跳到主要内容Skip to main content

Reflexion(反思)Reflexion

Reflexion

  • 智能体Agents
  • 第三站 · 用深Station 3 · Going Deeper
  • 引用核验 2026-11-19refs checked 2026-11-19
解决什么问题What problem it solves

让 agent 在失败后写一份「复盘」,把教训存进记忆,下一轮避免同样的错。Let an agent write a post-mortem after failure, store the lesson in memory and avoid the same mistake next time.

这是什么What it is

一次任务失败后,模型根据轨迹和反馈生成一段自我反思。

反思被写入长期记忆,下一次尝试时作为额外上下文读回来。

它不改模型参数,只改下一轮的提示与策略。

After a failed attempt, the model writes a reflection over the trajectory and feedback.

The reflection is stored in long-term memory and read back on the next attempt.

No weights change; only the next prompt and strategy change.

为什么需要知道Why it matters

agent 最常见的问题是重复犯错。反思把一次失败变成可复用的经验,而不是重新从零试。Agents often repeat the same error. Reflection turns one failure into reusable experience instead of starting from zero.

出处Sources
  • Reflexion 论文(arXiv)Reflexion: Language Agents with Verbal Reinforcement Learning (arXiv 2303.11366) ↗