Polymath is a data lab focused on increasing the reliability and autonomy of AI agents. It builds simulation environments for agents to practice and learn through experience.
Products & media
Polymath
Simulation environments combining working applications, tools, and multistep tasks to train and evaluate autonomous AI agents over long time horizons.
Horizon-SWE
A benchmark evaluating autonomous agents on end-to-end software engineering, including implementation, deployment, monitoring, and incident response in running systems.
Team
Founders
2 people
Jobs
See all jobs for Polymath here.
