About

Polymath is an applied research lab focused on scaling high fidelity environments for training and evaluating AI agents. We:

  • Design long-horizon, multi-tool environments for training and evaluation
  • Scale the production of environments
  • Build infrastructure to run thousands of environments in parallel, and provide tooling for researchers to easily observe and debug agent trajectories

We're a team of researchers and engineers from UC Berkeley, Hume AI, Plaid, and Amazon. We have years of experience post-training frontier models in industry, and building large scale distributed systems. Polymath is backed by Y Combinator.