Related papers: Towards Measuring Goal-Directedness in AI Systems

The governance of frontier general-purpose artificial intelligence has become a public-sector problem of institutional design, not merely a technical issue of model performance. Recent evidence indicates that AI capabilities are advancing…

In the long term, reinforcement learning (RL) is considered by many AI theorists to be the most promising path to artificial general intelligence. This places RL practitioners in a position to design systems that have never existed before…

As artificial intelligence scales, the concepts of alignment, agency, and autonomy have become central to AI safety, governance, and control. However, even in human contexts, these terms lack universal definitions, varying across…

This paper introduces a novel visual mapping methodology for assessing strategic alignment in national artificial intelligence policies. The proliferation of AI strategies across countries has created an urgent need for analytical…

This paper addresses the problem of designing control policies for agents with unknown stochastic dynamics and control objectives specified using Linear Temporal Logic (LTL). Recent Deep Reinforcement Learning (DRL) algorithms have aimed to…

Learning to control an environment without hand-crafted rewards or expert data remains challenging and is at the frontier of reinforcement learning research. We present an unsupervised learning algorithm to train agents to achieve…

Current large language models (LLMs) are constrained by human-derived training data and limited by a single level of abstraction that impedes definitive truth judgments. This paper introduces a novel framework in which AI models…

In continuous control, exploration is often performed through undirected strategies in which parameters of the networks or selected actions are perturbed by random noise. Although the deep setting of undirected exploration has been shown to…

Big models, exemplified by Large Language Models (LLMs), are models typically pre-trained on massive data and comprised of enormous parameters, which not only obtain significantly improved performance across diverse tasks but also present…

As AI systems become more advanced and widely deployed, there will likely be increasing debate over whether AI systems could have conscious experiences, desires, or other states of potential moral significance. It is important to inform…

Many AI problems, in robotics and other domains, are goal-directed, essentially seeking a trajectory leading to some goal state. In such problems, the way we choose to represent a trajectory underlies algorithms for trajectory prediction…

Sound deductive reasoning -- the ability to derive new knowledge from existing facts and rules -- is an indisputably desirable aspect of general intelligence. Despite the major advances of AI systems in areas such as math and science,…

Agentic AI denotes an architectural transition from stateless, prompt-driven generative models toward goal-directed systems capable of autonomous perception, planning, action, and adaptation through iterative control loops. This paper…

Progress in deep reinforcement learning (RL) research is largely enabled by benchmark task environments. However, analyzing the nature of those environments is often overlooked. In particular, we still do not have agreeable ways to measure…

This paper proposes a definition of system health in the context of multiple agents optimizing a joint reward function. We use this definition as a credit assignment term in a policy gradient algorithm to distinguish the contributions of…

Many AI alignment discussions of "runaway optimisation" focus on RL agents: unbounded utility maximisers that over-optimise a proxy objective (e.g., "paperclip maximiser", specification gaming) at the expense of everything else. LLM-based…

Behavioral skills or policies for autonomous agents are conventionally learned from reward functions, via reinforcement learning, or from demonstrations, via imitation learning. However, both modes of task specification have their…

Data is essential to train and fine-tune today's frontier artificial intelligence (AI) models and to develop future ones. To date, academic, legal, and regulatory work has primarily addressed how data can directly harm consumers and…

Finding meaningful and accurate dense rewards is a fundamental task in the field of reinforcement learning (RL) that enables agents to explore environments more efficiently. In traditional RL settings, agents learn optimal policies through…

To understand and identify the unprecedented risks posed by rapidly advancing artificial intelligence (AI) models, Frontier AI Risk Management Framework in Practice presents a comprehensive assessment of their frontier risks. As Large…