新年伊始，MIT CSAIL 的一纸论文在学术圈引发了不小的讨论。Alex L． Zhang 、 Tim Kraska 与 Omar Khattab 三位研究者在 arXiv 上发布了一篇题为《Recursive Language Models》的论文，提出了所谓“递归语言模型”（Recursive Language Models，简称 RLM）的推理策略。 早在 2025 年 10 月 ...

Researchers at MIT's CSAIL published a design for Recursive Language Models (RLM), a technique for improving LLM performance on long-context tasks. RLMs use a programming environment to recursively ...

最近一篇关于递归语言模型的论文《Recursive Language Models》引发了热议。有人称之为“AI记忆的终极解决方案”，也有人认为这不过是“换了马甲的RAG”。真相究竟如何？ 先说背景。大模型的上下文窗口一直是个老大难问题。厂商们比拼谁的窗口更大——“我们 ...

A genetic mutation that slowed down the development of the prefrontal cortex (PFC) in two or more children may have triggered a cascade of events leading to acquisition of recursive language and ...

Recursive language models (RLMs) are an inference technique developed by researchers at MIT CSAIL that treat long prompts as an external environment to the model. Instead of forcing the entire prompt ...

Recursion—the computational capacity to embed elements within elements of the same kind—has been lauded as the intellectual cornerstone of language, tool use and mathematics. A multi-institutional ...