Reflexion Pattern

Overview

When an agent fails, retrying with the same prompt produces the same failure. Reflexion adds a critic that reads the failed trajectory, writes a short verbal lesson, and stores it in episodic memory. The actor reads the lesson on next attempt. Bounded by a retry budget so it can't loop forever.

When to use

• Same task fails 2+ times with the same prompt
• You have a clear success signal (tests, golden, judge)
• Failure modes are recognizable in the trajectory (wrong tool, wrong arg, wrong plan)
• Combined with ralph for spec-first persistent loops

Don't use when

• One-shot tasks with no retry capacity
• Failure signal is noisy (judge LLM disagrees with itself)
• Budget too tight for 2+ attempts