# Self-improving models · Oxagen Research

Source: https://oxagen.sh/blog/pillars/self-improving-models

[Research](https://oxagen.sh/blog) · Pillar

# Self-improving models

Models that train on their own output.

Research on models that learn from their own reasoning and score their own answers. Posts also cover the limits the research keeps finding, such as model collapse, where training on its own output makes a model worse, and self-correction that fails without outside feedback.

## 2 posts in Self-improving models

[](https://oxagen.sh/blog/the-limits-of-self-correction-and-model-collapse)

*   [Self-improving models](https://oxagen.sh/blog/pillars/self-improving-models)
*   [AI agents](https://oxagen.sh/blog/pillars/ai-agents)

### [A model cannot grade its own homework](https://oxagen.sh/blog/the-limits-of-self-correction-and-model-collapse)

Without outside feedback, self-correction fails, and a model trained on its own output gets worse. This post covers what the collapse and verifier research says to do instead.

September 9, 2026 · 8 min read

[](https://oxagen.sh/blog/self-improving-models-from-star-to-self-rewarding)

*   [Self-improving models](https://oxagen.sh/blog/pillars/self-improving-models)

### [From STaR to DeepSeek-R1: what self-improvement means](https://oxagen.sh/blog/self-improving-models-from-star-to-self-rewarding)

A vendor says the model improves itself. This is the research behind that claim, the signal that drives each training loop, and what stops each one.

September 9, 2026 · 8 min read