5 papers
One Monitor Does Not Fit All: Formalism-Agnostic Runtime Verification for Agentic AI
Angelo Ferrando
Agentic AI systems combine model decisions, mutable state, tool calls, and delegation to external agents. Monitoring them requires observations from different execution boundaries,…
Predictive Varanus: Combining CSP Conformance Monitoring with Predictive LTL Runtime Verification
Angelo Ferrando, Matt Luckcuck, Pedro Ribeiro
Runtime Verification is well suited to autonomous and robotic systems because it checks the behaviour that is actually observed during execution. Its main limitation, however, is t…
Watchdogs and Oracles: Runtime Verification Meets Large Language Models for Autonomous Systems
Angelo Ferrando
Assuring the safety and trustworthiness of autonomous systems is particularly difficult when learning-enabled components and open environments are involved. Formal methods provide…
Expressive Reward Synthesis with the Runtime Monitoring Language
Daniel Donnelly, Angelo Ferrando, Francesco Belardinelli
A key challenge in reinforcement learning (RL) is reward (mis)specification, whereby imprecisely defined reward functions can result in unintended, possibly harmful, behaviours. In…
Varanus: Runtime Verification for CSP
Matt Luckcuck, Angelo Ferrando, Fatma Faruq
Autonomous systems are often used in changeable and unknown environments, where traditional verification may not be suitable. Runtime Verification (RV) checks events performed by a…