论文提出持久化Agent架构：模型与宿主可替换
What a super interesting paper this one is.
Agent持久化是迈向长期智能体的关键一步，这篇论文给出了具体的解耦架构和迁移协议，值得做Agent基建的同学深入研究。
What a super interesting paper this one is.
这篇论文非常有趣。
They propose an architecture for agents that outlive their model, harness and host.
他们提出了一种智能体架构，使智能体能够超越其模型、运行环境和宿主而持续存在。
Today we describe an agent by whatever model and harness it happens to run on. That works for a single session. It says very little about an agent that runs for months and gets moved to a new model, a new harness, or a new machine along the way.
今天，我们根据智能体实际运行的模型和运行环境来描述它。这适用于单个会话。但对于运行数月并在过程中迁移到新模型、新运行环境或新机器的智能体，这种描述方式几乎毫无意义。
The paper splits an agent in two.
该论文将智能体分为两部分。
One half is the agent itself, and it persists. Its identity, its private memory, and its own code with version history.
一半是智能体本身，它具有持久性。包括其身份、私有记忆以及带有版本历史的自有代码。
The other half is plumbing you can replace. The model doing the reasoning, the harness running it, the server hosting it, and the ways people reach it such as chat, an API, or a UI.
另一半是可替换的基础设施。包括负责推理的模型、运行它的运行环境、托管它的服务器，以及人们访问它的方式，如聊天界面、API 或用户界面。
Swap the plumbing and you have moved the agent rather than built a new one, as long as the handoff is authorized and keeps the record of where it came from.
更换基础设施即可实现智能体的迁移，而非重新构建一个新的智能体，前提是交接过程经过授权并保留了其来源记录。
The handoff is six steps. Pause the agent, save its state, check the save is valid, attach it to the new setup, load the state back, then let it run again.
交接过程包含六个步骤：暂停智能体、保存其状态、验证保存的有效性、将其连接到新环境、重新加载状态，然后让其再次运行。
They ran the frozen public release on a clean machine and it passed 833 core tests plus 92 more for providers and libraries. They also swapped model versions, interfaces and physical hosts on live deployments.
他们在干净的机器上运行了冻结的公开版本，通过了 833 项核心测试，此外还有 92 项针对提供程序和库的测试。他们还交换了实时部署中的模型版本、接口和物理主机。
The authors are careful about what this proves. It shows you can move an agent without breaking it mechanically. Whether the agent still behaves like itself afterwards is a separate question.
作者对这一结果所证明的内容持谨慎态度。它表明你可以机械地移动智能体而不破坏它。但智能体之后是否仍能保持其行为一致性，则是另一个独立的问题。
Paper: https://arxiv.org/abs/2609.00546
论文：https://arxiv.org/abs/2609.00546
Chat with Paper: https://academy.dair.ai/papers/runtime-independent-persistent-agents-preserving-identity-memory-and-code-across-2609.00546
与论文对话：https://academy.dair.ai/papers/runtime-independent-persistent-agents-preserving-identity-memory-and-code-across-2609.00546
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