Related papers: Right-to-Act: A Pre-Execution Non-Compensatory Dec…
AI-enabled decision-support systems aim to help medical providers rapidly make decisions with limited information during medical emergencies. A critical challenge in developing these systems is supporting providers in interpreting the…
AI systems are increasingly governed by natural language principles, yet a key challenge arising from reliance on language remains underexplored: interpretive ambiguity. As in legal systems, ambiguity arises both from how these principles…
Agentic AI systems increasingly act through tools, sub-agents, and external services, but governance controls are still commonly attached to prompts, dashboards, or post-hoc documentation. This creates a structural mismatch in regulated…
As the deployment of artificial intelligence (AI) is changing many fields and industries, there are concerns about AI systems making decisions and recommendations without adequately considering various ethical aspects, such as…
AI evaluations are an important component of the AI governance toolkit, underlying current approaches to safety cases for preventing catastrophic risks. Our paper examines what these evaluations can and cannot tell us. Evaluations can…
Event-driven scheduling policies are increasingly deployed in industrial environments, where decisions are made under asynchronous and partially observed system states. As a result, decision states are not temporally consistent, action…
Generative AI systems are increasingly used not only to produce content but also to retrieve data, invoke tools, and execute actions. This work examines the security and safety implications of that shift across content-level, model-level,…
Control evaluations measure whether monitoring and security protocols for AI systems prevent intentionally subversive AI models from causing harm. Our work presents the first control evaluation performed in an agent environment. We…
As Artificial Intelligence (AI) technologies continue to advance, protecting human autonomy and promoting ethical decision-making are essential to fostering trust and accountability. Human agency (the capacity of individuals to make…
Large language models (LLMs), initially developed for generative AI, are now evolving into agentic AI systems, which make decisions in complex, real-world contexts. Unfortunately, while their generative capabilities are well-documented,…
The more AI agents are deployed in scenarios with possibly unexpected situations, the more they need to be flexible, adaptive, and creative in achieving the goal we have given them. Thus, a certain level of freedom to choose the best path…
Artificial intelligence pipelines -- spanning data collection, model training, deployment, and post-deployment monitoring -- concentrate ethical risks that intensify with multimodal and agentic systems. Existing governance instruments,…
As Artificial Intelligence (AI) systems are integrated into more aspects of society, they offer new capabilities but also cause a range of harms that are drawing increasing scrutiny. A large body of work in the Responsible AI community has…
Cybersecurity decision-making increasingly occurs in environments characterized by uncertainty, partial observability, and adversarial manipulation, where heterogeneous signals from multiple sources are often incomplete, ambiguous, or…
Recent advances in AI research make it increasingly plausible that artificial agents with consequential real-world impact will soon operate beyond tightly controlled environments. Ensuring that these agents are not only safe but that they…
In the future, AI will increasingly find its way into systems that can potentially cause physical harm to humans. For such safety-critical systems, it must be demonstrated that their residual risk does not exceed what is acceptable. This…
The proliferation of autonomous AI agents capable of executing real-world actions - filesystem operations, API calls, database modifications, financial transactions - introduces a class of safety risk not addressed by existing…
What is appropriateness? Humans navigate a multi-scale mosaic of interlocking notions of what is appropriate for different situations. We act one way with our friends, another with our family, and yet another in the office. Likewise for AI,…
We present a new methodology for handling AI errors by introducing weakly supervised AI error correctors with a priori performance guarantees. These AI correctors are auxiliary maps whose role is to moderate the decisions of some previously…
AI agents increasingly act through external tools: they query databases, execute shell commands, read and write files, and send network requests. Yet in most current agent stacks, model-generated tool calls are handed to the execution layer…