About me

I am a PhD student at University College London (UCL) in the Machine Intelligence lab, supervised by Prof Mirco Musolesi and Prof Stephen Hailes, and part of the Centre for Doctoral Training in Cybersecurity. Before starting my PhD, I completed an MSc in Machine Learning at UCL, and an MSci in Theoretical Physics at Imperial College London, where I worked under Prof Fay Dowker for my dissertation on Causal Set Theory.

My research focuses on safety in multi-agent LLM systems. I am particularly interested in how these agents learn to interact strategically, influence each other’s behavior, and the potential risks that emerge from these dynamics. My recent work explores opponent shaping with LLM agents, where agents learn to influence each other’s behavior through multi-turn reinforcement learning in game-theoretic scenarios.

I am always interested in talking about multi-agent systems, agentic AI, AI safety, and RL in general, so feel free to reach out!