Will Brown

Researcher

Prime Intellect

Columbia PhD (2024). Lead author on PRIME-RL (async & decentralized RL training at scale) and Verifiers (environments for LLM RL). Focus: multi-turn reasoning in LLM agents, credit assignment, distributed RL. Published at NeurIPS/ICLR. Ex-Morgan Stanley. willcb.com

Sessions (1)

PRIME-RL: Async & Decentralized RL Training at Scale

1:55 PM·Track 9 · Room 2016

Will Brown (Researcher at Prime Intellect) covers post-training for LLM agents: multi-turn reasoning, credit assignment, distributed RL, PRIME-RL, and verifier-driven environments for LLM RL.

Posttraining & Midtrainingintermediatetalk