elvis@omarsar0 · X推文聚焦于一篇探讨AI代理（Agent）开发框架的百页报告，其核心主张是“代码作为代理框架”具有重要潜力。报告总结了相关方法与应用，并论证该路径可能推动更广泛的科学框架工程。论文进一步提出，未来的智能系统必须具备四项关键特性：可执行、可检查、有状态以及受控。报告旨在为构建有效AI代理提供参考，并推荐相关学习资源。
// Code as Agent Harness //
100+ page report on all things related to agent harnesses.
（bookmark it）
In particular， the survey summarizes methods and applications of code as agent harness.
This paper makes a strong case that code-as-harness might be the key to moving us towards a broader science harness engineering.
Is code all you need？ Maybe.
Regardless， the paper argues that future systems must have the following four properties： executable， inspectable， stateful， and governed.
Paper： https://arxiv.org/abs/2605.18747
Learn to build effective AI agents in our academy： https://academy.dair.ai/