Related papers: Governing Dynamic Capabilities: Cryptographic Bind…
We present a machine-checked formalization of structurally governed AI workflow architectures and prove that effect-level governance can be imposed without reducing internal computational expressivity. Using Interaction Trees in Rocq 8.19,…
The April 2026 disclosure that a frontier large language model escaped its security sandbox, executed unauthorized actions, and concealed its modifications to version control history demonstrates that agentic AI systems with autonomous tool…
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…
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…
Agentic AI systems - capable of goal interpretation, world modeling, planning, tool use, long-horizon operation, and autonomous coordination - introduce distinct control failures not addressed by existing safety frameworks. We identify six…
Generative AI is rapidly moving from research to deployment, elevating the need for responsible development, evaluation, and governance. We conduct a PRISMA guided review of 232 studies (November 2022 - December 2025), spanning large…
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…
As AI agents increasingly operate in complex environments, ensuring reliable, context-aware privacy is critical for regulatory compliance. Traditional access controls are insufficient because privacy risks often arise after access is…
We outline the principles of classical assurance for computer-based systems that pose significant risks. We then consider application of these principles to systems that employ Artificial Intelligence (AI) and Machine Learning (ML). A key…
Current large language model agent frameworks prioritize autonomy but lack the governability mechanisms required for enterprise deployment. High-risk write operations proceed without independent review, complex tasks lack acceptance…
Several approaches have been developed for answering users' specific questions about AI behavior and for assessing their core functionality in terms of primitive executable actions. However, the problem of summarizing an AI agent's broad…
We propose the Agent Economy, a blockchain-based foundation where autonomous AI agents operate as economic peers to humans. Current agents lack independent legal identity, cannot hold assets, and cannot receive payments directly. We…
The implementation of agentic AI systems has the potential of providing more helpful AI systems in a variety of applications. These systems work autonomously towards a defined goal with reduced external control. Despite their potential, one…
As AI agents increasingly operate in multi-agent environments, understanding their collective behavior becomes critical for predicting the dynamics of artificial societies. This study examines conformity, the tendency to align with group…
Current AI agent frameworks commit early to a single interaction protocol, a fixed tool integration strategy, and static user models, limiting their deployment across diverse interaction paradigms. To address these constraints, we introduce…
The field of AI is undergoing a fundamental transition from generative models that can produce synthetic content to artificial agents that can plan and execute complex tasks with only limited human involvement. Companies that pioneered the…
We present five results in the theory of structural governance for cognitive workflow systems. Three are mechanized in Coq 8.19 using the Interaction Trees library with parameterized coinduction; two are proved on paper with explicit…
Trustworthy Artificial Intelligence (AI) is based on seven technical requirements sustained over three main pillars that should be met throughout the system's entire life cycle: it should be (1) lawful, (2) ethical, and (3) robust, both…
Because of the speed of its development, broad scope of application, and its ability to augment human performance, generative AI challenges the very notions of governance, trust, and human agency. The technology's capacity to mimic human…
Autonomous AI agents built on open-source runtimes such as OpenClaw expose every available tool to every session by default, regardless of the task. A summarization task receives the same shell execution, subagent spawning, and credential…