ModelRefs / Stopping Condition — AI Glossary

Stopping Condition — AI Glossary

A criterion determining when an agent loop should terminate, either by task completion, error threshold, or resource limit.

Overview

Stopping conditions: task completed (LLM emits a final-answer tool call or stops generating tool calls), max iterations reached, error rate threshold exceeded, cost budget exhausted, or human interrupt signal received. Well-defined stopping conditions are essential for production agents to avoid infinite loops and runaway API costs.

Reference details

Topicagents
Last reviewed2026-06-24

Continue your research

Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Stopping Condition — AI Glossary.

Frequently asked questions

What is Stopping Condition?

A criterion determining when an agent loop should terminate, either by task completion, error threshold, or resource limit.

What concepts are related to Stopping Condition?

Closely related concepts include max iterations, retry logic, agent.