---
title: "Reflexion: Language Agents with Verbal Reinforcement Learning"
description: "Reflexion turns a failed agent trajectory into a short verbal lesson, stores that lesson as episodic memory, and retries without updating model weights. Read it to see how acting, evaluation, and reflection form one loop, why evaluator quality controls the learning signal, and how the original ALFWorld, HotPotQA, and coding results should be interpreted."
canonical_url: "https://fanout.sh/daily/2026-10-14-reflexion-verbal-reinforcement-learning"
md_url: "https://fanout.sh/daily/2026-10-14-reflexion-verbal-reinforcement-learning.md"
last_updated: "2026-10-14"
access: "public"
---

# Reflexion: Language Agents with Verbal Reinforcement Learning

Reflexion turns a failed agent trajectory into a short verbal lesson, stores that lesson as episodic memory, and retries without updating model weights. Read it to see how acting, evaluation, and reflection form one loop, why evaluator quality controls the learning signal, and how the original ALFWorld, HotPotQA, and coding results should be interpreted.

## Paper details

- Authors: Noah Shinn et al.

- Venue: NeurIPS 2023

- Track: AI Research

- Difficulty: Medium

- Reading time: 32 min

- Original paper: https://arxiv.org/abs/2303.11366

## What you will learn

- How the Actor, Evaluator, and Self-Reflection roles convert one failed trajectory into a new prompt.

- Why short-term trajectory context and long-term verbal memory solve different parts of the retry problem.

- Where generated tests and self-evaluation can create false lessons or end the loop too early.

## Continue exploring

[Start with ReAct](https://fanout.sh/daily/2026-08-10-react-reasoning-acting): See how thoughts, actions, and observations form one trial before adding reflection across repeated trials.

---
This representation contains public Fanout content only. Protected Pro lessons, account data, billing, checkout, and pricing are not included.

Browse the public content map: https://fanout.sh/sitemap.md