Google WikiSkill：将Agent经验转化为持久技能库
This WikiSkill paper from Google is a must-read.
Agent持久记忆与技能演化是核心方向，这篇论文给出了具体的自动化框架与实证效果，值得深入研读。
This WikiSkill paper from Google is a must-read.
Google 的这篇 WikiSkill 论文是必读之作。
At a high level, it shows the effectiveness of persistent agents, knowledge bases, and skills.
从宏观层面来看，它展示了持久化智能体（persistent agents）、知识库和技能（skills）的有效性。
@karpathy popularized LLM Wikis.
@karpathy 普及了 LLM 维基（LLM Wikis）。
But this paper provides an actual framework for how agents can tap into a wiki of skills that evolve.
但这篇论文提供了一个实际的框架，说明智能体如何接入不断演化的技能维基。
What's fascinating to me is how this can complement your agents.
让我着迷的是，这如何能补充你的智能体。
LLMs can only learn so much about the world. External knowledge is crucial to get agents to do tasks efficiently and accurately in the real world.
LLM 对世界的了解是有限的。外部知识对于让智能体在现实世界中高效、准确地完成任务至关重要。
So this is why I think this paper is an important one, as it tries to fix some of the common issues you face when building and maintaining skills.
因此，我认为这篇论文很重要，因为它试图解决你在构建和维护技能时面临的一些常见问题。
It automatically leverages your agent runs, persists that knowledge into a wiki, and uses all of that to keep skills properly tuned for reusability.
它自动利用你的智能体运行记录，将知识持久化到维基中，并利用所有这些来保持技能的适当调优，以便重用。
The most impressive part of WikiSkill is that it appears to be model-agnostic. In other words, it works across different tasks and models.
WikiSkill 最令人印象深刻的部分在于它似乎是模型无关的（model-agnostic）。换句话说，它适用于不同的任务和模型。
The evolved skills can even transfer to smaller models that sometimes outperform bigger models. This hints at the effectiveness of persistent agents, via persistent knowledge bases and evolved skills.
演化后的技能甚至可以迁移到较小的模型上，有时甚至优于较大的模型。这暗示了通过持久化知识库和演化技能，持久化智能体的有效性。
The big question for me is how evolved skills coming out of WikiSkill transfer to the next generation of models. I think they will provide a huge advantage and be leveraged in more interesting ways by smarter models.
对我来说最大的问题是，来自 WikiSkill 的演化技能如何迁移到下一代模型。我认为它们将提供巨大的优势，并被更聪明的模型以更多有趣的方式加以利用。
The practical takeaway here is that we should all be thinking about how to build persistent knowledge bases across our companies and projects. And how to use that to upgrade and evolve our skills.
这里的实际启示是，我们都应该思考如何在我们的公司和项目中构建持久化知识库。以及如何利用这些来升级和演化我们的技能。
Join our community to discuss this paper more: https://academy.dair.ai/papers/wikiskill-compiles-agent-experience-into-a-persistent-wiki-2608.27454
加入我们的社区，进一步讨论这篇论文：https://academy.dair.ai/papers/wikiskill-compiles-agent-experience-into-a-persistent-wiki-2608.27454
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力