Will Schwarzer

Hey there, I’m Will. I’m a PhD student at the University of Massachusetts Amherst, where I work with Philip Thomas, Bruno Castro da Silva and Scott Niekum. My long-term research goal is to create robust and aligned agents that can perform largely autonomous research in AI and the sciences. Right now I’m working on agentic evaluation for LLM agents, RL and post-training for safety and alignment, and robustness in generative models and agent behavior. More broadly, I’m interested in reliable long-horizon agents: systems that can carry out complex projects over many steps, keep honest accounts of partial progress and failure, and drive themselves toward genuinely correct solutions.

Fun fact: this headshot was taken at an excellent studio in Beijing while I was studying Mandarin there. I’m always happy to chat in Chinese. Aside from languages, I also enjoy playing the piano and rock climbing. I particularly love exploring climbing gyms in new countries (tally so far: three in Beijing, one in Bangkok, one in Istanbul, one in Fort William, Scotland, one in London, and a few in Montreal).

Note to prospective undergraduate and master’s collaborators: please read this before reaching out.