Related papers: SARC: A Governance-by-Architecture Framework for A…
The rapid proliferation of large language model (LLM)-based agentic systems raises critical concerns regarding digital sovereignty, environmental sustainability, regulatory compliance, and ethical alignment. Whilst existing frameworks…
AI-assisted software generation has increased development speed, but it has also amplified a persistent engineering problem: systems that are functionally correct may still be structurally insecure. In practice, prompt-based security review…
The transition of agentic AI from brittle prototypes to production systems is stalled by a pervasive crisis of craft. We suggest that the prevailing orchestration paradigm-delegating the system control loop to large language models and…
Agentic language models operate in a fundamentally different safety regime than chat models: they must plan, call tools, and execute long-horizon actions where a single misstep, such as accessing files or entering credentials, can cause…
The temporal assumptions underpinning conventional Identity and Access Management collapse under agentic execution regimes. A sixty-second revocation window permits on the order of $6 \times 10^3$ unauthorized API calls at 100 ops/tick; at…
Runtime enforcement refers to the theories, techniques, and tools for enforcing correct behavior with respect to a formal specification of systems at runtime. In this paper, we are interested in techniques for constructing runtime enforcers…
AI agents are increasingly embedded in real software systems, where they execute multi-step workflows through multi-turn dialogue, tool invocations, and intermediate decisions. These long execution histories, called agentic traces, make…
As LLM-based systems increasingly operate as agents embedded within human social and technical systems, alignment can no longer be treated as a property of an isolated model, but must be understood in relation to the environments in which…
Enterprise back office workflows require agentic systems that are auditable, policy-aligned, and operationally predictable, capabilities that generic multi-agent setups often fail to deliver. We present POLARIS (Policy-Aware LLM Agentic…
Agentic AI in software product development is increasingly adopted by organizations, yet the field lacks a consolidated synthesis of where adoption is mature, which architectural patterns dominate, and what limitations and coping mechanisms…
Large Language Model (LLM)-based agents increasingly interact, collaborate, and delegate tasks to one another autonomously with minimal human interaction. Industry guidelines for agentic system governance emphasize the need for users to…
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…
Traditional software relies on contracts -- APIs, type systems, assertions -- to specify and enforce correct behavior. AI agents, by contrast, operate on prompts and natural language instructions with no formal behavioral specification.…
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,…
Risk-based AI regulation has become the dominant paradigm in AI governance, promising proportional controls aligned with anticipated harms. This paper argues that such frameworks often fail for structural reasons: they implicitly assume…
Agentic artificial intelligence systems are autonomous technologies capable of pursuing complex goals with minimal human oversight and are rapidly emerging as the next frontier in AI. While these systems promise major gains in productivity,…
Recent advances in agentic AI have shifted the focus from standalone Large Language Models (LLMs) to integrated systems that combine LLMs with tools, memory, and other agents to perform complex tasks. These multi-agent architectures enable…
Authorizing Large Language Model (LLM)-driven agents to dynamically invoke tools and access protected resources introduces significant security risks, and the risks grow dramatically as agents engage in multi-turn conversations and scale…
As AI agents transition from human-supervised copilots to autonomous platform infrastructure, the ability to analyze their reasoning behavior across populations of investigations becomes a pressing infrastructure requirement. Existing…
Deep learning models for drug--target interaction (DTI) prediction often achieve strong benchmark performance without necessarily relying on mechanistically meaningful molecular features, a limitation that standard accuracy-based evaluation…