# JAZ framework lets LLMs run complex tasks with minimal code

Digest AI · Agents & Tools · published 2026-09-24T04:00:00Z

Canonical: https://digestai.news/story/jaz-framework-lets-llms-run-complex-tasks-with-minimal-code

## Summary

Researchers introduced JAZ, a lightweight agent framework that lets language models handle tasks usually requiring extra systems like memory or self-improvement. The framework uses a single `invoke` primitive, where the LLM generates executable code on the fly, including recursive calls. JAZ avoids custom tools or external systems, relying only on prompting.

JAZ outperformed existing agents like Letta (MemGPT) by 8% on long-term recall tasks in the StuLife benchmark, using half the resources. It also beat ACE by 4% on self-improvement tasks in AppWorld, the authors claim. The paper argues that a minimalist design—just the agent loop plus constraints—can replace specialized systems for many workflows.

## Key points

- JAZ uses an `invoke` primitive where LLMs generate executable code without manual tool design
- Outperformed Letta (MemGPT) by 8% on recall tasks at half the cost in StuLife benchmark
- Beat ACE by 4% on self-improvement tasks in AppWorld, per the authors

## Why it matters

JAZ challenges the need for complex agent architectures by showing a simple loop with code generation can match or exceed specialized systems. It could reduce engineering overhead for long-term tasks and self-improvement.

## Sources

1. [Harness as a Language: A Minimalist Agent Framework With Maximal Expressivity](https://arxiv.org/abs/2609.26891) (arXiv cs.AI, 2026-09-24, primary source)

## Cite

Digest AI, "JAZ framework lets LLMs run complex tasks with minimal code", 24 September 2026, https://digestai.news/story/jaz-framework-lets-llms-run-complex-tasks-with-minimal-code

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/jaz-framework-lets-llms-run-complex-tasks-with-minimal-code.json