MIT CSAIL 提出 JAZ：只用一个 invoke 原语构建自改进智能体框架
MIT CSAIL 的 JAZ 框架只用一个 invoke 原语就搞定记忆和自我改进，跑分还便宜一半，写 agent 的朋友可以看看这篇论文。
MIT CSAIL 的论文介绍 JAZ 智能体框架，核心只有一个原语 invoke。LLM 自己写代码，可递归调用 invoke，并把输入和历史当作代码环境中的变量。在 StuLife 的记忆密集部分，纯提示、无记忆系统的 JAZ 以一半成本超过 Letta（MemGPT）8%；在 AppWorld 上以更低成本超过自改进方法 ACE 4%。记忆与自我改进都由智能体在循环内写代码实现，钩子负责约束和监控。
Keep your agent harness minimal, folks. This paper from MIT CSAIL shows why. (bookmark it) While being very minimal it looks effective and promising for building self-improving agents. They present JAZ, an agent framework with one primitive, invoke. The LLM writes code, can call invoke recursively, and sees all of its inputs and history as variables in the code environment. With prompting only and no memory system, it beats Letta (MemGPT) by 8% at half the cost on the recall-heavy part of StuLife. On AppWorld it beats ACE, a self-improvement method, by 4% at lower cost. Memory and self-improvement are usually built as separate subsystems. Here both are code the agent writes inside the loop, and hooks handle the constraints and monitoring you want to enforce. Paper: arxiv.org/abs/2609.26891 Explore Paper: academy.dair.ai/papers/harness… 💬 13 🔄 4 ❤️ 27 👀 2636 📊 19 ⚡
