Unlocking the Working Memory of Large Language Models for Latent Reasoning 事件

Unlocking the Working Memory of Large Language Models for Latent Reasoning arXiv:2605.30343v1 Announce Type: new Abstract: 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 informa