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

related reading

• Recursive Language Models ("RLMs")whynowtech.substack.com
• Recursive Language Models: the paradigm of 2026primeintellect.ai
• GLM-5.2: Built for Long-Horizon Tasksz.ai
• Introduction to Large Language Models | Machine Learning | Google for Developersdevelopers.google.com
• Generalizing an LLM from 8k to 1M Context using Qwen-Agent | Qwenqwenlm.github.io
• The huge potential implications of long-context inferenceepochai.substack.com
• Extending Context is Hard | kaiokendevkaiokendev.github.io
• Long Context RAG Performance of LLMs | Databricks Blogdatabricks.com
• QwenLong-L1.5: Post-Training Recipe for Long-Context Reasoning and Memory Managementarxiv.org
• A History of Large Language Modelsgregorygundersen.com
• Alex L. Zhangalexzhang13.github.io
• gemini_v1_5_report.pdfstorage.googleapis.com