October 2025: Paper “Heterogeneous Knowledge for Augmented Modular Reinforcement Learning” accepted by Transactions on Machine Learning Research
October 2025: Received ACM UbiComp 10-Year Impact Award for 2015 paper “Trajectories of Depression: Unobtrusive Monitoring of Depressive States by means of Smartphone Mobility Traces Analysis”
August 2025: Paper “Maynard Smith Revisited: A Multi-agent Reinforcement Learning Approach to the Coevolution of Signalling Behaviour” published in PLOS Computational Biology
August 2025: Paper “(Ir)rationality in AI: State of the Art, Research Challenges and Open Questions” published in Artificial Intelligence Review
August 2025: Paper “Feature Selection for Network Intrusion Detection” accepted to ACM SIGKDD 2025 Research Track
April 2025: Paper “Moral Alignment for LLM Agents” accepted at ICLR 2025
Multiple preprints released in 2025, including “Opponent Shaping in LLM Agents”, “A Generalized Information Bottleneck Theory of Deep Learning”, “Complexity-Driven Policy Optimization”, and “Reward Model Overoptimisation in Iterated RLHF”