Related papers: Formal Policy Enforcement for Real-World Agentic S…
AI agent development relies heavily on natural language prompting to define agents' tasks, knowledge, and goals. These prompts are interpreted by Large Language Models (LLMs), which govern agent behavior. Consequently, agentic performance…
The field of Artificial Intelligence is undergoing a transition from Generative AI -- probabilistic generation of text and images -- to Agentic AI, in which autonomous systems execute actions within external environments on behalf of users.…
The dominant paradigm for AI agents is an "on-the-fly" loop in which agents synthesize plans and execute actions within seconds or minutes in response to user prompts. We argue that this paradigm short-circuits disciplined software…
The rise of multi-agent systems powered by large language models (LLMs) and specialized reasoning agents exposes fundamental limitations in today's data management architectures. Traditional databases and data fabrics were designed for…
The Agentic Paradigm faces a significant Software Engineering Absence, yielding Agentic systems commonly lacking robustness, observability, and evolvability. To address these deficiencies, we propose a principled engineering framework…
Large Language Models (LLMs) are increasingly central to agentic systems due to their strong reasoning and planning capabilities. By interacting with external environments through predefined tools, these agents can carry out complex user…
Explanations for AI models in high-stakes domains like medicine often lack verifiability, which can hinder trust. To address this, we propose an interactive agent that produces explanations through an auditable sequence of actions. The…
Rule-based policy and contract systems have rarely been studied in terms of their software engineering properties. This is a serious omission, because in rule-based policy or contract representation languages rules are being used as a…
As large language models transition from bounded generative engines to agents with expansive execution privileges, AI going out of control precipitates a fundamental crisis in artificial intelligence security. Existing defense architectures…
While there have been approaches for integrating security policies into operating systems (OSs) for more than two decades, applications often use objects of higher abstraction requiring individual security policies with application-specific…
Large language models are increasingly being used to support network operations (NetOps) and artificial intelligence for IT operations (AIOps), including incident investigation, root-cause analysis, configuration synthesis, and limited…
As the complexity of AI systems and their interactions with the world increases, generating explanations for their behaviour is important for safely deploying AI. For agents, the most natural abstractions for predicting behaviour attribute…
To enable human oversight, agentic AI systems often provide a trace of reasoning and action steps. Designing traces to have an informative, but not overwhelming, level of detail remains a critical challenge. In three user studies on a…
AI agents are increasingly transacting on behalf of users -- delegating tasks, spending budgets, and negotiating with unfamiliar counterparties. Unlike human marketplaces, which operate under institutional designs refined over centuries,…
Performing some task among a set of agents requires the use of some protocol that regulates the interactions between them. If those agents are rational, they may try to subvert the protocol for their own benefit, in an attempt to reach an…
Recent advances in agentic AI have enabled increasingly autonomous workflows, but existing systems still face substantial challenges in achieving reliable deployment in real-world scientific research. In this work, we present a safe,…
Humans solve problems by executing targeted plans, yet large language models (LLMs) remain unreliable for structured workflow execution. We propose RunAgent, a multi-agent plan execution platform that interprets natural-language plans while…
The integration of artificial intelligence (AI) agents into web browsers introduces security challenges that go beyond traditional web application threat models. Prior work has identified prompt injection as a new attack vector for web…
Agentic AI represents a significant shift in how intelligence is applied within organizations, moving beyond AI-assisted tools toward autonomous systems capable of reasoning, decision-making, and coordinated action across workflows. As…
The growing complexity of urban mobility systems has made traffic simulation indispensable for evidence-based transportation planning and policy evaluation. However, despite the analytical capabilities of platforms such as the Simulation of…