Related papers: Operationalizing Reconstructive Authority: Runtime…
Current AI systems increasingly operate in contexts where their outputs directly trigger real-world actions. Most existing approaches to AI safety, risk management, and governance focus on post-hoc validation, probabilistic risk estimation,…
Long-term autonomy of robotic systems implicitly requires dependable platforms that are able to naturally handle hardware and software faults, problems in behaviors, or lack of knowledge. Model-based dependable platforms additionally…
Large language model (LLM) agents increasingly issue API calls that mutate real systems, yet many current architectures pass stochastic model outputs directly to execution layers. We argue that this coupling creates a safety risk because…
Finite-state models are ubiquitous in the study of concurrent systems, especially controllers and servers that operate in a repetitive cycle. In this paper, we show how to extract finite state models from a run of a multi-threaded Java…
Software Engineering (SE) agents have shown promising abilities in supporting various SE tasks. Current SE agents remain fundamentally reactive, making decisions mainly based on conversation history and the most recent response. However,…
Runtime adaptability is often a crucial requirement for today's complex software systems. Several approaches use an architectural model as a runtime representation of a managed system for monitoring, reasoning and performing adaptation. To…
Known attempts to build autonomous robots rely on complex control architectures, often implemented with the Robot Operating System platform (ROS). Runtime adaptation is needed in these systems, to cope with component failures and with…
This chapter argues that the reliability of agentic and generative AI is chiefly an architectural property. We define agentic systems as goal-directed, tool-using decision makers operating in closed loops, and show how reliability emerges…
The advancement of automated vehicles introduces complex safety challenges, particularly in dynamic and unpredictable environments where AI-enabled perception systems must operate reliably. Ensuring compliance with safety standards such as…
Autonomous agent systems are governed by enforcement mechanisms that flag hard constraint violations at runtime. The Agent Control Protocol identifies a structural limit of such systems: a correctly-functioning enforcement engine can enter…
The action governor is an add-on scheme to a nominal control loop that monitors and adjusts the control actions to enforce safety specifications expressed as pointwise-in-time state and control constraints. In this paper, we introduce the…
Learned robot policies have consistently been shown to be versatile, but they typically have no built-in mechanism for handling the complexity of open environments, making them prone to execution failures; this implies that deploying…
The goal of Multi-Agent Path Finding (MAPF) is to find a set of paths for a fleet of agents moving in a shared environment such that the agents reach their goals without colliding with each other. In practice, some of the robots executing…
An agent must act on the situation before it, learn what it cannot yet represent, and model other agents well enough to coordinate. These faculties are usually realized by separate mechanisms, yet they share a failure mode: the situation…
Most governance frameworks assume that rules can be defined in advance, systems can be engineered to comply, and accountability can be applied after outcomes occur. This model worked when machines replaced physical labor or accelerated…
During the execution of Multi-Agent Path Finding (MAPF) plans in real-life applications, the MAPF assumption that the fleet's movement is perfectly synchronized does not apply. Since one or more of the agents may become delayed due to…
Imitation learning is a promising approach to end-to-end training of autonomous vehicle controllers. Typically the driving process with such approaches is entirely automatic and black-box, although in practice it is desirable to control the…
To achieve general-purpose utility, we argue that robots must evolve from passive executors into active Information Retrieval users. In strictly zero-shot settings where no prior demonstrations exist, robots face a critical information gap,…
Runtime enforcement is an increasingly popular and effective dynamic validation technique aiming to ensure the correct runtime behavior (w.r.t. a formal specification) of systems using a so-called enforcement monitor. In this paper we…
Real time model based control of high dimensional nonlinear systems presents severe computational challenges. Conventional reduced order model control relies heavily on expert tuning or parameter adaptation and seldom offers mechanisms for…