# MIT CSAIL paper introduces JAZ, a one-primitive agent framework

JAZ lets an LLM write code and recursively call a single invoke primitive, with inputs and history exposed as variables. With prompting only and no memory system, the paper reports an 8% gain over Letta (MemGPT) at half the cost on the recall-heavy part of StuLife, and a 4% gain over ACE at lower cost on AppWorld.

Language: en
Time zone: America/Los_Angeles
Current time (UTC, cached as of): 2026-11-17T15:24:00.000Z
Query date (America/Los_Angeles): 2026-11-17

HTML: https://didcodexreset.com/news/99d69b87d1da474a9ef575b6.html

Content language: en
Localization state: sameLanguage

Source: elvis · Published 9/26/2026, 05:51:54

A paper from MIT CSAIL introduces JAZ, an agent framework built around one primitive, invoke. The model writes code, can call invoke recursively, and sees its inputs and history as variables in the code environment. Memory and self-improvement are code the agent writes inside the loop, while hooks handle constraints and monitoring.

With prompting only and no memory system, the paper reports that JAZ 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.

The work is available as an [arXiv paper](https://arxiv.org/abs/2609.26891) and is also listed on [DAIR.AI Academy](https://academy.dair.ai/papers/harness-as-a-language-a-minimalist-agent-framework-with-maximal-expressivity-2609.26891).

Tags: JAZ, MIT CSAIL, AI agents, StuLife, AppWorld

[View original post](https://x.com/omarsar0/status/2103826930181308720)
