Research
Manuel Baltieri’s research on mathematical foundations of agency, cognition, artificial life, and AI safety in agent-environment systems.
Studying how agents can be identified, modelled, and composed, and what those formal choices imply for cognition, living systems, and AI safety.
Focussing on coupled open agent–environment systems that compose to form autonomous systems. This makes it possible to ask where a boundary comes from, what counts as a model or a goal, and which properties belong to a system rather than to the observer describing it.
01 · Maths
Mathematics for agents
Different mathematical languages reveal different aspects of agency. Category theory describes systems and processes, their compositional patterns and universal properties. Control theory formalises feedback and regulation, while Bayesian inference capture uncertainty and learning patterns.
Mathematical approaches to agents Bayesian updates from coalgebraic determinisation
02 · Cognition
Cognition and control
I use control theory, Bayesian reasoning, and dynamical systems to study perception, action, and minimal cognition. This includes examining when a controller can be said to contain an internal model and how causal representations support adaptive behaviour in natural and artificial agents.
Bayesian internal models Disentangled representations for causal cognition
03 · (A)Life
Artificial life
Research on living systems sharpens questions about autonomy, individuality and regulation. I investigate whether concepts from cybernetics, information and control theory can explain what separates living from non-living systems.
04 · AI safety
Agent foundations
I develop formal foundations for identifying AI agents in and among modern AI systems, their boundaries, goals, models to estimate their capabilities and improve interpretability. The aim is to make safety questions precise enough to analyse and test.
Compositional behavioural semantics AI in a vat World models
