Glossary · Evaluator mechanisms
Process reward model (PRM)
A learned judge operating at step or state resolution. "Process" names the resolution, not a rung above outcome checkers.
Defined in
Handbook · InstrumentSignals and resolutionVerdict, score, preference or critique; about a step, action, artifact, trajectory or population. Why PRMs, value models and margins are different objects.Related terms
- Process verifier
- Any process-resolution evaluator, whatever its mechanism family: formal, executable, learned, or human. Not a synonym for PRM.
- Value model
- Estimates expected future return from a state or prefix, conditional on a policy. Rollout-labeled "step quality" usually behaves like one.
Where it comes up
- Vocabulary without category errorsHandbook · Foundations
- Mechanism familiesHandbook · Instrument
- Evaluators inside training loopsHandbook · Regime
- Channels, independence, and anchor burnHandbook · Lifecycle
- A: Mathematical reasoningHandbook · Case studies
- E: Reasoning-model trainingHandbook · Case studies
- Notation and formula cardHandbook · Reference