Related papers: Active Inference Agency Formalization, Metrics, an…
As AI agents proliferate across industries and applications, evaluating their performance based solely on infrastructural metrics such as latency, time-to-first-token, or token throughput is proving insufficient. These metrics fail to…
Agentic Artificial Intelligence (AI) constitutes a transformative paradigm in the evolution of intelligent agents and decision-support systems, redefining smart environments by enhancing operational efficiency, optimizing resource…
Recent advances in large language models have sparked growing interest in AI agents capable of solving complex, real-world tasks. However, most existing agent systems rely on manually crafted configurations that remain static after…
Collaboration is crucial for reaching collective goals. However, its effectiveness is often undermined by the strategic behavior of individual agents -- a fact that is captured by a high Price of Stability (PoS) in recent literature [Blum…
As autonomous agentic AI systems see increasing adoption across organisations, persistent challenges in alignment, governance, and risk management threaten to impede deployment at scale. We present AURA (Agent aUtonomy Risk Assessment), a…
An Artificial Intelligence (AI) agent is a software entity that autonomously performs tasks or makes decisions based on pre-defined objectives and data inputs. AI agents, capable of perceiving user inputs, reasoning and planning tasks, and…
We present the design of an autoregressive active inference agent in the form of message passing on a factor graph. Expected free energy is derived and distributed across a planning graph. The proposed agent is validated on a robot…
We propose a framework for adaptive data-centric collaborative machine learning among self-interested agents, coordinated by an arbiter. Designed to handle the incremental nature of real-world data, the framework operates in an online…
The creation of effective governance mechanisms for AI agents requires a deeper understanding of their core properties and how these properties relate to questions surrounding the deployment and operation of agents in the world. This paper…
In cognitive neuroscience the sense of agency is defined as the as the experience of controlling ones own actions and, through this control, affecting the external world. At CHI 2012 I presented a paper entitled I did that! Measuring Users…
Alignment research focuses on making individual AI systems reliable. Human institutions achieve reliable collective behaviour differently: they mitigate the risk posed by misaligned individuals through organisational structure. Multi-agent…
AI agents are now running real transactions, workflows, and sub-agent chains across organizational boundaries without continuous human supervision. This creates a problem no current infrastructure is equipped to solve: how do you identify,…
Personalization has become an essential capability in modern AI systems, enabling customized interactions that align with individual user preferences, contexts, and goals. Recent research has increasingly concentrated on Retrieval-Augmented…
In computational reinforcement learning, a growing body of work seeks to express an agent's model of the world through predictions about future sensations. In this manuscript we focus on predictions expressed as General Value Functions:…
Significant digitalization of financial services in a short period of time has led to an urgent demand to have autonomous, transparent and real-time credit risk decision making systems. The traditional machine learning models are effective…
Ensuring fairness in decentralized multi-agent systems presents significant challenges due to emergent biases, systemic inefficiencies, and conflicting agent incentives. This paper provides a comprehensive survey of fairness in multi-agent…
As intelligent agents become more generally-capable, i.e. able to master a wide variety of tasks, the complexity and cost of properly evaluating them rises significantly. Tasks that assess specific capabilities of the agents can be…
Active inference is a probabilistic framework for modelling the behaviour of biological and artificial agents, which derives from the principle of minimising free energy. In recent years, this framework has successfully been applied to a…
We develop a theory of intelligent agency grounded in probabilistic modeling for neural models. Agents are represented as outcome distributions with epistemic utility given by log score, and compositions are defined through weighted…
Research on the so-called "free-energy principle'' (FEP) in cognitive neuroscience is becoming increasingly high-profile. To date, introductions to this theory have proved difficult for many readers to follow, but it depends mainly upon two…