By Marco De Santis; work predating Nullsilver.
- What it is
- Compressing reasoning without breaking it
- Kind
- Research
- Status
- Earlier work
- Reading
- 1 min
A study on whether reasoning models can learn from compressed versions of their own outputs, reducing the tokens they use without losing the steps needed to solve a problem.
From the entry
The evaluations are small, and shorter traces alone are not enough to show that a model reasons better.


