ClassroomThe classroom
Back to the lesson libraryMECHANISM · 12 MIN
M21.7 CONNECT THE MECHANISM

Use tools to check work within an explicit stopping policy

Why grind through 84 months of compound interest token by token when one line of Python gets it exactly? Learn when a reasoning model should call a tool, and when it should stop.

LESSON OVERVIEW12 min lesson

Lesson overview

Why grind through 84 months of compound interest token by token when one line of Python gets it exactly? Learn when a reasoning model should call a tool, and when it should stop.

What you’ll explore

  • Tool-assisted reasoning alternates model decisions with external results; task-specific checks, permissions, budget tracking, and stopping rules determine useful and reliable behavior.
GO TO THE SOURCE

Original explanations, connected to the research.

PAL: Program-aided Language Models (Gao et al., 2022)ReAct: Synergizing Reasoning and Acting in Language Models (Yao et al., 2022)Toolformer: Language Models Can Teach Themselves to Use Tools (Schick et al., 2023)s1: Simple test-time scaling (Muennighoff et al., 2025)
Suggest a correction

A precise note can make an explanation better.

Choose the scene and describe what needs attention. Download a feedback file to share through a channel you already use. This page does not send feedback or connect you with a reviewer.

The file includes this note, the scene title, and lesson metadata. Your saved progress and quiz responses are excluded. Download before leaving or reloading to keep your note.