Related papers: Limits to Verification and Validation of Agentic B…
AI agents have been boosted by large language models. AI agents can function as intelligent assistants and complete tasks on behalf of their users with access to tools and the ability to execute commands in their environments. Through…
Agentic AI systems can now generate code with remarkable fluency, but a fundamental question remains: \emph{does the generated code actually do what the user intended?} The gap between informal natural language requirements and precise…
AI scientists powered by large language models have demonstrated substantial promise in autonomously conducting experiments and facilitating scientific discoveries across various disciplines. While their capabilities are promising, these…
AI agents dynamically acquire tools, orchestrate sub-agents, and transact across organizational boundaries, yet no existing security layer verifies what an agent can do, whether it executed what it claims, or what happened in a multi-agent…
Human users increasingly communicate with large language models (LLMs), but LLMs suffer from frequent overconfidence in their output, even when its accuracy is questionable, which undermines their trustworthiness and perceived legitimacy.…
Agentic AI systems automate enterprise workflows but existing defenses--guardrails, semantic filters--are probabilistic and routinely bypassed. We introduce authenticated workflows, the first complete trust layer for enterprise agentic AI.…
Agentic AIs $-$ AIs that are capable and permitted to undertake complex actions with little supervision $-$ mark a new frontier in AI capabilities and raise new questions about how to safely create and align such systems with users,…
Classic evaluation methods of believable agents are time-consuming because they involve many human to judge agents. They are well suited to validate work on new believable behaviours models. However, during the implementation, numerous…
Agentic AI systems -- Large Language Models (LLMs) augmented with planning, tool use, memory, and long-horizon interactions -- can execute complex tasks autonomously, but their multi-step trajectories introduce new failure modes that…
Human behavior is conditioned by codes and norms that constrain action. Rules, ``manners,'' laws, and moral imperatives are examples of classes of constraints that govern human behavior. These systems of constraints are "messy:" individual…
Artificial Knowledge (AK) systems are transforming decision-making across critical domains such as healthcare, finance, and criminal justice. However, their growing opacity presents governance challenges that current regulatory approaches,…
Incorrect operations of a Multi-Robot System (MRS) may not only lead to unsatisfactory results, but can also cause economic losses and threats to safety. These threats may not always be apparent, since they may arise as unforeseen…
As learned control policies become increasingly common in autonomous systems, there is increasing need to ensure that they are interpretable and can be checked by human stakeholders. Formal specifications have been proposed as ways to…
The leading AI companies are increasingly focused on building generalist AI agents -- systems that can autonomously plan, act, and pursue goals across almost all tasks that humans can perform. Despite how useful these systems might be,…
Autonomous AI agents powered by Large Language Models can reason, plan, and execute complex tasks, but their ability to autonomously retrieve information and run code introduces significant security risks. Existing approaches attempt to…
We consider the setting of stochastic multiagent systems modelled as stochastic multiplayer games and formulate an automated verification framework for quantifying and reasoning about agents' trust. To capture human trust, we work with a…
Ensuring that artificial intelligence (AI) systems satisfy formal safety and policy constraints is a central challenge in safety-critical domains. While limitations of verification are often attributed to combinatorial complexity and model…
Artificial Intelligence (AI) achieved super-human performance in a broad variety of domains. We say that an AI is made Artificially Stupid on a task when some limitations are deliberately introduced to match a human's ability to do the…
Autonomous Intelligent Agents are employed in many applications upon which the life and welfare of living beings and vital social functions may depend. Therefore, agents should be trustworthy. A priori certification techniques (i.e.,…
While AI agents have long been discussed and studied in computer science, today's Agentic AI systems are something new. We consider other definitions of Agentic AI and propose a new realist definition. Agentic AI is a software delivery…