RiM 解决了自回归推理计算效率低的问题，做模型推理优化的研究者可以直接参考其两阶段训练方法。
论文提出 Reasoning in Memory (RiM) 方法，用固定内存块替代自回归生成推理步骤，让大模型在单次前向传播中完成潜在推理。该方法受人类工作记忆启发，通过两阶段课程训练：先预测显式推理步骤来锚定内存块，再丢弃步骤级监督直接优化最终答案。实验表明，RiM 在多个推理基准上匹配或超越现有潜在推理方法，且计算效率更高。这为提升大模型推理能力提供了新思路，尤其适合需要高效推理的场景。
Unlocking the Working Memory of Large Language Models for Latent Reasoning
To improve the reasoning capabilities of large language models, test-time compute is typically scaled by generating intermediate tokens before the final answer. However, this couples reasoning to autoregressive generation and thereby conflates internal computation with external communication. In contrast, human cognition can use working memory to hold and manipulate information internally without the need to externalize intermediate thoughts. Drawing on this principle, we introduce Reasoning in Memory (RiM), a latent reasoning method that replaces the autoregressive generation of reasoning steps with memory blocks. These memory blocks are fixed sequences of special tokens that unlock the working-memory capacity of large language models. Since they are fixed rather than generated, they can be processed in a single forward pass, enabling compute-efficient latent reasoning. To operationalize these memory blocks, we employ a two-stage curriculum. First, we ground them by predicting explicit reasoning steps after each memory block. Second, we discard this step-level supervision and iteratively refine the final answer after each memory block. Our experiments on reasoning benchmarks show that, across language models of different families and sizes, RiM matches or exceeds existing latent reasoning methods while avoiding the autoregressive generation of thoughts. These results demonstrate that large language models can be trained to use working memory as an effective mechanism for latent reasoning.