Google open-sources Harness2, which rewrites agent harnesses at test time

Google Research released Harness2 under Apache-2.0, a framework that rewrites an agent's harness at test time. One refinement step lifted GLM-5 by 11.5 points on WorkBuddy-Bench with no weight updates.

Why it matters: Gains from improving the scaffolding around a model, not the model itself, are cheap and usable with any open weights. It reinforces that harness design is a major performance lever for agents.