---
id: 20261016-T0-12
title: "Harness^2：递归自改进框架让LLM智能体适应开放世界"
title_en: "Harness^2 Enables Recursive Self-Improvement for LLM Agents in Open Worlds"
url: https://ai.daily.yangsir.net/daily/20261016-T0-12
issue_date: 2026-10-16
publish_date: 2026-10-15T04:00:00.000Z
category: research
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2610.14224
---

# Harness^2：递归自改进框架让LLM智能体适应开放世界

arXiv发布论文Harness^2，提出递归智能体框架以应对开放世界中的自改进挑战。研究指出，LLM智能体的能力不仅取决于底层模型，还取决于执行框架（harness）。递归自改进（RSI）可自动演化这些框架，但在开放环境中部署面临困难。Harness^2通过递归机制让智能体在开放世界中持续优化自身执行框架，为构建能适应未知任务的自主智能体提供了新思路。

## English Version

**Harness^2 Enables Recursive Self-Improvement for LLM Agents in Open Worlds**

arXiv paper Harness^2 proposes a recursive agent harnessing framework for open-world self-improvement. The research notes that LLM agent capabilities depend not only on underlying models but also on execution harnesses. Recursive self-improvement (RSI) can automatically evolve these harnesses, but deployment in open-world settings remains challenging. Harness^2 uses recursive mechanisms to let agents continuously optimize their execution frameworks in open environments, offering a new approach for building autonomous agents that adapt to unknown tasks.

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2610.14224)

**详情页**：https://ai.daily.yangsir.net/daily/20261016-T0-12

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*