Agentic Systems
Long-horizon reasoning, tool use, stateful interaction, and autonomous behaviour.
RESEARCH
Research into the systems around intelligence.
We build experiments that make model behaviour, reasoning, interaction, and learning easier to inspect.
OUR THESIS
Westudywhathappensaftermodelsbecomecapable.
As AI systems act across time, capability depends on more than model weights. Tools, state, feedback, reasoning processes, environments, and failure recovery become part of intelligence itself.
We study the machinery around intelligence.RESEARCH DIRECTIONS
Whatweinvestigate.
Model Intelligence
Internal representations, mechanistic interpretability, model intervention, and behavioural analysis.
Reasoning & Verification
Search, symbolic constraints, structured reasoning, and verifiable computation.
Simulation & Learning
Interactive environments, synthetic experience, robotics, and adaptive learning systems.
AI Red Teaming
Reward-hacking analysis, model-hacking benchmarks, adversarial evaluations, and repeatable tests for unsafe optimisation and deceptive behaviour.
FEATURED RESEARCH
Noma:anopen,calibrateddecisionmodel
An open-weight decision model for agents and pipelines. It reads a state and typed questions and returns calibrated probabilities, an abstain signal, and an uncertainty estimate in one forward pass, in about 16 ms, with no generated text.