MIT 论文提出 JAZ 极简 Agent 框架，在长程任务上以更低成本超过 Letta 和 ACE
MIT 论文《Harness as a Language: A Minimalist Agent Framework With Maximal Expressivity》提出 JAZ 框架，只保留基础 Agent 循环，让模型编写 Python、把自己作为子智能体调用，并把提示词和完整历史当作可搜索、可传递给子智能体的代码变量，避免手工复制上下文造成指令丢失。
New MIT paper says give your agent its own history and prompt as code variables it can search and pass to subagents, and a plain agent loop beats purpose-built memory and self-improvement systems at lower cost.
Agents lose instructions when they copy context into subagents by hand, and passing the prompt and history by reference let JAZ beat dedicated memory and self-tuning systems.
Long-term memory and self-improvement usually need extra systems like Letta or ACE, which add cost and break when tasks don't fit their design.
JAZ keeps only the loop. The model writes Python, calls itself as a subagent, and sees its prompt and full history as variables it can pass along without loss.
On StuLife tasks that needed facts from over 50 tasks earlier, JAZ passed 69.9% against 61.8% for Letta, at less than half the cost. Improving itself across 417 AppWorld tasks, it completed 74.2% against 69.9% for ACE, again for less.
– arxiv. org/abs/2609.26891
Title: "Harness as a Language: A Minimalist Agent Framework With Maximal Expressivity"
来源：rohanpaul_ai · x.com