Automating harness evolution, using an LLM to propose and keep edits to an agent's prompts, tools, and control flow based on scores from a fixed set of tasks, is a fast-growing shortcut for the manual work of harness engineering. The…
In the News: September 26, 2026 (Extra 3)
A Google-led study finds automated agent-harness evolution overfits its benchmark, and tests a regularized version that still generalizes.
Extra edition
Machine-readable
Download Markdown