Related papers: Operationalizing Reconstructive Authority: Runtime…
The rapid evolution to autonomous, agentic AI systems introduces significant risks due to their inherent unpredictability and emergent behaviors; this also renders traditional verification methods inadequate and necessitates a shift towards…
Contract automata have been introduced for specifying applications through behavioural contracts and for synthesising their orchestrations as finite state automata. This paper addresses the realisation of applications from contract automata…
A major challenge in autonomous vehicle research is modeling agent behaviors, which has critical applications including constructing realistic and reliable simulations for off-board evaluation and forecasting traffic agents motion for…
We introduce a resource adaptive agent mechanism which supports the user in interactive theorem proving. The mechanism uses a two layered architecture of agent societies to suggest appropriate commands together with possible command…
This article proposes a Model Reference Adaptive Control (MRAC) strategy to achieve fixed-time convergence of parameter estimation and tracking errors for unknown linear time-invariant systems, without relying on the persistence of…
Model Predictive Control (MPC) is widely used to achieve performance objectives, while enforcing operational and safety constraints. Despite its high performance, MPC often demands significant computational resources, making it challenging…
When faced with an execution failure, an intelligent robot should be able to identify the likely reasons for the failure and adapt its execution policy accordingly. This paper addresses the question of how to utilise knowledge about the…
Agentic AI systems - systems that can pursue goals through multi-step planning and tool-mediated action with limited direct supervision - are moving from experimental prototypes to enterprise deployments. This transition introduces tensions…
In reinforcement learning, it is common to let an agent interact for a fixed amount of time with its environment before resetting it and repeating the process in a series of episodes. The task that the agent has to learn can either be to…
Traditional software relies on contracts -- APIs, type systems, assertions -- to specify and enforce correct behavior. AI agents, by contrast, operate on prompts and natural language instructions with no formal behavioral specification.…
Automating scientific computing workflows requires more than generating executable code: autonomous systems must also select appropriate computational strategies, implement them faithfully, and ensure that the resulting outcomes remain…
This paper presents a framework for enforcing penalties on intelligent agents that do not comply with authorization or obligation policies in a changing environment. A framework is proposed to represent and reason about penalties in plans,…
This paper presents a fault-tolerant control scheme for constrained linear systems. First, a new variant of the Reference Governor (RG) called At Once Reference Governor (AORG) is introduced. The AORG is distinguished from the conventional…
LLM agents are increasingly used for code generation, but physics-based simulation poses a deeper challenge: natural-language descriptions of simulation models are inherently underspecified, and different admissible resolutions of implicit…
Compensation programming is typically used in the programming of web service compositions whose correct implementation is crucial due to their handling of security-critical activities such as financial transactions. While traditional…
Artificial intelligence systems are increasingly embedded as persistent, closed-loop components within cyber-physical, social, and institutional processes. Rather than producing isolated outputs, such systems operate continuously under…
In multi-agent system design, a crucial aspect is to ensure robustness, meaning that for a coalition of agents A, small violations of adversarial assumptions only lead to small violations of A's goals. In this paper we introduce a logical…
We present Springdrift, a persistent runtime for long-lived LLM agents. The system integrates an auditable execution substrate (append-only memory, supervised processes, git-backed recovery), a case-based reasoning memory layer with hybrid…
The specification and validation of robotics applications require bridging the gap between formulating requirements and systematic testing. This often involves manual and error-prone tasks that become more complex as requirements, design,…
We present a task-and-motion planning (TAMP) algorithm robust against a human operator's cooperative or adversarial interventions. Interventions often invalidate the current plan and require replanning on the fly. Replanning can be…