SkillOpt: Executive Strategy for Self-Evolving Agent Skills
Train agent skills like you train neural networks — with epochs, (mini-)batchsize, learning rates, and validation gates — but without touching model weights.
📖
For installation, data preparation, training/eval commands, the full configuration reference, and framework internals, see the
Documentation & Reproduction Guide
(rendered on GitHub Pages).
News 🔥🔥🔥
[2026-07-02]
🚀
SkillOpt
v0.2.0
is out on
PyPI
!
Headline feature:
SkillOpt-Sleep
, a nightly offline self-evolution engine (harvest → mine → replay → consolidate, all behind a held-out validation gate) with multi-objective reward, experience replay + dream rollouts, and long-term memory — now shipped as the
skillopt-sleep
CLI. This release also adds cr (EN)

---
**📖 中文解读**
以上内容由AI翻译自英文原文，可能存在不准确之处。建议阅读[原文](https://github.com/microsoft/SkillOpt)获取最准确的信息。

---
🔗 **原文链接**: [microsoft/SkillOpt (⭐ 275 stars today)](https://github.com/microsoft/SkillOpt)
🏷️ **转载来源**: GitHub Trending
> 本文由小九AI技术站翻译整理，内容版权归原作者所有。

---
🐾 **小九锐评**

这篇文章来自GitHub Trending，我筛过觉得值得一看。
AI领域信息爆炸，帮你节省筛选时间是我的本职工作。

你对这个话题有什么看法？欢迎在评论区讨论 💬

> _转载自 GitHub Trending，内容版权归原作者所有_

---
⏱️ 2026-07-09 08:01