RV4JaCa -- Runtime Verification for Multi-Agent Systems
This work addresses security concerns in multi-agent systems for hybrid intelligence applications, such as healthcare decision-making, but it appears incremental as it applies existing runtime verification techniques to a specific domain.
The paper tackles the problem of ensuring secure communication in multi-agent systems by introducing a runtime verification approach using the JaCaMo framework, specifically implementing a monitor to control dialogue flow in natural language interactions for hospital bed allocation decision-making.
This paper presents a Runtime Verification (RV) approach for Multi-Agent Systems (MAS) using the JaCaMo framework. Our objective is to bring a layer of security to the MAS. This layer is capable of controlling events during the execution of the system without needing a specific implementation in the behaviour of each agent to recognise the events. MAS have been used in the context of hybrid intelligence. This use requires communication between software agents and human beings. In some cases, communication takes place via natural language dialogues. However, this kind of communication brings us to a concern related to controlling the flow of dialogue so that agents can prevent any change in the topic of discussion that could impair their reasoning. We demonstrate the implementation of a monitor that aims to control this dialogue flow in a MAS that communicates with the user through natural language to aid decision-making in hospital bed allocation.