August 2026

How Deep Should a Recursive Language Model Recurse?

Depth 1 captured most of the gain at flat or lower cost. Depth 2 and 3 paid off only on quadratic aggregation with a frontier coder, and hurt weak coders and simple retrieval. The evidence at each depth and a decision rule.

August 2026

How Do You Evaluate a Recursive Language Model?

Accuracy alone tells you almost nothing. The complexity class of the benchmark, the depth-0 ablation, the latency tail, and the answer-extraction failure rate are what decide the number.

August 2026

What Are the Limitations of Recursive Language Models?

The documented failure modes: base models that cannot write correct code, recursion depth that only pays off sometimes, brittle answer detection, and a long cost tail.

February 2026

Agent-to-Agent Recursive Knowledge Transfer

Everyone is writing about self-improvement loops. The real unlock is when one model teaches another -- not its outputs, but its learning process.

February 2026

LCM: When Someone Else Validates Your Paradigm

Voltropy's new paper doesn't compete with RLM. It builds on it, proves it works, and takes it further than we did.

February 2026

Why Context Windows Are the Wrong Abstraction

The industry spent five years making context windows bigger. RLMs suggest the entire framing was wrong from the start.

February 2026

The Decompose-Recurse-Aggregate Pattern Explained

A practitioner's guide to the core algorithmic pattern behind Recursive Language Models -- and why it mirrors how expert humans solve complex problems.

February 2026

RLM vs RAG: Two Approaches to the Long-Context Problem

Retrieval-Augmented Generation dominated the long-context conversation for three years. RLMs take a fundamentally different path. Here is where each one wins.

February 2026

Inference-Time Compute: The New Scaling Frontier

Training-time scaling dominated the last decade of AI progress. The next decade belongs to inference-time scaling -- and RLMs are a leading example of why.

February 2026

Real-World Applications for Recursive Language Models

From legal discovery to genomics, the tasks where RLMs create the largest performance gap over standard LLMs.

February 2026

Small Models, Big Contexts: The Efficiency Case for RLMs

How an 8B parameter model post-trained on 1,000 samples can rival GPT-5 on long-context tasks -- and what that means for cost and deployment.