Recursive Language Models | Alex L. Zhang

We propose Recursive Language Models (RLMs), an inference strategy where language models can decompose and recursively interact with input context of unbounded length through REPL environments.

Recursive Language Models | Alex L. Zhang Recursive Language Models We propose Recursive Language Models (RLMs), an inference strategy where language models can decompose and recursively interact with input context of unbounded length through REPL environments. The full paper is now available here: https://arxiv.org/abs/2512.24601 . You can find the official codebase for Recursive Language Models (RLMs) here: https://github.com/alexzhang13/rlm tl;dr benchmark by more than **double** the number of correct answers, and is **cheaper** per query on average! On an offline retrieval task (BrowseComp

saved by

• Elizabeth Qiu
• abinaya dinesh
• Ratan Kaliani
• Linda
• Benedict Neo
• Lydia Nottingham
• Timothy Kostolansky
• Julian H
• Ishan Mukherjee
• Zifan Wang
• Jack Zheng

related reading

• MIT CSAIL Explains: Recursive Language Modelsyoutube.com
• Recursive Language Models ("RLMs")whynowtech.substack.com
• [2511.08579] Training Language Models to Explain Their Own Computationsarxiv.org
• [2510.13786] The Art of Scaling Reinforcement Learning Compute for LLMsarxiv.org
• RLMs are Compositional Generalizers with Alex Zhang from MITyoutube.com
• Training Language Models to Explain Their Own Computationsarxiv.org
• Recursive Language Models — Alex Zhang, MIT PhDyoutube.com
• [2005.11401] Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasksarxiv.org
• Recursive Language Models: the paradigm of 2026primeintellect.ai
• Language Models can Solve Computer Tasksarxiv.org
• Alex L. Zhangalexzhang13.github.io
• Self-Adapting Language Modelsarxiv.org