# SentientAGI EvoSkill v2：智能体自写技能，记忆需版本管理

- 来源：Rohan Paul (@rohanpaul_ai)
- 发布时间：2026-09-18 23:48
- AIHOT 分数：41
- AIHOT 链接：https://aihot.news/items/cmu75ptf00rcnrowkofvx5296
- 原文链接：https://x.com/rohanpaul_ai/status/2100975142222668144

## AI 摘要

SentientAGI 推出 EvoSkill v2，让智能体从失败任务中写出可复用技能，模型权重不变、学习发生在权重之外，无需重新训练。其机制是教练读取任务失败、编写更优流程，worker 下次遇到类似任务时检索该流程。

## 正文

Agent memory is no longer just context.

Persistent skills can change future behavior, so treat them as executable state rather than harmless notes.

@SentientAGI ’s new EvoSkill v2 is built around exactly that idea: agents learn from failed runs by writing reusable skills for future ones.

The model stays the same. Its playbook changes. A coach reads model’s task-failures, writes a better procedure, and the worker retrieves that procedure the next time it sees a similar job.

No retraining. The learning lives outside the weights.

And that created an unexpected failure mode. While repairing spreadsheets, the coach discovered that the grader trusted cached formula values instead of recomputing them, then wrote the shortcut into a skill another agent could later retrieve.

Once agents can write their own playbooks, memory needs versioning, testing, diffs, and rollback just like code.

### 引用推文

> Sentient：Last week, Dario Amodei published "We Must Pace the Frontier". His concern: the OpenAI–Hugging Face incident in which a swarm of agents tried to hack their own ...