Dillon Z. Chen

I am a PhD student working on building autonomous agents that can solve long-horizon problems in complex, dynamic environments. My lifelong goal is to develop embodied generalist agents ~ or at least robots that can perform all my household chores and manage my vegetable garden.

My most recent work focuses on generalised planning – the task of synthesising programs that solve families of planning problems. I design systems that best leverage structured world models in order to few-shot learn policies from simple demonstrations that can solve problems exhibiting hundreds of relevant objects and solutions with thousands of relevant actions. My work on generalised planning spans the usage of graph neural networks (AAAI’24), statistical machine learning (NeurIPS’24), large language models (PRL@RLC’25), and knowledge representation and reasoning techniques (AAAI’26).

For more research, check out my publications. To play the dog gacha, refresh the page (rates and rarities coming soon!).