Topic
Reasoning models and chain-of-thought training.
Reasoning models turned inference into a per-request dial. This is an economic read on when spending FLOPs at test time actually buys accuracy, why it only pays where answers are cheap to verify, and what variable-cost inference does to latency budgets and capacity planning.
The reproducible part is the method, not a leaderboard cell: group-relative RL on verifiable rewards, with open weights to probe. It is the cleanest public artifact for understanding the reasoning-model training loop.
GRPO swaps PPO's learned critic for a Monte-Carlo baseline — the mean reward over a group of sampled completions — trading rollout compute and per-token credit assignment for a simpler, more stable RL loop on verifiable-reward tasks.