Reasoning & Test-Time Compute · 2023

Verifiers & Process Supervision (GSM8K / Let's Verify Step by Step)

Karl Cobbe, John Schulman, Hunter Lightman, Ilya Sutskever, Jan Leike

It compared rewarding only the final answer (outcome supervision) against rewarding each intermediate reasoning step (process supervision) and showed that step-level feedback trains a more reliable verifier that selects correct solutions to hard math problems more often.

Editorial record

Plain-language summary

The authors had humans label the correctness of every step in a model's chain of reasoning, then trained a verifier to score solutions step by step. Ranking many candidate solutions by this process-supervised verifier picked correct answers more often than a verifier trained only on whether the final answer was right. They also released PRM800K, a large dataset of step-level human labels, making process-based reward modeling reproducible for reasoning tasks.

Knowledge graph

Relationships

Antecedents

Source record

Provenance

Record ID
P-223
Record created
2026-07-13
Last reviewed
2026-07-14
Record version
2

Citation caveat: Citation metadata is approximate and marked unverified in the source dataset.