We introduce agent-environment systems where the agent is stateful and executing a ReLU
recurrent neural network. We define and study their verification problem by providing …

Given the increasing calls for AI to be trustworthy and explainable there has been growing
attention to issues of safety and reliability in the context of AI systems. Indeed, over the past …

A key difficulty in deploying multi-agent systems (MAS) in critical applications is to ensure
that the MAS under development meets its intended specifications. Languages such as …

This paper outlines some of the key methods we developed towards the formal verification of
multiagent systems, covering both symbolic and connectionist systems. It discusses logic …

The advent of autonomous mobile multi-robot systems has driven innovation in both the
industrial and defense sectors. The integration of such systems in safety-and security-critical …

We introduce a semantics for reasoning about probabilistic multi-agent systems in which the
number of participants is not known at design-time. We define the parameterised model …

A Counter Abstraction Technique for the Verification of Probabilistic Swarm Systems Page 1 A
Counter Abstraction Technique for the Verification of Probabilistic Swarm Systems Alessio …

We study how stability can be maintained even after any set of at most k players leave their
groups, in the context of hedonic games. While stability properties ensure an outcome to be …

Synthesis of models and strategies is a very important problem in software engineering. The
main element here is checking the satisfiability of formulae expressing the specification of a …

We study the problem of verifying multi-agent systems composed of arbitrarily many neural-
symbolic agents. We introduce a novel parameterised model, where the parameter denotes …