Skip to content

Glossary · RSI and self-improvement

Training-time self-iteration

Self-improvement in which self-generated data, rewards, or teacher signals update the model's weights in a training phase.

Defined in

Handbook · Agents and self-improvementSelf-improvement and evaluator co-evolutionWhen a system can change what defines "better", the evaluator becomes the load-bearing wall. What changes, who validates, how loops fail.

See it in the full glossary →