Google DeepMind 论文发现自我进化智能体边学边忘，GEPA 学得最快也遗忘最多

Rohan Paul· @rohanpaul_ai · X·2026-10-21 02:47· 57 分钟前AI 评分59

AI 导读

Rohan Paul 介绍了 Google DeepMind 论文《Are Self-Evolving Agents Continual Learners?》的发现：自我进化智能体通过编辑系统提示词、记忆或技能文件来改进，但在任务流变化时会出现遗忘，学新任务最快的方法破坏旧任务也最多。

正文 · 原文

New Google DeepMind paper finds that self-improving agents forget as they learn, and the method that learned new tasks fastest broke old ones the most.

Self-evolving agents improve without retraining by editing their system prompt, memory, or skill files. In real use tasks keep shifting, and each edit made for 1 task also applies to every task that follows.

The team ran ReasoningBank, GEPA, and Meta-Harness on task streams that changed topic, workflow, or domain. They tracked how much each method learned on the current task and lost on the others.

GEPA learned the most, 6.2 points per block on average, and also lost the most elsewhere, 4.3 points. After it learned to ask users for missing details, a later block rewrote that rule and its 15.5-point gain fell to 2.5.

If your agent edits its own prompt or memory, keep task-specific rules separate and retest old tasks after every update.

来源：Rohan Paul · x.com