Model internals encode rich information about how a large language model (LLM) processes its training data; however, post-training data engineering largely relies on external signals and ignores rich intrinsic signals lying in model internals. We propose SAERL, a data engineering framework for LLM reinforcement learning (RL). It models three intrinsic data properties: diversity, difficulty, and quality, using model internals extracted with Sparse Autoencoder (SAE), an advanced mechanistic interpretability tool. Each property grounds a concrete data engineering operation: SAE-space clustering with moderate batch mixing for batch diversity control, a difficulty proxy for easy-to-hard curriculum ordering, and a quality probe for data filtering. SAERL improves average accuracy by 3.00% over vanilla GRPO and reaches target accuracy with 20% fewer training steps on Qwen2.5-Math-1.5B, with consistent gains across model scales and RL algorithms. Experiments show that SAE transfers effectively across model families and scales, serving as a lightweight and reusable data engineering tool. These results demonstrate that model internals are a powerful and practical source of signals for post-training data engineering.

翻译：模型内部编码了大语言模型（LLM）处理训练数据时的丰富信息；然而，后训练数据工程主要依赖外部信号，忽视了模型内部蕴含的丰富内在信号。我们提出SAERL——一种面向LLM强化学习（RL）的数据工程框架。该框架利用先进的可解释性工具稀疏自编码器（SAE）提取的模型内部信号，建模三种数据内在属性：多样性、难度与质量。每种属性均对应具体的数据工程操作：基于SAE空间聚类的适度批次混合以控制批次多样性、用于简单到困难课程排序的难度代理指标，以及用于数据过滤的质量探测算法。SAERL在Qwen2.5-Math-1.5B上相比原始GRPO平均准确率提升3.00%，并以减少20%训练步数达到目标准确率，且在不同模型规模与RL算法中均取得一致性增益。实验表明，SAE可跨模型族与规模有效迁移，成为轻量级可复用的数据工程工具。这些结果证明，模型内部信号是后训练数据工程中强大且实用的信号来源。