Recursive Language Models

Follow this topic Ask about this topic

Recursive Language Models study how language models can solve problems through repeated computation, either by invoking themselves on subtasks or by reusing layers to refine latent states. Approaches include code- and context-based recursive agents, looped transformers, adaptive-depth computation, and methods for stabilizing, training, or compressing recurrent models. They are evaluated on long-context retrieval, mathematical and algorithmic reasoning, code generation, and tool-use tasks. A central tension is that added depth can improve difficult reasoning but also increase latency, memory use, instability, or overthinking, while its effects on knowledge retention and safety remain important concerns.

Latest papers

65 papers29 papers in the last four weeks, up 222% on the four weeks before. 0.2% of all new papers.

Recursive Language Models Meet Uncertainty: The Surprising Effectiveness of Self-Reflective Program Search for Long Context
Mar 7, 2026Keivan Alizadeh, Parshin Shojaee, Minsik Cho +1Long-Context Language Model Inference Recursive Language Models
Apple
Think, But Don't Overthink: Reproducing Recursive Language Models
Mar 3, 2026Daren WangRecursive Language Models Overthinking in Language Models
The Chinese University of Hong Kong
Recursive Models for Long-Horizon Reasoning
Mar 2, 2026Chenxiao Yang, Nathan Srebro, Zhiyuan LiRecursive Language Models Language Modeling
Toyota Technological Institute at Chicago
Recursive language models for jailbreak detection: a procedural defense for tool-augmented agents
Feb 18, 2026Doron ShavitJailbreak Detection LLM Security
Scaling Latent Reasoning via Looped Language Models
Oct 29, 2025Rui-Jie Zhu, Zixuan Wang, Kai Hua +30Language Model Pretraining Implicit Reasoning in Language Models
ByteDance Seed · UC Santa Cruz · Princeton University +8

Mar 7, 2026J/K move · Enter open · S save

Recursive Language Models Meet Uncertainty: The Surprising Effectiveness of Self-Reflective Program Search for Long Context

Keivan Alizadeh, Parshin Shojaee, Minsik Cho, Mehrdad Farajtabar

Apple

Long-Context Language Model Inference Recursive Language Models Metacognition in Language Models

Open paper AskPDF arXiv

Long-context handling remains a core challenge for language models: even with extended context windows, models often fail to reliably extract, reason over, and use the information across long contexts. Recent works like Recursive Language Models (RLM) have approached this challenge by agentic way of decomposing long contexts into recursive sub-calls through programmatic interaction at inference. While promising, the success of RLM critically depends on how these context-interaction programs are selected, which has remained largely unexplored. In this paper, we study this problem and introduce SRLM, a framework that augments programmatic context interaction with uncertainty-aware Self-Reflection. SRLM leverages three intrinsic signals: self consistency, reasoning length, and verbalized confidence. These serve as complementary indicators of a model's internal uncertainty, and the model uses them to evaluate and compare candidate context-interaction programs. Extensive experiments across diverse benchmark datasets, context lengths, and backbone models, show that SRLM consistently outperforms state-of-the-art baselines, yielding up to 22% improvement over RLM under the same time budget. Our findings show that recursion itself is not the primary driver of performance in RLM, and a simple self-reflective program search can match or surpass RLM without requiring self-query or explicit recursion mechanisms. We find that for context lengths within the model's window, RLMs with recursion often degrade performance relative to the base model, whereas SRLM yields consistent gains across both short and long contexts. We also find that RLM is less effective in tasks with semantically intensive nature, where heuristic program search is insufficient and broader contextual understanding is required, while self-reflection in SRLM provides a semantic signal that better steers reasoning in these scenarios.

Latest papers

Recursive Language Models Meet Uncertainty: The Surprising Effectiveness of Self-Reflective Program Search for Long Context

Think, But Don't Overthink: Reproducing Recursive Language Models

Recursive Models for Long-Horizon Reasoning

Recursive language models for jailbreak detection: a procedural defense for tool-augmented agents

Scaling Latent Reasoning via Looped Language Models