Theory-to-experiment lab for search stability in long-running agents under finite context, with exact simulator tests and lightweight mechanistic probe tasks.
-
Updated
Mar 12, 2026 - Python
Theory-to-experiment lab for search stability in long-running agents under finite context, with exact simulator tests and lightweight mechanistic probe tasks.
Add a description, image, and links to the scientific-audit topic page so that developers can more easily learn about it.
To associate your repository with the scientific-audit topic, visit your repo's landing page and select "manage topics."