Glossary · Term

RAO

← all terms

Definition

A training method that teaches an AI agent to spawn copies of itself for sub-tasks and learn from the whole tree of attempts.

Recursive Agent Optimization, a training framework in which a single shared policy learns to recursively delegate sub-tasks to child agent instances, with per-node local rewards combining own-task success with average child success.

Also called: Recursive Agent Optimization

Mentioned in 1 episode

  1. 028
    Teaching a Model to Hire Copies of Itself: Recursive Agent Optimization