Skip to content
Rota Nacional

Radar ·

RL recipes for math, code, and tool use

Prime Intellect’s documentation collects practical reinforcement-learning training recipes for mathematical reasoning, code generation, tool use, and other tasks in the Lab.

Published on February 25, 2026, the material presents practical reinforcement learning (RL) training recipes for tasks such as mathematical reasoning, code generation, and tool use in the Lab. The documentation also mentions other tasks, without detailing them in the available summary.

The recipes can be a starting point for studying or planning RL experiments; they do not replace validation for each problem. If you use AI to study or apply the material, avoid entering personal or confidential organizational data and follow your organization’s data-handling rules.

Get new articles

Privacy, AI engineering and security in your inbox.

Rota Nacional

Bring privacy into your workflow.

30 days, no card, with a starting quota. After that, Pix credit from R$ 5,00.

Try free