Glossary · Term

process reward model

← all terms

Definition

Plain language

A grader that scores each step of an AI's reasoning, not just the final answer.

As stated in the literature

A reward model trained to score intermediate reasoning steps rather than only outcomes, providing dense supervision for RL; typically expensive because it requires step-level annotation.

Also called: PRM, process reward models

Why it matters: By rewarding good reasoning steps, not just correct endings, it gives much richer guidance during training, at the cost of expensive step-by-step labeling.

For example, instead of only checking the final answer to a math problem, it grades each line of the working to catch a mistake midway.

Heard on the show

“What you actually want is a process reward model, a PRM, that scores each step: was this move progress?”
Episode 173 — The Free Step-Level Grader Hiding in Every RL Training Run

Mentioned in 3 episodes

  1. 173
    The Free Step-Level Grader Hiding in Every RL Training Run
  2. 081
    When Reasoning Models Decide Before They Think: Detecting and Fixing Premature Confidence
  3. 008
    Why Long-Horizon AI Agents Get Stuck, and a Milestone-Based Fix That Helps

Related terms