Reasoning & Test-Time Compute · 2022

Solving Quantitative Reasoning Problems with Language Models (Minerva)

Aitor Lewkowycz, Anders Andreassen, David Dohan, Vinay Ramasesh

Showed that a large model trained on mathematical and scientific text, with chain-of-thought and majority voting, could solve quantitative reasoning problems far better than prior models without external tools.

Editorial record

Plain-language summary

Minerva continues pretraining a large language model on math-heavy web and arXiv data, then uses step-by-step prompting and samples many solutions to vote on the answer. It substantially raised scores on MATH and STEM problem sets using only the model’s own reasoning. It marked how far scaled models plus test-time sampling could push mathematical reasoning.

Knowledge graph

Relationships

Descendants

Source record

Provenance

Record ID
P-522
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.