Foundation Lab

Process Reward Models

Key to o1-style reasoning: verify each step, not just the answer

Concept 81 of 100Scaling & AlignmentPhase 11

#81PRMsScaling & Alignment

key equationR_{PRM} = \prod_k P(\text{step } k \text{ correct})

Selected Foundation Object

Keep the equation fixed; move through the evidence.

Concept 81 of 100PRMsScaling & Alignment / Phase 11: Frontier research & scaling

Current question

Outcome is sparse feedback; process is dense—better credit assignment

R_{PRM} = \prod_k P(\text{step } k \text{ correct})

PredictionCommit before the demo.

Ask what should change when the equation is manipulated, then let the visualization test that expectation.

EvidenceCompare local witness and source.

Use the runnable panel, the key equation, and canonical papers as separate forms of evidence for the same object.

InvariantName what survives notation changes.

The useful learning product is the reusable mechanism you can carry into another model, paper, or engineering tradeoff.

Next moveContinue in the newer notebook.

This atlas page keeps the working demo; the domain notebook carries the fuller Intuition -> Math -> Code -> Demo sequence.

What is still poorly explained in textbooks and papers:

If you want intuition first, start with the key equation and the visualization. Come back here for the full walkthrough.

Key Equation

R_{PRM} = \prod_k P(\text{step } k \text{ correct})

Outcome RM: Score final answer: $R_{ORM}(y) = P(\text{correct})$

Process RM: Score each step:

R_{PRM}(s_1, ..., s_K) = \prod_{k=1}^K P(\text{step } s_k \text{ correct})

Best-of-N with PRM: Reject solutions with any incorrect step:

y^* = \arg\max_{y} \min_{k} R_{PRM}(s_1, ..., s_k)

Lightman et al.2023arXiv

Choose the next question to carry this object forward.