Skip to content
Search Sign in List your company

Polymath

Polymath builds the simulated environments AI agents train in. It is aimed at the slowest part of teaching an agent to work: producing the worlds it practises in.

No reviews yet San Francisco, United States Small Founded 2026

About Polymath

Polymath builds simulated worlds where AI agents learn to operate on their own over long stretches of work, rather than one instruction at a time. The problem it is aimed at is a practical one. Training an agent with reinforcement learning needs an environment for it to act in, and building those environments by hand is slow enough that it, rather than the training itself, is what holds teams up. Polymath makes them easier to produce. The company was founded in 2026 by Dylan Ma and Naren Yenuganti, and went through Y Combinator's Winter 2026 batch. The team came out of UC Berkeley, Hume AI, Plaid and Amazon, and it is based in San Francisco.

Client reviews

No reviews yet

Be the first to review Polymath.

Frequently asked questions

What is Polymath?
A company building simulated environments for training AI agents. The agents practise long, multi-step digital work in those environments before they do it anywhere real.
Why do AI agents need training environments?
Reinforcement learning teaches by doing, which means the agent needs somewhere to act and something to be scored against. Building those environments by hand is slow, and that has become the constraint rather than the training itself.
When was Polymath founded, and where is it based?
Founded in 2026 by Dylan Ma and Naren Yenuganti, based in San Francisco, and part of Y Combinator's Winter 2026 batch.