Bring a task, a model baseline, an evaluation adapter, or feedback on the protocol. Small, reproducible contributions can make RSI experiments easier for more people to run and compare. Every run follows the same five steps:

1. Start

   Choose a task and model, then declare the run budget.

2. Iterate

   The agent revises its solution, prompts, or tools over repeated rounds.

3. Accept

   Use validation to check whether a change improves on the starting point.

4. Stop

   End at the declared budget or round limit, and record resources used.

5. Test

   Score the selected final solution once on held-out test data.