Related papers: Bounded Autonomy for Enterprise AI: Typed Action C…
Large language models (LLMs) have transformed the development of embodied intelligence. By providing a few contextual demonstrations, developers can utilize the extensive internal knowledge of LLMs to effortlessly translate complex tasks…
AI agents -- systems that plan, reason, and act using large language models -- produce non-deterministic, path-dependent behavior that cannot be fully governed at design time, where with governed we mean striking the right balance between…
Production AI systems often operate with incomplete, conflicting, or insufficient evidence. Forced classifiers collapse such cases into action labels, while generative systems can produce outputs that are difficult to interpret as auditable…
As AI models scale to billions of parameters and operate with increasing autonomy, ensuring their safe, reliable operation demands engineering-grade security and assurance frameworks. This paper presents an enterprise-level, risk-aware,…
Since its inception, artificial intelligence has relied upon a theoretical foundation centered around perfect rationality as the desired property of intelligent systems. We argue, as others have done, that this foundation is inadequate…
In high-conflict mixed-traffic scenarios involving human-driven and autonomous vehicles, most existing autonomous driving systems default to overly conservative behaviors, lack proactive interaction, and consequently suffer from limited…
This paper asks whether a bounded neural architecture can exhibit a meaningful division of labor between intuition and deliberation on a classic 64-item syllogistic reasoning benchmark. More broadly, the benchmark is relevant to ongoing…
Large Language Model (LLM)-based agents are increasingly employed to automate complex software engineering tasks, such as program repair and issue resolution. These agents operate by autonomously generating natural language thoughts,…
Enterprise penetration-testing is often limited by high operational costs and the scarcity of human expertise. This paper investigates the feasibility and effectiveness of using Large Language Model (LLM)-driven autonomous systems to…
Agents powered by large language models (LLMs) have demonstrated strong planning and decision-making capabilities in complex embodied environments. However, such agents often suffer from inefficiencies in multi-turn interactions, frequently…
The popularisation of applying AI in businesses poses significant challenges relating to ethical principles, governance, and legal compliance. Although businesses have embedded AI into their day-to-day processes, they lack a unified…
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.…
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…
Incident management for cloud services is a complex process involving several steps and has a huge impact on both service health and developer productivity. On-call engineers require significant amount of domain knowledge and manual effort…
In Agentic AI, Large Language Models (LLMs) are increasingly used in the orchestration layer to coordinate multiple agents and to interact with external services, retrieval components, and shared memory. In this setting, failures are not…
Agentic AI systems plan, use tools, maintain state, and produce multi-step trajectories with external effects. Those properties create a governance problem that differs materially from single-turn generative AI: important risks emerge dur-…
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,…
Self-modification of agents embedded in complex environments is hard to avoid, whether it happens via direct means (e.g. own code modification) or indirectly (e.g. influencing the operator, exploiting bugs or the environment). It has been…
We sketch how developers of frontier AI systems could construct a structured rationale -- a 'safety case' -- that an AI system is unlikely to cause catastrophic outcomes through scheming. Scheming is a potential threat model where AI…
Large language models are increasingly deployed as *deep agents* that plan, maintain persistent state, and invoke external tools, shifting safety failures from unsafe text to unsafe *trajectories*. We introduce **AgentFence**, an…