Will Brown is Research Lead at Prime Intellect and the creator/maintainer of the open-source `verifiers` library and the Environments Hub, making him one of the most hands-on practitioners in agentic reinforcement learning. His session offers direct insight into the infrastructure decisions and research driving multi-turn RL training at scale.

Recent talks (4)

RL Environments at Scale – Will Brown, Prime IntellectAI Engineer Code Summit · Nov 2025How Prime Intellect Builds Scalable Infrastructure for Agentic RLRay Summit 2025 · Nov 2025Training Agentic Reasoners — Will Brown, Prime IntellectCO/AI · Jul 2025Open Questions in Agentic RL — Will Brown (Prime Intellect)Intelligence Unbound · May 2025

Public activity researched automatically · as of Jun 2026