Elena Yan

Explainability is more and more considered a crucial property to be featured by AI-based systems, including those engineered in terms of agents and multi-agent systems. This property is primarily important at the user level, to increase e.g., system trustworthiness, but can play an important role also at the engineering level, to support activities such as debugging and validation. In this paper, we focus on BDI agent systems and introduce a multi-level explainability framework to understand the system’s behaviour that targets different classes of users: developers who implement the system, software designers who verify the soundness and final users. A prototype implementation of a tool based on the JaCaMo platform for multi-agent systems is adopted to explore the idea in practice.

As the complexity of software systems rises, explainability - i.e. the ability of systems to provide explanations of their behaviour - becomes a crucial property. This is true for any AI-based systems, including autonomous systems that exhibit decision making capabilities such as multi-agent systems. Although explainability is generally considered useful to increase the level of trust for end-users, we argue it is also an interesting property for software engineers, developers, and designers to debug and validate the system’s behaviour. In this paper, we propose a multi-level explainability framework for BDI agents to generate explanations of a running system from logs at different levels of abstraction, tailored to different users and their needs. We describe the mapping from logs to explanations, and present a prototype tool based on the JaCaMo platform which implements the framework.

In increasingly autonomous and highly distributed multi-agent systems, centralized coordination becomes impractical and raises the need for governance and enforcement mechanisms from an agent-centric perspective. In our conceptual view, sanctioning norm enforcement is part of this agent-centric perspective and they aim at promoting norm compliance while preserving agents’ autonomy. The few works dealing with sanctioning norm enforcement and sanctions from the agent-centric perspective present limitations regarding the representation of sanctions and the comprehensiveness of their norm enforcement process. To address these drawbacks, we propose the NPL(s), an extension of the NPL normative programming language enriched with the representation of norms and sanctions as first-class abstractions. We also propose a BDI normative agent architecture embedding an engine for processing the NPL(s) language and a set of capabilities for approaching more comprehensively the sanctioning norm enforcement process. We apply our contributions in a case study for improving the robustness of agents’ decision-making in a production automation system.