跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.23138 · v1

RSI-Prime: Training Models to Train Models

RSI-Prime:训练模型去训练模型

首次提交 2026-11-18 01:55
版本更新 2026-11-18 01:55
雷达观测 2026-11-18 12:34
arXiv ↗PDF ↗

摘要

Enabling large language models (LLMs) to autonomously conduct training and improve target models is an important foundation for recursive self-improvement (RSI). As LLMs expand their role from being trained to conducting training, their model-training capability warrants dedicated study and systematic development. To this end, we construct RSI-Prime, a dataset for improving model-training capability, comprising 350 complete experimental trajectories across seven task categories. To help LLMs learn to make high-quality experimental decisions from training practice, we perform fine-grained decision identification and quality annotation, then apply decision-level loss masking to exclude supervision on low-quality behavior. Experiments with GLM-5.3 on PostTrainBench, a benchmark for autonomous post-training, show that training on RSI-Prime yields a 31.95% relative improvement in overall performance over the original GLM-5.3, highlighting a path toward future RSI systems in which models autonomously sustain their own advancement.

AI 论文解读

基于摘要 · 非全文审阅

作者构建了 RSI-Prime 数据集,用于提升大语言模型的模型训练能力,并在 PostTrainBench 上报告了 GLM-5.3 的性能相对提升。

正在读取账号与研究记录…

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-18 01:55 · 最新观测版本

RSI-Prime: Training Models to Train Models

Enabling large language models (LLMs) to autonomously conduct training and improve target models is an important foundation for recursive self-improvement (RSI). As LLMs expand their role from being trained to conducting training, their model-training capability warrants dedicated study and systematic development. To this end, we construct RSI-Prime, a dataset for improving model-training capability, comprising 350 complete experimental trajectories across seven task categories. To help LLMs learn to make high-quality experimental decisions from training practice, we perform fine-grained decision identification and quality annotation, then apply decision-level loss masking to exclude supervision on low-quality behavior. Experiments with GLM-5.3 on PostTrainBench, a benchmark for autonomous post-training, show that training on RSI-Prime yields a 31.95% relative improvement in overall performance over the original GLM-5.3, highlighting a path toward future RSI systems in which models autonomously sustain their own advancement.

查看此版本解读 →查看此版本原文 ↗