Related papers: Operationalizing Reconstructive Authority: Runtime…
Intelligent robots need to generate and execute plans. In order to deal with the complexity of real environments, planning makes some assumptions about the world. When executing plans, the assumptions are usually not met. Most works have…
Role-Based Access Control (RBAC) is a popular authorization model used to manage data-access constraints in a wide range of systems. RBAC usually defines the static view on the access rights. However, to ensure dependability of a system, it…
Principled accountability in the aftermath of harms is essential to the trustworthy design and governance of algorithmic decision making. Legal theory offers a paramount method for assessing culpability: putting the agent 'on the stand' to…
Controllable trajectory generation guided by high-level semantic decisions, termed meta-actions, is crucial for autonomous driving systems. A significant limitation of existing frameworks is their reliance on invariant meta-actions assigned…
Runtime verification of temporal properties is essential for ensuring the correctness and reliability of real-time systems, particularly in cyber-physical systems. A significant challenge in this domain is the effective prediction of…
Language model (LM) agents have demonstrated significant potential for automating real-world tasks, yet they pose a diverse array of potential, severe risks in safety-critical scenarios. In this work, we identify a significant gap between…
Large language models are increasingly used as natural-language interfaces to enterprise software, but their direct use as system operators remains unsafe. Model errors can propagate into unauthorized actions, malformed requests,…
One of the benefits of using executable specifications such as Behavioral Programming (BP) is the ability to align the system implementation with its requirements. This is facilitated in BP by a protocol that allows independent…
Autonomous AI agents increasingly issue side-effect-bearing actions: database mutations, refunds, payments, external commitments. We propose the Actuarial Action Interface (AAI), a deterministic runtime contract that prices each such action…
Compositional spatiotemporal reasoning often requires a system to invoke multiple heterogeneous specialists, such as geometric, temporal, topological, and trajectory agents. A central question is how such a system should route among…
This paper addresses the problem of providing runtime assurance for systems operating online under unknown and potentially time-varying data distributions. We propose Cost-Aware Adaptive Conformal Inference (ACI), a novel framework that…
Modern artificial intelligence (AI) systems act with a high degree of independence yet lack legal personhood-a paradox that fractures doctrines grounded in human-centric notions of mens rea and actus reus. This Article introduces…
Reinforcement learning (RL) allows to solve complex tasks such as Go often with a stronger performance than humans. However, the learned behaviors are usually fixed to specific tasks and unable to adapt to different contexts. Here we…
Recent years, multimodal models have made remarkable strides and pave the way for intelligent browser use agents. However, when solving tasks on real world webpages in multi-turn, long-horizon trajectories, current agents still suffer from…
As artificial agents become increasingly capable, what internal structure is *necessary* for an agent to act competently under uncertainty? Classical results show that optimal control can be *implemented* using belief states or world…
Tool-using language agents turn model decisions into external side effects: they read files, run scripts, call APIs, send messages, and invoke Model Context Protocol tools. This makes agent attacks different from jailbreaks. The harmful…
Current agentic frameworks underperform on long-horizon tasks. As reasoning depth increases, sequential orchestration becomes brittle, context windows impose hard limits that degrade performance, and opaque execution traces make failures…
Every system that performs effects has two boundaries: what it can do (expressiveness) and what governance covers (governance). In nearly all deployed AI systems, these boundaries are defined independently, creating three regions: governed…
Runtime enforcement is a dynamic analysis technique that uses monitors to enforce the behaviour specified by some correctness property on an executing system. The enforceability of a logic captures the extent to which the properties…
Runtime Verification deals with the question of whether a run of a system adheres to its specification. This paper studies runtime verification in the presence of partial knowledge about the observed run, particularly where input values may…