exploratory-iteration

What problem does it solve?

This Skill addresses the challenge of implementing autocurriculum learning, enabling multi-step self-improvement without fixed depth.

Core Features & Use Cases

• Dynamic Task Space Expansion: Grows task space from intermediate states for continuous improvement.
• Selective Sampling: Selects most informative partial histories for continuation.
• Self-Divergence: Supports diverse approaches to problem-solving.
• Use Case: Ideal for tasks requiring multiple revision attempts, such as math problems or ML engineering tasks.

Quick Start

Use the exploratory-iteration skill to trigger an ExIt process for self-improvement in your task.