I am a PhD student in the Department of Computer Science at UCL, focusing on rational and irrational behaviour in multi-agent systems. I have approached this problem from a theoretical perspective using reinforcement learning, as well as investigating the application of this research to political science and conflict studies, paritucularly with LLM agents. My research interests lie in understanding the role that rationality plays in AI systems and in their interaction with humans. With LLMs, I am particularly interested in their emergent capabilities and the potential implacts these could have.
My PhD is funded by the Leverhulme Trust as part of the Leverhulme Doctoral Training Programme for the Ecological Study of the Brain and is supervised by Prof. Mirco Musolesi and Prof. Nils Metternich. During my PhD, I also spent 6 months as an AI Research Intern at the Alan Turing Institute’s Defence and National Security grand challenge. I graduated from UCL with a degree in Arts and Sciences (BASc) in 2020, where I majored in mathematics and minored in conflict studies and international relations, alongside studying Arabic.