system that supports more objective and data-driven decision-making for air quality management in Plovdiv.

This paper presents the design and implementation of an integrated software platform that connects air quality monitoring systems with smart agriculture tools, with a focus on secondary air quality standards. The study investigates the correlation between air pollution and the development of tomato crops in the Plovdiv region of Bulgaria. The system integrates two intelligent agents: Air Agent, responsible for analysing real-time pollutant data, and Farmer Agent, which monitors the vegetation dynamics of tomato plants. Experimental results from the 2023 growing season indicate that elevated concentrations of PM2.5 and PM10 during critical growth stages significantly inhibited both plant height and stem development. The proposed platform utilises ontologies, asynchronous communication protocols, and data analytics to provide actionable insights for farmers and to support the practical application of environmental standards in agriculture. These findings underscore the importance of incorporating secondary air quality considerations into agricultural decision-making and environmental policy.

This article summarizes the results of a research conducted to create an intelligent platform supporting small farmers growing vegetables. In Bulgaria, many farmers use relatively small areas for their production. Considering this situation, the platform is designed for regional use, trying to make maximum use of the specific climatic features of the monitored microdistrict. Consequently, special attention is paid to the possibilities of adapting the platform to the specific environment in which the observed plants grow. Thus, the platform is implemented as an agent-oriented system providing needed flexibility. The core of the platform is a personal assistant, which is responsible for tracking the vegetation cycle of the monitored crop and, upon detection of anomalies, preparing warnings to the farmer. The general architecture of the platform is also presented. In a distributed knowledge base, agriculture-specific knowledge are stored. Furthermore, a standardized interface for receiving data from the sensor networks located in the production areas is briefly described. Currently, the platform is being tested for monitoring four varieties of tomatoes grown on the territory of the national research center for potato breeding. Special attention is paid to the measurements carried out. Conclusions have been drawn that will help improve the platform.

This paper presents PLAM (Plovdiv Air Monitoring)—a regional multi-agent platform for air quality monitoring, semantic reasoning, and forecasting. The platform uses a hybrid architecture that combines two types of intelligent agents: classic BDI (Belief-Desire-Intention) agents for complex, goal-oriented behavior and planning, and ReAct agents based on large language models (LLM) for quick response, analysis, and interaction with users. The system integrates data from heterogeneous sources, including local IoT sensor networks and public external services, enriching it with a specialized OWL ontology of environmental norms. Based on this data, the platform performs comparative analysis, detection of anomalies and inconsistencies between measurements, as well as predictions using machine learning models. The results are visualized and presented to users via a web interface and mobile application, including personalized alerts and recommendations. The architecture demonstrates essential properties of an intelligent agent such as autonomy, proactivity, reactivity, and social capabilities. The implementation and testing in the city of Plovdiv demonstrate the system’s ability to provide a more objective and comprehensive assessment of air quality, revealing significant differences between measurements from different institutions. The platform offers a modular and adaptive design, making it applicable to other regions, and outlines future development directions, such as creating a specialized small language model and expanding sensor capabilities.