这篇论文为AI智能体架构提供了一个清晰的设计原则——用代码作为核心工作层，做智能体系统或工具链的开发者值得一读，能帮你理解为什么代码比纯文本更适合作为智能体的“思考环境”。
Meta、斯坦福和伊利诺伊大学联合发表了一篇综述论文，核心观点是：当代码成为AI智能体的主要工作层时，智能体表现更优。论文指出，仅靠LLM做文本预测，长任务容易丢失状态、隐藏错误，将计划转化为行动的方式也很脆弱。真正的进步不是“AI写代码”，而是“AI把代码当作它思考的环境”。作者将围绕模型构建的工具、记忆、沙箱、检查和反馈循环称为“智能体马具”，而代码应处于这个马具的中心，因为代码可以被运行、检查、保存、编辑和共享。论文总结了一个跨领域的模式：代码帮助智能体通过可执行步骤推理、通过工具调用或控制程序行动、通过测试、追踪、日志、仓库和模拟器建模环境。
This Meta + Stanford + Illinois survey paper argue…
This Meta + Stanford + Illinois survey paper argues that AI agents work better when code becomes their main working layer.
The problem is that an LLM by itself is mostly a text predictor, so long tasks can lose state, hide mistakes, and turn plans into actions in fragile ways.
The real advance is not “AI writes code,” but “AI uses code as the environment it thinks inside.”
The authors call the surrounding system an agent harness, meaning the tools, memory, sandboxes, checks, and feedback loops that turn a model into an agent.
Their core idea is that code should sit at the center of that harness, because code can be run, inspected, checked, saved, edited, and shared.
Tests become sensors.
Repositories become memory.
Logs become history.
Sandboxes become boundaries.
A generated script is no longer merely an answer; it is a handle the system can run, check, revise, share, and roll back.
The main finding is a pattern across many fields: code helps agents reason through executable steps, act through tool calls or control programs, and model environments through tests, traces, logs, repositories, and simulators.
----
Paper Link – arxiv. org/abs/2605.18747
Paper Title: "Code as Agent Harness"