Marwa Abdulhai is an incoming Postdoctoral Fellow at Princeton University.
She completed her PhD in Computer Science at UC Berkeley advised by Professor Sergey Levine with Professor Natasha Jaques as a close research collaborator. Her research focuses on building goal-directed agents that operate within the complexities of the real-world. This includes improving the performance of existing large language models (LLMs) for multi-turn dialogue interactions, developing simulators for human behavior, and understanding how to protect against deception in AI systems. Her research has been supported by the Quad Fellowship, AI Policy Hub, Open AI Research, and Cooperative AI PhD Fellowship.