跳到正文
arXiv cs.AI· Dewu Zheng, Yang Ye, Hongyu Zhang, Jun Yu, Yanlin Wang·· 2 小时前AI 评分47

RSI-Prime:训练模型去训练模型的数据集

RSI-Prime: Training Models to Train Models

AI 导读

研究者构建 RSI-Prime 数据集以提升大语言模型的模型训练能力,包含七类任务的 350 条完整实验轨迹,并对决策进行细粒度标注与决策级损失掩码。在 PostTrainBench 上,基于该数据集训练的 GLM-5.3 整体性能较原模型相对提升 31.95%,为递归自我改进(RSI)系统提供了路径。

正文 · 原文

View PDF HTML (experimental)

Abstract: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.
Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
Cite as: arXiv:2611.23138 [cs.AI]
  (or arXiv:2611.23138v1 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2611.23138

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Dewu Zheng [view email]
[v1] Tue, 17 Nov 2026 17:55:30 UTC (317 KB)

来源:arXiv cs.AI · arxiv.org