# RLM Agents live healthier when they talk via Structured Outputs

**@neural_avb** · X Article

![RLM Agents live healthier when they talk via Structured Outputs](https://pbs.twimg.com/media/HKSAAbeaYAADNTk.jpg)

We got one goal today: understand one of the common failure modes of Recursive Language Models, and a simple cool way to reduce it.
Recursive Language Models (RLMs) let a model answer questions over a

_Article preview only — see the source for the full article._

**Source:** [https://x.com/neural_avb/status/2063907440509571354](https://x.com/neural_avb/status/2063907440509571354)