---
id: 20261027-T0-12
title: "RSI-Opt：让LLM代理在训练中自我改进优化器设置"
title_en: "RSI-Opt: LLM Agents Recursively Self-Improve Optimizer Settings During Training"
url: https://ai.daily.yangsir.net/daily/20261027-T0-12
issue_date: 2026-10-27
publish_date: 2026-10-26T04:00:00.000Z
category: research
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2610.32026
---

# RSI-Opt：让LLM代理在训练中自我改进优化器设置

传统神经网络训练依赖预设的优化配方，RSI-Opt提出用LLM代理监控训练动态并随训练进程调整优化器设置。论文指出固定策略的代理无法积累经验，因此引入递归自我改进机制，让代理从自身调整历史中学习。该方法的目标是减少人工调参，让训练过程根据实际动态自适应。目前结果来自arXiv预印本，尚未经过同行评审。

## English Version

**RSI-Opt: LLM Agents Recursively Self-Improve Optimizer Settings During Training**

Conventional neural network training follows a predefined optimization recipe. RSI-Opt proposes an LLM agent that monitors training dynamics and adjusts optimizer settings as training progresses. The authors note that a fixed agent policy cannot accumulate experience, so they add a recursive self-improvement mechanism that lets the agent learn from its own adjustment history. The goal is to reduce manual tuning and make training adapt to observed dynamics. The work is an arXiv preprint and has not been peer-reviewed.

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2610.32026)

**详情页**：https://ai.daily.yangsir.net/daily/20261027-T0-12

---

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